MOTIVATION: Protein structure generative models have seen a recent surge of interest, but meaningfully evaluating them computationally is an active area of research. While current metrics have driven useful progress, they do not capture how well models sample the design space represented by the training data. We argue for a protein Frechet Inception Distance (FID) metric to supplement current evaluations with a measure of distributional similarity in a semantically meaningful latent space. RESULTS: Our FID behaves desirably under protein structure perturbations and correctly recapitulates similarities between protein samples: it correlates with optimal transport distances and recovers FoldSeek clusters and the CATH hierarchy. Evaluating current protein structure generative models with FID shows that they fall short of modeling the distribution of PDB proteins. AVAILABILITY: Code is available at: https://github.com/ffaltings/protfid.

Diffusion models have emerged as a successful approach for molecular docking, but they often cannot model protein flexibility or generate nonphysical poses. We argue that both these challenges can be tackled by framing the problem as a transport between distributions. Still, existing paradigms lack the flexibility to define effective maps between such complex distributions. To address this limitation, we propose Unbalanced Flow Matching, a generalization of Flow Matching (FM) that allows trading off sample efficiency with approximation accuracy and enables more accurate transport. Empirically, we apply Unbalanced FM on flexible docking and structure relaxation, demonstrating our ability to model protein flexibility and generate energetically favorable poses. On the PDBBind docking benchmark, our method FlexDock improves the docking performance while increasing the proportion of energetically favorable poses from 30% to 73%.

Identifying variables responsible for changes to a biological system enables applications in drug target discovery and cell engineering. Given a pair of observational and interventional datasets, the goal is to isolate the subset of observed variables that were the targets of the intervention. Directly applying causal discovery algorithms is challenging: the data may contain thousands of variables with as few as tens of samples per intervention, and biological systems do not adhere to classical causality assumptions. We propose a causality-inspired approach to address this practical setting. First, we infer noisy causal graphs from the observational and interventional data. Then, we learn to map the differences between these graphs, along with additional statistical features, to sets of variables that were intervened upon. Both modules are jointly trained in a supervised framework, on simulated and real data that reflect the nature of biological interventions. This approach consistently outperforms baselines for perturbation modeling on seven single-cell transcriptomics datasets. We also demonstrate significant improvements over current causal discovery methods for predicting soft and hard intervention targets across a variety of synthetic data.

Accurate blind docking has the potential to lead to new biological breakthroughs, but for this promise to be realized, docking methods must generalize well across the proteome. Existing benchmarks, however, fail to rigorously assess generalizability. Therefore, we develop DockGen, a new benchmark based on the ligand-binding domains of proteins, and we show that existing machine learning-based docking models have very weak generalization abilities. We carefully analyze the scaling laws of ML-based docking and show that, by scaling data and model size, as well as integrating synthetic data strategies, we are able to significantly increase the generalization capacity and set new state-of-the-art performance across benchmarks. Further, we propose Confidence Bootstrapping, a new training paradigm that solely relies on the interaction between diffusion and confidence models and exploits the multi-resolution generation process of diffusion models. We demonstrate that Confidence Bootstrapping significantly improves the ability of ML-based docking methods to dock to unseen protein classes, edging closer to accurate and generalizable blind docking methods.

In light of the widespread success of generative models, a significant amount of research has gone into speeding up their sampling time. However, generative models are often sampled multiple times to obtain a diverse set incurring a cost that is orthogonal to sampling time. We tackle the question of how to improve diversity and sample efficiency by moving beyond the common assumption of independent samples. We propose particle guidance, an extension of diffusion-based generative sampling where a joint-particle time-evolving potential enforces diversity. We analyze theoretically the joint distribution that particle guidance generates, how to learn a potential that achieves optimal diversity, and the connections with methods in other disciplines. Empirically, we test the framework both in the setting of conditional image generation, where we are able to increase diversity without affecting quality, and molecular conformer generation, where we reduce the state-of-the-art median error by 13% on average.

The ability to engineer novel proteins with higher fitness for a desired property would be revolutionary for biotechnology and medicine. Modeling the combinatorially large space of sequences is infeasible; prior methods often constrain optimization to a small mutational radius, but this drastically limits the design space. Instead of heuristics, we propose smoothing the fitness landscape to facilitate protein optimization. First, we formulate protein fitness as a graph signal then use Tikunov regularization to smooth the fitness landscape. We find optimizing in this smoothed landscape leads to improved performance across multiple methods in the GFP and AAV benchmarks. Second, we achieve state-of-the-art results utilizing discrete energy-based models and MCMC in the smoothed landscape. Our method, called Gibbs sampling with Graph-based Smoothing (GGS), demonstrates a unique ability to achieve 2.5 fold fitness improvement (with in-silico evaluation) over its training set. GGS demonstrates potential to optimize proteins in the limited data regime. Code: https://github.com/kirjner/GGS

In this paper, we propose a novel approach to conformal prediction for language models (LMs) in which we produce prediction sets with performance guarantees. LM responses are typically sampled from a predicted distribution over the large, combinatorial output space of language. Translating this to conformal prediction, we calibrate a stopping rule for sampling LM outputs that get added to a growing set of candidates until we are confident that the set covers at least one acceptable response. Since some samples may be low-quality, we also simultaneously calibrate a rejection rule for removing candidates from the output set to reduce noise. Similar to conformal prediction, we can prove that the final output set obeys certain desirable distribution-free guarantees. Within these sets of candidate responses, we also show that we can also identify subsets of individual components---such as phrases or sentences---that are each independently correct (e.g., that are not ``hallucinations''), again with guarantees. Our method can be applied to any LM API that supports sampling. Furthermore, we empirically demonstrate that we can achieve many desired coverage levels within a limited number of total samples when applying our method to multiple tasks in open-domain question answering, text summarization, and radiology report generation using different LM variants.

Combining discrete and continuous data is an important capability for generative models. We present Discrete Flow Models (DFMs), a new flow-based model of discrete data that provides the missing link in enabling flow-based generative models to be applied to multimodal continuous and discrete data problems. Our key insight is that the discrete equivalent of continuous space flow matching can be realized using Continuous Time Markov Chains. DFMs benefit from a simple derivation that includes discrete diffusion models as a specific instance while allowing improved performance over existing diffusion-based approaches. We utilize our DFMs method to build a multimodal flow-based modeling framework. We apply this capability to the task of protein co-design, wherein we learn a model for jointly generating protein structure and sequence. Our approach achieves state-of-the-art co-design performance while allowing the same multimodal model to be used for flexible generation of the sequence or structure.

Computational screening of naturally occurring proteins has the potential to identify efficient catalysts among the hundreds of millions of sequences that remain uncharacterized. Current experimental methods remain time, cost and labor intensive, limiting the number of enzymes they can reasonably screen. In this work, we propose a computational framework for in-silico enzyme screening. Through a contrastive objective, we train CLIPZyme to encode and align representations of enzyme structures and reaction pairs. With no standard computational baseline, we compare CLIPZyme to existing EC (enzyme commission) predictors applied to virtual enzyme screening and show improved performance in scenarios where limited information on the reaction is available (BEDROC$_{85}$ of 44.69%). Additionally, we evaluate combining EC predictors with CLIPZyme and show its generalization capacity on both unseen reactions and protein clusters.

