In computer-supported collaborative learning environments, analyzing student dialogue is essential for understanding collaborative problem-solving behaviors and supporting effective learning. Prior work often treats all dialogue interactions uniformly, failing to capture how specific dialogue interaction differentially impact learning experiences and outcomes. To address this limitation, we introduce a dialogue-based learning analytics framework that integrates weighted temporal clustering of dialogue with large language model-based interpretation. Our framework identifies student interaction patterns most predictive of group learning gains and uses these insights to enable early prediction of learning outcomes and generate pedagogically meaningful interpretations. We evaluate our framework on collaborative dialogue from middle school students engaged in a collaborative game-based learning environment. Our results show that our framework achieves 83.1% accuracy in learning outcome prediction. In addition, expert evaluations and case studies demonstrate that the identified weighted dialogue patterns reflect key collaborative problem-solving behaviors recognized as important in collaborative learning. By surfacing high-impact interaction patterns and enabling prioritized interpretation generation, our framework provides a promising approach for accurately analyzing students’ collaborative dialogue.

As LLM-generated text is increasingly used, especially in fictional domains, we explore how much LLM-generated stories differ from human-written stories.In this work, we focus on characters.We borrow definitions from narratology to analyze 8 intricate category-pairs of character, such as stylization and wholeness.These category-pairs consider more than just basic characteristics.They assess how characters are portrayed within their stories.After automatically inferring categories of characters within both LLM and human-written stories, we compare and contrast these two sets of stories.We consider the following overarching questions: (1) Do LLMs and human-written stories have similar characters? and (2) Do LLMs generate stories with a variety of characters?Our analysis includes research questions that focus on stories generated by popular LLMs and recently published human-written stories.We describe a number of interesting similarities, differences and key takeaways.1

Power differences shape human communication through well-documented socio-cognitive effects, including language coordination, pronoun usage, authority bias, and harmful compliance.We examine whether large language models (LLMs) exhibit similar behaviors when assigned high-or low-status personas.Using personas from diverse professions, we simulate multi-turn, power-asymmetric dialogues (e.g., principal-teacher, justice-lawyer) and measure (i) linguistic coordination, (ii) pronoun usage, (iii) persuasion success, and (iv) compliance with unsafe requests.Our results show that LLMs show key socio-cognitive effects of power, albeit with nuances and variability, linking simulated interactions to both desirable and unsafe behaviors.1

Collaborative problem solving requires students to jointly reason, negotiate, and regulate their learning. Understanding collaborative problem solving through student dialogue can inform timely identification of productive and unproductive collaborative behaviors. In this study, we investigate the use of large language models to automatically classify collaborative problem-solving dialogue segments into two categories: Productive and Unproductive. To support deeper analysis, we additionally explore classification of eight detailed collaborative problem-solving sub-categories. We present an error-augmented few-shot prompting method that incorporates misclassified examples to refine model understanding of classification boundaries. Using dialogue data from a middle school collaborative game-based learning environment, our approach substantially improves classification accuracy over zero-shot baselines. Qualitative analysis of the resulting models further highlights which dialogue types are most frequently misclassified, suggesting design implications for adaptive scaffolding. These findings demonstrate that large language models, when guided with targeted prompting strategies, can effectively recognize productive and unproductive dialogue in collaborative learning.

Anneliese Brei, Katharine Henry, Abhisheik Sharma, Shashank Srivastava, Snigdha Chaturvedi. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Concept erasure is the task of erasing information about a concept (e.g., gender or race) from a representation set while retaining the maximum possible utility – information from original representations. Concept erasure is useful in several applications, such as removing sensitive concepts to achieve fairness and interpreting the impact of specific concepts on a model’s performance. Previous concept erasure techniques have prioritized robustly erasing concepts over retaining the utility of the resultant representations. However, there seems to be an inherent tradeoff between erasure and retaining utility, making it unclear how to achieve perfect concept erasure while maintaining high utility. In this paper, we offer a fresh perspective toward solving this problem by quantifying the fundamental limits of concept erasure through an information-theoretic lens. Using these results, we investigate constraints on the data distribution and the erasure functions required to achieve the limits of perfect concept erasure. Empirically, we show that the derived erasure functions achieve the optimal theoretical bounds. Additionally, we show that our approach outperforms existing methods on a range of synthetic and real-world datasets using GPT-4 representations.