A significant amount of protein function requires binding small molecules, including enzymatic catalysis. As such, designing binding pockets for small molecules has several impactful applications ranging from drug synthesis to energy storage. Towards this goal, we first develop HarmonicFlow, an improved generative process over 3D protein-ligand binding structures based on our self-conditioned flow matching objective. FlowSite extends this flow model to jointly generate a protein pocket’s discrete residue types and the molecule’s binding 3D structure. We show that HarmonicFlow improves upon state-of-the-art generative processes for docking in simplicity, generality, and average sample quality in pocket-level docking. Enabled by this structure modeling, FlowSite designs binding sites substantially better than baseline approaches.

Discrete diffusion or flow models could enable faster and more controllable sequence generation than autoregressive models. We show that naive linear flow matching on the simplex is insufficient toward this goal since it suffers from discontinuities in the training target and further pathologies. To overcome this, we develop Dirichlet flow matching on the simplex based on mixtures of Dirichlet distributions as probability paths. In this framework, we derive a connection between the mixtures' scores and the flow's vector field that allows for classifier and classifier-free guidance. Further, we provide distilled Dirichlet flow matching, which enables one-step sequence generation with minimal performance hits, resulting in $O(L)$ speedups compared to autoregressive models. On complex DNA sequence generation tasks, we demonstrate superior performance compared to all baselines in distributional metrics and in achieving desired design targets for generated sequences. Finally, we show that our classifier-free guidance approach improves unconditional generation and is effective for generating DNA that satisfies design targets.

This paper focuses on using natural language descriptions to enhance predictive models in the chemistry field.Conventionally, chemoinformatics models are trained with extensive structured data manually extracted from the literature.In this paper, we introduce TextReact, a novel method that directly augments predictive chemistry with texts retrieved from the literature.TextReact retrieves text descriptions relevant for a given chemical reaction, and then aligns them with the molecular representation of the reaction.This alignment is enhanced via an auxiliary masked LM objective incorporated in the predictor training.We empirically validate the framework on two chemistry tasks: reaction condition recommendation and onestep retrosynthesis.By leveraging text retrieval, TextReact significantly outperforms state-ofthe-art chemoinformatics models trained solely on molecular data.

The use of mutual information as a tool in private data sharing has remained an open challenge due to the difficulty of its estimation in practice. In this paper, we propose InfoShape, a task-based encoder that aims to remove unnecessary sensitive information from training data while maintaining enough relevant information for a particular ML training task. We achieve this goal by utilizing mutual information estimators that are based on neural networks, in order to measure two performance metrics, privacy and utility. Using these together in a Lagrangian optimization, we train a separate neural network as a lossy encoder. We empirically show that InfoShape is capable of shaping the encoded samples to be informative for a specific downstream task while eliminating unnecessary sensitive information. Moreover, we demonstrate that the classification accuracy of downstream models has a meaningful connection with our utility and privacy measures.

The design of novel protein structures remains a challenge in protein engineering for applications across biomedicine and chemistry. In this line of work, a diffusion model over rigid bodies in 3D (referred to as frames) has shown success in generating novel, functional protein backbones that have not been observed in nature. However, there exists no principled methodological framework for diffusion on SE(3), the space of orientation preserving rigid motions in R3, that operates on frames and confers the group invariance. We address these shortcomings by developing theoretical foundations of SE(3) invariant diffusion models on multiple frames followed by a novel framework, FrameDiff, for estimating the SE(3) equivariant score over multiple frames. We apply FrameDiff on monomer backbone generation and find it can generate designable monomers up to 500 amino acids without relying on a pretrained protein structure prediction network that has been integral to previous methods. We find our samples are capable of generalizing beyond any known protein structure.

While unbiased machine learning models are essential for many applications, bias is a human-defined concept that can vary across tasks. Given only input-label pairs, algorithms may lack sufficient information to distinguish stable (causal) features from unstable (spurious) features. However, related tasks often share similar biases – an observation we may leverage to develop stable classifiers in the transfer setting. In this work, we explicitly inform the target classifier about unstable features in the source tasks. Specifically, we derive a representation that encodes the unstable features by contrasting different data environments in the source task. We achieve robustness by clustering data of the target task according to this representation and minimizing the worst-case risk across these clusters. We evaluate our method on both text and image classifications. Empirical results demonstrate that our algorithm is able to maintain robustness on the target task for both synthetically generated environments and real-world environments. Our code is available at https://github.com/YujiaBao/Tofu.

We develop a new approach to multi-label conformal prediction in which we aim to output a precise set of promising prediction candidates with a bounded number of incorrect answers. Standard conformal prediction provides the ability to adapt to model uncertainty by constructing a calibrated candidate set in place of a single prediction, with guarantees that the set contains the correct answer with high probability. In order to obey this coverage property, however, conformal sets can become inundated with noisy candidates—which can render them unhelpful in practice. This is particularly relevant to practical applications where there is a limited budget, and the cost (monetary or otherwise) associated with false positives is non-negligible. We propose to trade coverage for a notion of precision by enforcing that the presence of incorrect candidates in the predicted conformal sets (i.e., the total number of false positives) is bounded according to a user-specified tolerance. Subject to this constraint, our algorithm then optimizes for a generalized notion of set coverage (i.e., the true positive rate) that allows for any number of true answers for a given query (including zero). We demonstrate the effectiveness of this approach across a number of classification tasks in natural language processing, computer vision, and computational chemistry.

Computational antibody design seeks to automatically create an antibody that binds to an antigen. The binding affinity is governed by the 3D binding interface where antibody residues (paratope) closely interact with antigen residues (epitope). Thus, the key question of antibody design is how to predict the 3D paratope-epitope complex (i.e., docking) for paratope generation. In this paper, we propose a new model called Hierarchical Structure Refinement Network (HSRN) for paratope docking and design. During docking, HSRN employs a hierarchical message passing network to predict atomic forces and use them to refine a binding complex in an iterative, equivariant manner. During generation, its autoregressive decoder progressively docks generated paratopes and builds a geometric representation of the binding interface to guide the next residue choice. Our results show that HSRN significantly outperforms prior state-of-the-art on paratope docking and design benchmarks.

Predicting how a drug-like molecule binds to a specific protein target is a core problem in drug discovery. An extremely fast computational binding method would enable key applications such as fast virtual screening or drug engineering. Existing methods are computationally expensive as they rely on heavy candidate sampling coupled with scoring, ranking, and fine-tuning steps. We challenge this paradigm with EquiBind, an SE(3)-equivariant geometric deep learning model performing direct-shot prediction of both i) the receptor binding location (blind docking) and ii) the ligand’s bound pose and orientation. EquiBind achieves significant speed-ups and better quality compared to traditional and recent baselines. Further, we show extra improvements when coupling it with existing fine-tuning techniques at the cost of increased running time. Finally, we propose a novel and fast fine-tuning model that adjusts torsion angles of a ligand’s rotatable bonds based on closed form global minima of the von Mises angular distance to a given input atomic point cloud, avoiding previous expensive differential evolution strategies for energy minimization.

Molecular conformer generation is a fundamental task in computational chemistry. Several machine learning approaches have been developed, but none have outperformed state-of-the-art cheminformatics methods. We propose torsional diffusion, a novel diffusion framework that operates on the space of torsion angles via a diffusion process on the hypertorus and an extrinsic-to-intrinsic score model. On a standard benchmark of drug-like molecules, torsional diffusion generates superior conformer ensembles compared to machine learning and cheminformatics methods in terms of both RMSD and chemical properties, and is orders of magnitude faster than previous diffusion-based models. Moreover, our model provides exact likelihoods, which we employ to build the first generalizable Boltzmann generator. Code is available at https://github.com/gcorso/torsional-diffusion.

We introduce Nutri-bullets, a multi-document summarization task for health and nutrition. First, we present two datasets of food and health summaries from multiple scientific studies. Furthermore, we propose a novel extract-compose model to solve the problem in the regime of limited parallel data. We explicitly select key spans from several abstracts using a policy network, followed by composing the selected spans to present a summary via a task specific language model. Compared to state-of-the-art methods, our approach leads to more faithful, relevant and diverse summarization -- properties imperative to this application. For instance, on the BreastCancer dataset our approach gets a more than 50% improvement on relevance and faithfulness.

In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development. Building on the recent success of graph neural networks for learning molecular embeddings and flow-based models for image generation, we propose Mol2Image: a flow-based generative model for molecule to cell image synthesis. To generate cell features at different resolutions and scale to high-resolution images, we develop a novel multi-scale flow architecture based on a Haar wavelet image pyramid. To maximize the mutual information between the generated images and the molecular interventions, we devise a training strategy based on contrastive learning. To evaluate our model, we propose a new set of metrics for biological image generation that are robust, interpretable, and relevant to practitioners. We show quantitatively that our method learns a meaningful embedding of the molecular intervention, which is translated into an image representation reflecting the biological effects of the intervention.

We develop a novel approach for confidently accelerating inference in the large and expensive multilayer Transformers that are now ubiquitous in natural language processing (NLP).Amortized or approximate computational methods increase efficiency, but can come with unpredictable performance costs.In this work, we present CATs-Confident Adaptive Transformers-in which we simultaneously increase computational efficiency, while guaranteeing a specifiable degree of consistency with the original model with high confidence.Our method trains additional prediction heads on top of intermediate layers, and dynamically decides when to stop allocating computational effort to each input using a meta consistency classifier.To calibrate our early prediction stopping rule, we formulate a unique extension of conformal prediction.We demonstrate the effectiveness of this approach on four classification and regression tasks. 1 * The first two authors contributed equally. 1

We propose Predict then Interpolate (PI), a simple algorithm for learning correlations that are stable across environments. The algorithm follows from the intuition that when using a classifier trained on one environment to make predictions on examples from another environment, its mistakes are informative as to which correlations are unstable. In this work, we prove that by interpolating the distributions of the correct predictions and the wrong predictions, we can uncover an oracle distribution where the unstable correlation vanishes. Since the oracle interpolation coefficients are not accessible, we use group distributionally robust optimization to minimize the worst-case risk across all such interpolations. We evaluate our method on both text classification and image classification. Empirical results demonstrate that our algorithm is able to learn robust classifiers (outperforms IRM by 23.85% on synthetic environments and 12.41% on natural environments). Our code and data are available at https://github.com/YujiaBao/ Predict-then-Interpolate.

We develop a novel approach to conformal prediction when the target task has limited data available for training. Conformal prediction identifies a small set of promising output candidates in place of a single prediction, with guarantees that the set contains the correct answer with high probability. When training data is limited, however, the predicted set can easily become unusably large. In this work, we obtain substantially tighter prediction sets while maintaining desirable marginal guarantees by casting conformal prediction as a meta-learning paradigm over exchangeable collections of auxiliary tasks. Our conformalization algorithm is simple, fast, and agnostic to the choice of underlying model, learning algorithm, or dataset. We demonstrate the effectiveness of this approach across a number of few-shot classification and regression tasks in natural language processing, computer vision, and computational chemistry for drug discovery.

Typical fact verification models use retrieved written evidence to verify claims.Evidence sources, however, often change over time as more information is gathered and revised.In order to adapt, models must be sensitive to subtle differences in supporting evidence.We present VITAMINC, a benchmark infused with challenging cases that require fact verification models to discern and adjust to slight factual changes.We collect over 100,000 Wikipedia revisions that modify an underlying fact, and leverage these revisions, together with additional synthetically constructed ones, to create a total of over 400,000 claim-evidence pairs.Unlike previous resources, the examples in VITAMINC are contrastive, i.e., they contain evidence pairs that are nearly identical in language and content, with the exception that one supports a given claim while the other does not.We show that training using this design increases robustness-improving accuracy by 10% on adversarial fact verification and 6% on adversarial natural language inference (NLI).Moreover, the structure of VITAMINC leads us to define additional tasks for fact-checking resources: tagging relevant words in the evidence for verifying the claim, identifying factual revisions, and providing automatic edits via factually consistent text generation. 1

We present a method for generating comparative summaries that highlights similarities and contradictions in input documents.The key challenge in creating such summaries is the lack of large parallel training data required for training typical summarization systems.To this end, we introduce a hybrid generation approach inspired by traditional concept-to-text systems.To enable accurate comparison between different sources, the model first learns to extract pertinent relations from input documents.The content planning component uses deterministic operators to aggregate these relations after identifying a subset for inclusion into a summary.The surface realization component lexicalizes this information using a text-infilling language model.By separately modeling content selection and realization, we can effectively train them with limited annotations.We implemented and tested the model in the domain of nutrition and health -rife with inconsistencies.Compared to conventional methods, our framework leads to more faithful, relevant and aggregation-sensitive summarization -while being equally fluent. 1

Prediction of a molecule’s 3D conformer ensemble from the molecular graph holds a key role in areas of cheminformatics and drug discovery. Existing generative models have several drawbacks including lack of modeling important molecular geometry elements (e.g., torsion angles), separate optimization stages prone to error accumulation, and the need for structure fine-tuning based on approximate classical force-fields or computationally expensive methods. We propose GEOMOL --- an end-to-end, non-autoregressive, and SE(3)-invariant machine learning approach to generate distributions of low-energy molecular 3D conformers. Leveraging the power of message passing neural networks (MPNNs) to capture local and global graph information, we predict local atomic 3D structures and torsion angles, avoid- ing unnecessary over-parameterization of the geometric degrees of freedom (e.g., one angle per non-terminal bond). Such local predictions suffice both for both the training loss computation and for the full deterministic conformer assembly (at test time). We devise a non-adversarial optimal transport based loss function to promote diverse conformer generation. GEOMOL predominantly outperforms popular open-source, commercial, or state-of-the-art machine learning (ML) models, while achieving significant speed-ups. We expect such differentiable 3D structure generators to significantly impact molecular modeling and related applications.