Machine unlearning is the process of efficiently removing the influence of a training data instance from a trained machine learning model without retraining it from scratch. A popular subclass of unlearning approaches is exact machine unlearning, which focuses on techniques that explicitly guarantee the removal of the influence of a data instance from a model. Exact unlearning approaches use a machine learning model in which individual components are trained on disjoint subsets of the data. During deletion, exact unlearning approaches only retrain the affected components rather than the entire model. While existing approaches reduce retraining costs, it can still be expensive for an organization to retrain a model component as it requires halting a system in production, which leads to service failure and adversely impacts customers. To address these challenges, we introduce an exact unlearning framework -- Sequence-aware Sharded Sliced Training (S3T), which is designed to enhance the deletion capabilities of an exact unlearning system while minimizing the impact on model's performance. At the core of S3T, we utilize a lightweight parameter-efficient fine-tuning approach that enables parameter isolation by sequentially training layers with disjoint data slices. This enables efficient unlearning by simply deactivating the layers affected by data deletion. Furthermore, to reduce the retraining cost and improve model performance, we train the model on multiple data sequences, which allows S3T to handle an increased number of deletion requests. Both theoretically and empirically, we demonstrate that S3T attains superior deletion capabilities and enhanced performance compared to baselines across a wide range of settings.

Haoyuan Li, Yusen Zhang, Rui Zhang, Snigdha Chaturvedi. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Anvesh Rao Vijjini, Somnath Basu Roy Chowdhury, Snigdha Chaturvedi. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Efficient neural networks are essential for scaling machine learning models to real-time applications and resource-constrained environments. Fully-connected feedforward layers (FFLs) introduce computation and parameter count bottlenecks within neural network architectures. To address this challenge, in this work, we propose a new class of dense layers that generalize standard fully-connected feedforward layers, $\textbf{E}$fficient, $\textbf{U}$nified and $\textbf{Gen}$eral dense layers (EUGens). EUGens leverage random features to approximate standard FFLs and go beyond them by incorporating a direct dependence on the input norms in their computations. The proposed layers unify existing efficient FFL extensions and improve efficiency by reducing inference complexity from quadratic to linear time. They also lead to $\textbf{the first}$ unbiased algorithms approximating FFLs with arbitrary polynomial activation functions. Furthermore, EuGens reduce the parameter count and computational overhead while preserving the expressive power and adaptability of FFLs. We also present a layer-wise knowledge transfer technique that bypasses backpropagation, enabling efficient adaptation of EUGens to pre-trained models. Empirically, we observe that integrating EUGens into Transformers and MLPs yields substantial improvements in inference speed (up to $\textbf{27}$\%) and memory efficiency (up to $\textbf{30}$\%) across a range of tasks, including image classification, language model pre-training, and 3D scene reconstruction. Overall, our results highlight the potential of EUGens for the scalable deployment of large-scale neural networks in real-world scenarios.

Fairness, especially group fairness, is an important consideration in the context of machine learning systems. The most commonly adopted group fairness-enhancing techniques are in-processing methods that rely on a mixture of a fairness objective (e.g., demographic parity) and a task-specific objective (e.g., cross-entropy) during the training process. However, when data arrives in an online fashion – one instance at a time – optimizing such fairness objectives poses several challenges. In particular, group fairness objectives are defined using expectations of predictions across different demographic groups. In the online setting, where the algorithm has access to a single instance at a time, estimating the group fairness objective requires additional storage and significantly more computation (e.g., forward/backward passes) than the task-specific objective at every time step. In this paper, we propose Aranyani, an ensemble of oblique decision trees, to make fair decisions in online settings. The hierarchical tree structure of Aranyani enables parameter isolation and allows us to efficiently compute the fairness gradients using aggregate statistics of previous decisions, eliminating the need for additional storage and forward/backward passes. We also present an efficient framework to train Aranyani and theoretically analyze several of its properties. We conduct empirical evaluations on 5 publicly available benchmarks (including vision and language datasets) to show that Aranyani achieves a better accuracy-fairness trade-off compared to baseline approaches.

Haoyuan Li, Snigdha Chaturvedi. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

We present a new class of fast polylog-linear algorithms based on the theory of structured matrices (in particular *low displacement rank*) for integrating tensor fields defined on weighted trees. Several applications of the resulting *fast tree-field integrators* (FTFIs) are presented, including: (a) approximation of graph metrics with tree metrics, (b) graph classification, (c) modeling on meshes, and finally (d) *Topological Transformers* (TTs) (Choromanski et al., 2022) for images. For Topological Transformers, we propose new relative position encoding (RPE) masking mechanisms with as few as **three** extra learnable parameters per Transformer layer, leading to **1.0-1.5\%+** accuracy gains. Importantly, most of FTFIs are **exact** methods, thus numerically equivalent to their brute-force counterparts. When applied to graphs with thousands of nodes, those exact algorithms provide **5.7-13x** speedups. We also provide an extensive theoretical analysis of our methods.