Retrosynthesis prediction is a fundamental problem in organic synthesis, where the task is to identify precursor molecules that can be used to synthesize a target molecule. A key consideration in building neural models for this task is aligning model design with strategies adopted by chemists. Building on this viewpoint, this paper introduces a graph-based approach that capitalizes on the idea that the graph topology of precursor molecules is largely unaltered during a chemical reaction. The model first predicts the set of graph edits transforming the target into incomplete molecules called synthons. Next, the model learns to expand synthons into complete molecules by attaching relevant leaving groups. This decomposition simplifies the architecture, making its predictions more interpretable, and also amenable to manual correction. Our model achieves a top-1 accuracy of 53.7%, outperforming previous template-free and semi-template-based methods.

Most undeciphered lost languages exhibit two characteristics that pose significant decipherment challenges: (1) the scripts are not fully segmented into words; (2) the closest known language is not determined. We propose a decipherment model that handles both of these challenges by building on rich linguistic constraints reflecting consistent patterns in historical sound change. We capture the natural phonological geometry by learning character embeddings based on the International Phonetic Alphabet (IPA). The resulting generative framework jointly models word segmentation and cognate alignment, informed by phonological constraints. We evaluate the model on both deciphered languages (Gothic, Ugaritic) and an undeciphered one (Iberian). The experiments show that incorporating phonetic geometry leads to clear and consistent gains. Additionally, we propose a measure for language closeness which correctly identifies related languages for Gothic and Ugaritic. For Iberian, the method does not show strong evidence supporting Basque as a related language, concurring with the favored position by the current scholarship. 1

Online encyclopediae like Wikipedia contain large amounts of text that need frequent corrections and updates. The new information may contradict existing content in encyclopediae. In this paper, we focus on rewriting such dynamically changing articles. This is a challenging constrained generation task, as the output must be consistent with the new information and fit into the rest of the existing document. To this end, we propose a two-step solution: (1) We identify and remove the contradicting components in a target text for a given claim, using a neutralizing stance model; (2) We expand the remaining text to be consistent with the given claim, using a novel two-encoder sequence-to-sequence model with copy attention. Applied to a Wikipedia fact update dataset, our method successfully generates updated sentences for new claims, achieving the highest SARI score. Furthermore, we demonstrate that generating synthetic data through such rewritten sentences can successfully augment the FEVER fact-checking training dataset, leading to a relative error reduction of 13%.1

Automatic question generation can benefit many applications ranging from dialogue systems to reading comprehension. While questions are often asked with respect to long documents, there are many challenges with modeling such long documents. Many existing techniques generate questions by effectively looking at one sentence at a time, leading to questions that are easy and not reflective of the human process of question generation. Our goal is to incorporate interactions across multiple sentences to generate realistic questions for long documents. In order to link a broad document context to the target answer, we represent the relevant context via a multi-stage attention mechanism, which forms the foundation of a sequence to sequence model. We outperform state-of-the-art methods on question generation on three question-answering datasets - SQuAD, MS MARCO and NewsQA. 1

The traditional image captioning task uses generic reference captions to provide textual information about images.Different user populations, however, will care about different visual aspects of images.In this paper, we propose a new task, Captioning with A Purpose (CAPWAP).Our goal is to develop systems that can be tailored to be useful for the information needs of an intended population, rather than merely provide generic information about an image.In this task, we use questionanswer (QA) pairs-a natural expression of information need-from users, instead of reference captions, for both training and postinference evaluation.We show that it is possible to use reinforcement learning to directly optimize for the intended information need, by rewarding outputs that allow a question answering model to provide correct answers to sampled user questions.We convert several visual question answering datasets into CAP-WAP datasets, and demonstrate that under a variety of scenarios our purposeful captioning system learns to anticipate and fulfill specific information needs better than its generic counterparts, as measured by QA performance on user questions from unseen images, when using the caption alone as context.

We propose Blank Language Model (BLM), a model that generates sequences by dynamically creating and filling in blanks.The blanks control which part of the sequence to expand, making BLM ideal for a variety of text editing and rewriting tasks.The model can start from a single blank or partially completed text with blanks at specified locations.It iteratively determines which word to place in a blank and whether to insert new blanks, and stops generating when no blanks are left to fill.BLM can be efficiently trained using a lower bound of the marginal data likelihood.On the task of filling missing text snippets, BLM significantly outperforms all other baselines in terms of both accuracy and fluency.Experiments on style transfer and damaged ancient text restoration demonstrate the potential of this framework for a wide range of applications.1

Graph generation techniques are increasingly being adopted for drug discovery. Previous graph generation approaches have utilized relatively small molecular building blocks such as atoms or simple cycles, limiting their effectiveness to smaller molecules. Indeed, as we demonstrate, their performance degrades significantly for larger molecules. In this paper, we propose a new hierarchical graph encoder-decoder that employs significantly larger and more flexible graph motifs as basic building blocks. Our encoder produces a multi-resolution representation for each molecule in a fine-to-coarse fashion, from atoms to connected motifs. Each level integrates the encoding of constituents below with the graph at that level. Our autoregressive coarse-to-fine decoder adds one motif at a time, interleaving the decision of selecting a new motif with the process of resolving its attachments to the emerging molecule. We evaluate our model on multiple molecule generation tasks, including polymers, and show that our model significantly outperforms previous state-of-the-art baselines.

Drug discovery aims to find novel compounds with specified chemical property profiles. In terms of generative modeling, the goal is to learn to sample molecules in the intersection of multiple property constraints. This task becomes increasingly challenging when there are many property constraints. We propose to offset this complexity by composing molecules from a vocabulary of substructures that we call molecular rationales. These rationales are identified from molecules as substructures that are likely responsible for each property of interest. We then learn to expand rationales into a full molecule using graph generative models. Our final generative model composes molecules as mixtures of multiple rationale completions, and this mixture is fine-tuned to preserve the properties of interest. We evaluate our model on various drug design tasks and demonstrate significant improvements over state-of-the-art baselines in terms of accuracy, diversity, and novelty of generated compounds.

Generative autoencoders offer a promising approach for controllable text generation by leveraging their learned sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text manipulations via latent vector operations. Specifically, we demonstrate by example that neural encoders do not necessarily map similar sentences to nearby latent vectors. A theoretical explanation for this phenomenon establishes that high-capacity autoencoders can learn an arbitrary mapping between sequences and associated latent representations. To remedy this issue, we augment adversarial autoencoders with a denoising objective where original sentences are reconstructed from perturbed versions (referred to as DAAE). We prove that this simple modification guides the latent space geometry of the resulting model by encouraging the encoder to map similar texts to similar latent representations. In empirical comparisons with various types of autoencoders, our model provides the best trade-off between generation quality and reconstruction capacity. Moreover, the improved geometry of the DAAE latent space enables \emph{zero-shot} text style transfer via simple latent vector arithmetic.

Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models from data may be challenging due to the lack of sufficient training data. In this paper, we propose a surprisingly effective self-training approach for iteratively creating additional molecular targets. We first pre-train the generative model together with a simple property predictor. The property predictor is then used as a likelihood model for filtering candidate structures from the generative model. Additional targets are iteratively produced and used in the course of stochastic EM iterations to maximize the log-likelihood that the candidate structures are accepted. A simple rejection (re-weighting) sampler suffices to draw posterior samples since the generative model is already reasonable after pre-training. We demonstrate significant gains over strong baselines for both unconditional and conditional molecular design. In particular, our approach outperforms the previous state-of-the-art in conditional molecular design by over 10% in absolute gain. Finally, we show that our approach is useful in other domains as well, such as program synthesis.

Recent developments in neural language models (LMs) have raised concerns about their potential misuse for automatically spreading misinformation. In light of these concerns, several studies have proposed to detect machine-generated fake news by capturing their stylistic differences from human-written text. These approaches, broadly termed stylometry, have found success in source attribution and misinformation detection in human-written texts. However, in this work, we show that stylometry is limited against machine-generated misinformation. Whereas humans speak differently when trying to deceive, LMs generate stylistically consistent text, regardless of underlying motive. Thus, though stylometry can successfully prevent impersonation by identifying text provenance, it fails to distinguish legitimate LM applications from those that introduce false information. We create two benchmarks demonstrating the stylistic similarity between malicious and legitimate uses of LMs, utilized in auto-completion and editing-assistance settings. 1 Our findings highlight the need for non-stylometry approaches in detecting machine-generated misinformation, and open up the discussion on the desired evaluation benchmarks.

In this paper we propose a novel neural approach for automatic decipherment of lost languages.To compensate for the lack of strong supervision signal, our model design is informed by patterns in language change documented in historical linguistics.The model utilizes an expressive sequence-to-sequence model to capture character-level correspondences between cognates.To effectively train the model in an unsupervised manner, we innovate the training procedure by formalizing it as a minimum-cost flow problem.When applied to the decipherment of Ugaritic, we achieve a 5.5% absolute improvement over state-of-the-art results.We also report the first automatic results in deciphering Linear B, a syllabic language related to ancient Greek, where our model correctly translates 67.3% of cognates.1

Adam Fisch, Jiang Guo, Regina Barzilay. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Tal Schuster, Darsh Shah, Yun Jie Serene Yeo, Daniel Roberto Filizzola Ortiz, Enrico Santus, Regina Barzilay. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Engineered proteins offer the potential to solve many problems in biomedicine, energy, and materials science, but creating designs that succeed is difficult in practice. A significant aspect of this challenge is the complex coupling between protein sequence and 3D structure, with the task of finding a viable design often referred to as the inverse protein folding problem. We develop relational language models for protein sequences that directly condition on a graph specification of the target structure. Our approach efficiently captures the complex dependencies in proteins by focusing on those that are long-range in sequence but local in 3D space. Our framework significantly improves in both speed and robustness over conventional and deep-learning-based methods for structure-based protein sequence design, and takes a step toward rapid and targeted biomolecular design with the aid of deep generative models.

Attention-based models are successful when trained on large amounts of data.In this paper, we demonstrate that even in the low-resource scenario, attention can be learned effectively.To this end, we start with discrete humanannotated rationales and map them into continuous attention.Our central hypothesis is that this mapping is general across domains, and thus can be transferred from resource-rich domains to low-resource ones.Our model jointly learns a domain-invariant representation and induces the desired mapping between rationales and attention.Our empirical results validate this hypothesis and show that our approach delivers significant gains over state-ofthe-art baselines, yielding over 15% average error reduction on benchmark datasets.

We propose a mixture-of-experts approach for unsupervised domain adaptation from multiple sources.The key idea is to explicitly capture the relationship between a target example and different source domains.This relationship, expressed by a point-to-set metric, determines how to combine predictors trained on various domains.The metric is learned in an unsupervised fashion using metatraining.Experimental results on sentiment analysis and part-of-speech tagging demonstrate that our approach consistently outperforms multiple baselines and can robustly handle negative transfer. 1

We seek to automate the design of molecules based on specific chemical properties. In computational terms, this task involves continuous embedding and generation of molecular graphs. Our primary contribution is the direct realization of molecular graphs, a task previously approached by generating linear SMILES strings instead of graphs. Our junction tree variational autoencoder generates molecular graphs in two phases, by first generating a tree-structured scaffold over chemical substructures, and then combining them into a molecule with a graph message passing network. This approach allows us to incrementally expand molecules while maintaining chemical validity at every step. We evaluate our model on multiple tasks ranging from molecular generation to optimization. Across these tasks, our model outperforms previous state-of-the-art baselines by a significant margin.

In this paper, we explore the utilization of natural language to drive transfer for reinforcement learning (RL). Despite the wide-spread application of deep RL techniques, learning generalized policy representations that work across domains remains a challenging problem. We demonstrate that textual descriptions of environments provide a compact intermediate channel to facilitate effective policy transfer. Specifically, by learning to ground the meaning of text to the dynamics of the environment such as transitions and rewards, an autonomous agent can effectively bootstrap policy learning on a new domain given its description. We employ a model-based RL approach consisting of a differentiable planning module, a model-free component and a factorized state representation to effectively use entity descriptions. Our model outperforms prior work on both transfer and multi-task scenarios in a variety of different environments. For instance, we achieve up to 14% and 11.5% absolute improvement over previously existing models in terms of average and initial rewards, respectively.

The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment. We consider the task of spatial reasoning in a simulated environment, where an agent can act and receive rewards. The proposed model learns a representation of the world steered by instruction text. This design allows for precise alignment of local neighborhoods with corresponding verbalizations, while also handling global references in the instructions. We train our model with reinforcement learning using a variant of generalized value iteration. The model outperforms state-of-the-art approaches on several metrics, yielding a 45% reduction in goal localization error.

The design of neural architectures for structured objects is typically guided by experimental insights rather than a formal process. In this work, we appeal to kernels over combinatorial structures, such as sequences and graphs, to derive appropriate neural operations. We introduce a class of deep recurrent neural operations and formally characterize their associated kernel spaces. Our recurrent modules compare the input to virtual reference objects (cf. filters in CNN) via the kernels. Similar to traditional neural operations, these reference objects are parameterized and directly optimized in end-to-end training. We empirically evaluate the proposed class of neural architectures on standard applications such as language modeling and molecular graph regression, achieving state-of-the-art results across these applications.

The prediction of organic reaction outcomes is a fundamental problem in computational chemistry. Since a reaction may involve hundreds of atoms, fully exploring the space of possible transformations is intractable. The current solution utilizes reaction templates to limit the space, but it suffers from coverage and efficiency issues. In this paper, we propose a template-free approach to efficiently explore the space of product molecules by first pinpointing the reaction center -- the set of nodes and edges where graph edits occur. Since only a small number of atoms contribute to reaction center, we can directly enumerate candidate products. The generated candidates are scored by a Weisfeiler-Lehman Difference Network that models high-order interactions between changes occurring at nodes across the molecule. Our framework outperforms the top-performing template-based approach with a 10% margin, while running orders of magnitude faster. Finally, we demonstrate that the model accuracy rivals the performance of domain experts.

This paper focuses on style transfer on the basis of non-parallel text. This is an instance of a broad family of problems including machine translation, decipherment, and sentiment modification. The key challenge is to separate the content from other aspects such as style. We assume a shared latent content distribution across different text corpora, and propose a method that leverages refined alignment of latent representations to perform style transfer. The transferred sentences from one style should match example sentences from the other style as a population. We demonstrate the effectiveness of this cross-alignment method on three tasks: sentiment modification, decipherment of word substitution ciphers, and recovery of word order.

This paper focuses on unsupervised modeling of morphological families, collectively comprising a forest over the language vocabulary. This formulation enables us to capture edge-wise properties reflecting single-step morphological derivations, along with global distributional properties of the entire forest. These global properties constrain the size of the affix set and encourage formation of tight morphological families. The resulting objective is solved using Integer Linear Programming (ILP) paired with contrastive estimation. We train the model by alternating between optimizing the local log-linear model and the global ILP objective. We evaluate our system on three tasks: root detection, clustering of morphological families, and segmentation. Our experiments demonstrate that our model yields consistent gains in all three tasks compared with the best published results.

We introduce a neural method for transfer learning between two (source and target) classification tasks or aspects over the same domain. Rather than training on target labels, we use a few keywords pertaining to source and target aspects indicating sentence relevance instead of document class labels. Documents are encoded by learning to embed and softly select relevant sentences in an aspect-dependent manner. A shared classifier is trained on the source encoded documents and labels, and applied to target encoded documents. We ensure transfer through aspect-adversarial training so that encoded documents are, as sets, aspect-invariant. Experimental results demonstrate that our approach outperforms different baselines and model variants on two datasets, yielding an improvement of 27% on a pathology dataset and 5% on a review dataset.

Prediction without justification has limited applicability.As a remedy, we learn to extract pieces of input text as justifications -rationales -that are tailored to be short and coherent, yet sufficient for making the same prediction.Our approach combines two modular components, generator and encoder, which are trained to operate well together.The generator specifies a distribution over text fragments as candidate rationales and these are passed through the encoder for prediction.Rationales are never given during training.Instead, the model is regularized by desiderata for rationales.We evaluate the approach on multi-aspect sentiment analysis against manually annotated test cases.Our approach outperforms attention-based baseline by a significant margin.We also successfully illustrate the method on the question retrieval task. 1

This paper explores the task of translating natural language queries into regular expressions which embody their meaning.In contrast to prior work, the proposed neural model does not utilize domain-specific crafting, learning to translate directly from a parallel corpus.To fully explore the potential of neural models, we propose a methodology for collecting a large corpus 1 of regular expression, natural language pairs.Our resulting model achieves a performance gain of 19.6% over previous state-of-the-art models.

Most successful information extraction systems operate with access to a large collection of documents. In this work, we explore the task of acquiring and incorporating external evidence to improve extraction accuracy in domains where the amount of training data is scarce. This process entails issuing search queries, extraction from new sources and reconciliation of extracted values, which are repeated until sufficient evidence is collected. We approach the problem using a reinforcement learning framework where our model learns to select optimal actions based on contextual information. We employ a deep Q-network, trained to optimize a reward function that reflects extraction accuracy while penalizing extra effort. Our experiments on two databases -- of shooting incidents, and food adulteration cases -- demonstrate that our system significantly outperforms traditional extractors and a competitive meta-classifier baseline.

Tao Lei, Hrishikesh Joshi, Regina Barzilay, Tommi Jaakkola, Kateryna Tymoshenko, Alessandro Moschitti, Lluís Màrquez. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

This work addresses the task of dependency labeling-assigning labels to an (unlabeled) dependency tree.We employ and extend a feature representation learning approach, optimizing it for both high speed and accuracy.We apply our labeling model on top of state-of-the-art parsers and evaluate its performance on standard benchmarks including the CoNLL-2009 and the English PTB datasets.Our model processes over 1,700 English sentences per second, which is 30 times faster than the sparse-feature method.It improves labeling accuracy over the outputs of top parsers, achieving the best LAS on 5 out of 7 datasets 1 .

Yuan Zhang, David Gaddy, Regina Barzilay, Tommi Jaakkola. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

Karthik Narasimhan, Regina Barzilay. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

The success of deep learning often derives from well-chosen operational building blocks.In this work, we revise the temporal convolution operation in CNNs to better adapt it to text processing.Instead of concatenating word representations, we appeal to tensor algebra and use low-rank n-gram tensors to directly exploit interactions between words already at the convolution stage.Moreover, we extend the n-gram convolution to non-consecutive words to recognize patterns with intervening words.Through a combination of lowrank tensors, and pattern weighting, we can efficiently evaluate the resulting convolution operation via dynamic programming.We test the resulting architecture on standard sentiment classification and news categorization tasks.Our model achieves state-of-the-art performance both in terms of accuracy and training speed.For instance, we obtain 51.2% accuracy on the fine-grained sentiment classification task. 1

In this paper, we consider the task of learning control policies for text-based games.In these games, all interactions in the virtual world are through text and the underlying state is not observed.The resulting language barrier makes such environments challenging for automatic game players.We employ a deep reinforcement learning framework to jointly learn state representations and action policies using game rewards as feedback.This framework enables us to map text descriptions into vector representations that capture the semantics of the game states.We evaluate our approach on two game worlds, comparing against baselines using bag-ofwords and bag-of-bigrams for state representations.Our algorithm outperforms the baselines on both worlds demonstrating the importance of learning expressive representations.

Accurate multilingual transfer parsing typically relies on careful feature engineering.In this paper, we propose a hierarchical tensor-based approach for this task.This approach induces a compact feature representation by combining atomic features.However, unlike traditional tensor models, it enables us to incorporate prior knowledge about desired feature interactions, eliminating invalid feature combinations.To this end, we use a hierarchical structure that uses intermediate embeddings to capture desired feature combinations.Algebraically, this hierarchical tensor is equivalent to the sum of traditional tensors with shared components, and thus can be effectively trained with standard online algorithms.In both unsupervised and semi-supervised transfer scenarios, our hierarchical tensor consistently improves UAS and LAS over state-of-theart multilingual transfer parsers and the traditional tensor model across 10 different languages.1

Tao Lei, Yuan Zhang, Lluís Màrquez, Alessandro Moschitti, Regina Barzilay. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.

Yuan Zhang, Chengtao Li, Regina Barzilay, Kareem Darwish. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.

Correction for the list of authors in the reference (Seddah et al., 2013).

Most state-of-the-art systems today produce morphological analysis based only on orthographic patterns. In contrast, we propose a model for unsupervised morphological analysis that integrates orthographic and semantic views of words. We model word formation in terms of morphological chains, from base words to the observed words, breaking the chains into parent-child relations. We use log-linear models with morpheme and word-level features to predict possible parents, including their modifications, for each word. The limited set of candidate parents for each word render contrastive estimation feasible. Our model consistently matches or outperforms five state-of-the-art systems on Arabic, English and Turkish.

We present an approach for automatically learning to solve algebra word problems.Our algorithm reasons across sentence boundaries to construct and solve a system of linear equations, while simultaneously recovering an alignment of the variables and numbers in these equations to the problem text.The learning algorithm uses varied supervision, including either full equations or just the final answers.We evaluate performance on a newly gathered corpus of algebra word problems, demonstrating that the system can correctly answer almost 70% of the questions in the dataset.This is, to our knowledge, the first learning result for this task.

Accurate scoring of syntactic structures such as head-modifier arcs in dependency parsing typically requires rich, highdimensional feature representations.A small subset of such features is often selected manually.This is problematic when features lack clear linguistic meaning as in embeddings or when the information is blended across features.In this paper, we use tensors to map high-dimensional feature vectors into low dimensional representations.We explicitly maintain the parameters as a low-rank tensor to obtain low dimensional representations of words in their syntactic roles, and to leverage modularity in the tensor for easy training with online algorithms.Our parser consistently outperforms the Turbo and MST parsers across 14 different languages.We also obtain the best published UAS results on 5 languages.1

Much of the recent work on depen-dency parsing has been focused on solv-ing inherent combinatorial problems as-sociated with rich scoring functions. In contrast, we demonstrate that highly ex-pressive scoring functions can be used with substantially simpler inference pro-cedures. Specifically, we introduce a sampling-based parser that can easily han-dle arbitrary global features. Inspired by SampleRank, we learn to take guided stochastic steps towards a high scoring parse. We introduce two samplers for traversing the space of trees, Gibbs and Metropolis-Hastings with Random Walk. The model outperforms state-of-the-art re-sults when evaluated on 14 languages of non-projective CoNLL datasets. Our sampling-based approach naturally ex-tends to joint prediction scenarios, such as joint parsing and POS correction. The resulting method outperforms the best re-ported results on the CATiB dataset, ap-proaching performance of parsing with gold tags.1 1

We explore the impact of morphological segmentation on keyword spotting (KWS).Despite potential benefits, stateof-the-art KWS systems do not use morphological information.In this paper, we augment a state-of-the-art KWS system with sub-word units derived from supervised and unsupervised morphological segmentations, and compare with phonetic and syllabic segmentations.Our experiments demonstrate that morphemes improve overall performance of KWS systems.Syllabic units, however, rival the performance of morphological units when used in KWS.By combining morphological, phonetic and syllabic segmentations, we demonstrate substantial performance gains.

Dependency parsing with high-order features results in a provably hard decoding problem.A lot of work has gone into developing powerful optimization methods for solving these combinatorial problems.In contrast, we explore, analyze, and demonstrate that a substantially simpler randomized greedy inference algorithm already suffices for near optimal parsing: a) we analytically quantify the number of local optima that the greedy method has to overcome in the context of first-order parsing; b) we show that, as a decoding algorithm, the greedy method surpasses dual decomposition in second-order parsing; c) we empirically demonstrate that our approach with up to third-order and global features outperforms the state-of-the-art dual decomposition and MCMC sampling methods when evaluated on 14 languages of non-projective CoNLL datasets.1

Prepositional phrase (PP) attachment disambiguation is a known challenge in syntactic parsing. The lexical sparsity associated with PP attachments motivates research in word representations that can capture pertinent syntactic and semantic features of the word. One promising solution is to use word vectors induced from large amounts of raw text. However, state-of-the-art systems that employ such representations yield modest gains in PP attachment accuracy. In this paper, we show that word vector representations can yield significant PP attachment performance gains. This is achieved via a non-linear architecture that is discriminatively trained to maximize PP attachment accuracy. The architecture is initialized with word vectors trained from unlabeled data, and relearns those to maximize attachment accuracy. We obtain additional performance gains with alternative representations such as dependency-based word vectors. When tested on both English and Arabic datasets, our method outperforms both a strong SVM classifier and state-of-the-art parsers. For instance, we achieve 82.6% PP attachment accuracy on Arabic, while the Turbo and Charniak self-trained parsers obtain 76.7% and 80.8% respectively.

We present a model for aggregation of product review snippets by joint aspect identification and sentiment analysis. Our model simultaneously identifies an underlying set of ratable aspects presented in the reviews of a product (e.g., sushi and miso for a Japanese restaurant) and determines the corresponding sentiment of each aspect. This approach directly enables discovery of highly-rated or inconsistent aspects of a product. Our generative model admits an efficient variational mean-field inference algorithm. It is also easily extensible, and we describe several modifications and their effects on model structure and inference. We test our model on two tasks, joint aspect identification and sentiment analysis on a set of Yelp reviews and aspect identification alone on a set of medical summaries. We evaluate the performance of the model on aspect identification, sentiment analysis, and per-word labeling accuracy. We demonstrate that our model outperforms applicable baselines by a considerable margin, yielding up to 32% relative error reduction on aspect identification and up to 20% relative error reduction on sentiment analysis.

Domain knowledge is crucial for effective performance in autonomous control systems. Typically, human effort is required to encode this knowledge into a control algorithm. In this paper, we present an approach to language grounding which automatically interprets text in the context of a complex control application, such as a game, and uses domain knowledge extracted from the text to improve control performance. Both text analysis and control strategies are learned jointly using only a feedback signal inherent to the application. To effectively leverage textual information, our method automatically extracts the text segment most relevant to the current game state, and labels it with a task-centric predicate structure. This labeled text is then used to bias an action selection policy for the game, guiding it towards promising regions of the action space. We encode our model for text analysis and game playing in a multi-layer neural network, representing linguistic decisions via latent variables in the hidden layers, and game action quality via the output layer. Operating within the Monte-Carlo Search framework, we estimate model parameters using feedback from simulated games. We apply our approach to the complex strategy game Civilization II using the official game manual as the text guide. Our results show that a linguistically-informed game-playing agent significantly outperforms its language-unaware counterpart, yielding a 34% absolute improvement and winning over 65% of games when playing against the built-in AI of Civilization.

We present a method for dependency grammar induction that utilizes sparse annotations of semantic relations. This induction set-up is attractive because such annotations provide useful clues about the underlying syntactic structure, and they are readily available in many domains (e.g., info-boxes and HTML markup). Our method is based on the intuition that syntactic realizations of the same semantic predicate exhibit some degree of consistency. We incorporate this intuition in a directed graphical model that tightly links the syntactic and semantic structures. This design enables us to exploit syntactic regularities while still allowing for variations. Another strength of the model lies in its ability to capture non-local dependency relations. Our results demonstrate that even a small amount of semantic annotations greatly improves the accuracy of learned dependencies when tested on both in-domain and out-of-domain texts.

This paper presents a new Monte-Carlo search algorithm for very large sequential decision-making problems. We apply non-linear regression within Monte-Carlo search, online, to estimate a stateaction value function from the outcomes of random roll-outs. This value function generalizes between related states and actions, and can therefore provide more accurate evaluations after fewer rollouts. A further significant advantage of this approach is its ability to automatically extract and leverage domain knowledge from external sources such as game manuals. We apply our algorithm to the game of Civilization II, a challenging multiagent strategy game with an enormous state space and around 1021joint actions. We approximate the value function by a neural network, augmented by linguistic knowledge that is extracted automatically from the official game manual. We show that this non-linear value function is significantly more efficient than a linear value function, which is itself more efficient than Monte-Carlo tree search. Our non-linear Monte-Carlo search wins over 78% of games against the built-in AI of Civilization II.

In this paper, we introduce a new envisioned application for speech which allows users to enter restaurant reviews orally via their mobile device, and, at a later time, update a shared and growing database of consumer-provided information about restaurants. During the intervening period, a speech recognition and NLP based system has analyzed their audio recording both to extract key descriptive phrases and to compute sentiment ratings based on the evidence provided in the audio clip. We report here on our preliminary work moving towards this goal. Our experiments demonstrate that multi-aspect sentiment ranking works surprisingly well on speech output, even in the presence of recognition errors. We also present initial experiments on integrated sentence boundary detection and key phrase extraction from recognition output.

This paper presents a new method for inferring the semantic properties of documents by leveraging free-text keyphrase annotations. Such annotations are becoming increasingly abundant due to the recent dramatic growth in semi-structured, user-generated online content. One especially relevant domain is product reviews, which are often annotated by their authors with pros/cons keyphrases such as ``a real bargain'' or ``good value.'' These annotations are representative of the underlying semantic properties; however, unlike expert annotations, they are noisy: lay authors may use different labels to denote the same property, and some labels may be missing. To learn using such noisy annotations, we find a hidden paraphrase structure which clusters the keyphrases. The paraphrase structure is linked with a latent topic model of the review texts, enabling the system to predict the properties of unannotated documents and to effectively aggregate the semantic properties of multiple reviews. Our approach is implemented as a hierarchical Bayesian model with joint inference. We find that joint inference increases the robustness of the keyphrase clustering and encourages the latent topics to correlate with semantically meaningful properties. Multiple evaluations demonstrate that our model substantially outperforms alternative approaches for summarizing single and multiple documents into a set of semantically salient keyphrases.

We present a novel Bayesian topic model for learning discourse-level document structure. Our model leverages insights from discourse theory to constrain latent topic assignments in a way that reflects the underlying organization of document topics. We propose a global model in which both topic selection and ordering are biased to be similar across a collection of related documents. We show that this space of orderings can be effectively represented using a distribution over permutations called the Generalized Mallows Model. We apply our method to three complementary discourse-level tasks: cross-document alignment, document segmentation, and information ordering. Our experiments show that incorporating our permutation-based model in these applications yields substantial improvements in performance over previously proposed methods.

We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The central assumption of our work is that by combining cues from multiple languages, the structure of each becomes more apparent. We consider two ways of applying this intuition to the problem of unsupervised part-of-speech tagging: a model that directly merges tag structures for a pair of languages into a single sequence and a second model which instead incorporates multilingual context using latent variables. Both approaches are formulated as hierarchical Bayesian models, using Markov Chain Monte Carlo sampling techniques for inference. Our results demonstrate that by incorporating multilingual evidence we can achieve impressive performance gains across a range of scenarios. We also found that performance improves steadily as the number of available languages increases.

This article proposes a novel framework for representing and measuring local coherence. Central to this approach is the entity-grid representation of discourse, which captures patterns of entity distribution in a text. The algorithm introduced in the article automatically abstracts a text into a set of entity transition sequences and records distributional, syntactic, and referential information about discourse entities. We re-conceptualize coherence assessment as a learning task and show that our entity-based representation is well-suited for ranking-based generation and text classification tasks. Using the proposed representation, we achieve good performance on text ordering, summary coherence evaluation, and readability assessment.

Gesture is a non-verbal modality that can contribute crucial information to the understanding of natural language. But not all gestures are informative, and non-communicative hand motions may confuse natural language processing (NLP) and impede learning. People have little diffculty ignoring irrelevant hand movements and focusing on meaningful gestures, suggesting that an automatic system could also be trained to perform this task. However, the informativeness of a gesture is context-dependent and labeling enough data to cover all cases would be expensive. We present conditional modality fusion, a conditional hidden-variable model that learns to predict which gestures are salient for coreference resolution, the task of determining whether two noun phrases refer to the same semantic entity. Moreover, our approach uses only coreference annotations, and not annotations of gesture salience itself. We show that gesture features improve performance on coreference resolution, and that by attending only to gestures that are salient, our method achieves further significant gains. In addition, we show that the model of gesture salience learned in the context of coreference accords with human intuition, by demonstrating that gestures judged to be salient by our model can be used successfully to create multimedia keyframe summaries of video. These summaries are similar to those created by human raters, and significantly outperform summaries produced by baselines from the literature.

In this paper we discuss our research activities in the area of spoken lecture processing. Our goal is to improve the access to on-line audio/visual recordings of academic lectures by developing tools for the processing, transcription, indexing, segmentation, summarization, retrieval and browsing of this media. In this paper, we provide an overview of the technology components and systems that have been developed as part of this project, present some experimental results, and discuss our ongoing and future research plans. Index Terms:spoken lecture processing, spoken document retrieval, audio browsing

We consider the task of unsupervised lecture segmentation. We formalize segmentation as a graph-partitioning task that optimizes the normalized cut criterion. Our approach moves beyond localized comparisons and takes into account long-range cohesion dependencies. Our results demonstrate that global analysis improves the segmentation accuracy and is robust in the presence of speech recognition errors.

This paper considers the problem of automatic assessment of local coherence.We present a novel entity-based representation of discourse which is inspired by Centering Theory and can be computed automatically from raw text.We view coherence assessment as a ranking learning problem and show that the proposed discourse representation supports the effective learning of a ranking function.Our experiments demonstrate that the induced model achieves significantly higher accuracy than a state-of-the-art coherence model.

A system that can produce informative summaries, highlighting common information found in many online documents, will help Web users to pinpoint information that they need without extensive reading. In this article, we introduce sentence fusion, a novel text-to-text generation technique for synthesizing common information across documents. Sentence fusion involves bottom-up local multisequence alignment to identify phrases conveying similar information and statistical generation to combine common phrases into a sentence. Sentence fusion moves the summarization field from the use of purely extractive methods to the generation of abstracts that contain sentences not found in any of the input documents and can synthesize information across sources.

An important component of any generation system is the mapping dictionary, a lexicon of elementary semantic expressions and corresponding natural language realizations. Typically, labor-intensive knowledge-based methods are used to construct the dictionary. We instead propose to acquire it automatically via a novel multiple-pass algorithm employing multiple-sequence alignment, a technique commonly used in bioinformatics. Crucially, our method lever-ages latent information contained in multi-parallel corpora --- datasets that supply several verbalizations of the corresponding semantics rather than just one.We used our techniques to generate natural language versions of computer-generated mathematical proofs, with good results on both a per-component and overall-output basis. For example, in evaluations involving a dozen human judges, our system produced output whose readability and faithfulness to the semantic input rivaled that of a traditional generation system.

The problem of organizing information for multidocument summarization so that the generated summary is coherent has received relatively little attention. While sentence ordering for single document summarization can be determined from the ordering of sentences in the input article, this is not the case for multidocument summarization where summary sentences may be drawn from different input articles. In this paper, we propose a methodology for studying the properties of ordering information in the news genre and describe experiments done on a corpus of multiple acceptable orderings we developed for the task. Based on these experiments, we implemented a strategy for ordering information that combines constraints from chronological order of events and topical relatedness. Evaluation of our augmented algorithm shows a significant improvement of the ordering over two baseline strategies.

While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases. We present an unsupervised learning algorithm for identification of paraphrases from a corpus of multiple English translations of the same source text. Our approach yields phrasal and single word lexical paraphrases as well as syntactic paraphrases.

We present a method to automatically generate a concise summary by identifying and synthesizing similar elements across related text from a set of multiple documents. Our approach is unique in its usage of language generation to reformulate the wording of the summary.