Recent efforts to scale Transformer models have demonstrated rapid progress across a wide range of tasks (Wei at. al 2022). However, fine-tuning these models for downstream tasks is quite expensive due to their large parameter counts. Parameter-efficient fine-tuning (PEFT) approaches have emerged as a viable alternative, allowing us to fine-tune models by updating only a small number of parameters. In this work, we propose a general framework for parameter efficient fine-tuning (PEFT), based on *structured unrestricted-rank matrices* (SURM) which can serve as a drop-in replacement for popular approaches such as Adapters and LoRA. Unlike other methods like LoRA, SURMs give us more flexibility in finding the right balance between compactness and expressiveness. This is achieved by using *low displacement rank matrices* (LDRMs), which hasn't been used in this context before. SURMs remain competitive with baselines, often providing significant quality improvements while using a smaller parameter budget. SURMs achieve: **5**-**7**% accuracy gains on various image classification tasks while replacing low-rank matrices in LoRA and: up to **12x** reduction of the number of parameters in adapters (with virtually no loss in quality) on the GLUE benchmark.

Machine learning systems are often deployed for making critical decisions like credit lending, hiring, etc. While making decisions, such systems often encode the user's demographic information (like gender, age) in their intermediate representations. This can lead to decisions that are biased towards specific demographics. Prior work has focused on debiasing intermediate representations to ensure fair decisions. However, these approaches fail to remain fair with changes in the task or demographic distribution. To ensure fairness in the wild, it is important for a system to adapt to such changes as it accesses new data in an incremental fashion. In this work, we propose to address this issue by introducing the problem of learning fair representations in an incremental learning setting. To this end, we present Fairness-aware Incremental Representation Learning (FaIRL), a representation learning system that can sustain fairness while incrementally learning new tasks. FaIRL is able to achieve fairness and learn new tasks by controlling the rate-distortion function of the learned representations. Our empirical evaluations show that FaIRL is able to make fair decisions while achieving high performance on the target task, outperforming several baselines.

We present two new classes of algorithms for efficient field integration on graphs encoding point cloud data. The first class, $\mathrm{SeparatorFactorization}$ (SF), leverages the bounded genus of point cloud mesh graphs, while the second class, $\mathrm{RFDiffusion}$ (RFD), uses popular $\epsilon$-nearest-neighbor graph representations for point clouds. Both can be viewed as providing the functionality of Fast Multipole Methods (FMMs), which have had a tremendous impact on efficient integration, but for non-Euclidean spaces. We focus on geometries induced by distributions of walk lengths between points (e.g. shortest-path distance). We provide an extensive theoretical analysis of our algorithms, obtaining new results in structural graph theory as a byproduct. We also perform exhaustive empirical evaluation, including on-surface interpolation for rigid and deformable objects (in particular for mesh-dynamics modeling) as well as Wasserstein distance computations for point clouds, including the Gromov-Wasserstein variant.

Distributed representations provide a vector space that captures meaningful relationships between data instances. The distributed nature of these representations, however, entangles together multiple attributes or concepts of data instances (e.g., the topic or sentiment of a text, characteristics of the author (age, gender, etc), etc). Recent work has proposed the task of concept erasure, in which rather than making a concept predictable, the goal is to remove an attribute from distributed representations while retaining other information from the original representation space as much as possible. In this paper, we propose a new distance metric learning-based objective, the Kernelized Rate-Distortion Maximizer (KRaM), for performing concept erasure. KRaM fits a transformation of representations to match a specified distance measure (defined by a labeled concept to erase) using a modified rate-distortion function. Specifically, KRaM's objective function aims to make instances with similar concept labels dissimilar in the learned representation space while retaining other information. We find that optimizing KRaM effectively erases various types of concepts—categorical, continuous, and vector-valued variables—from data representations across diverse domains. We also provide a theoretical analysis of several properties of KRaM's objective. To assess the quality of the learned representations, we propose an alignment score to evaluate their similarity with the original representation space. Additionally, we conduct experiments to showcase KRaM's efficacy in various settings, from erasing binary gender variables in word embeddings to vector-valued variables in GPT-3 representations.

Opinion summarization is the task of automatically generating summaries that encapsulate information from multiple user reviews.We present Semantic Autoencoder (SemAE) to perform extractive opinion summarization in an unsupervised manner.SemAE uses dictionary learning to implicitly capture semantic information from the review and learns a latent representation of each sentence over semantic units.A semantic unit is supposed to capture an abstract semantic concept.Our extractive summarization algorithm leverages the representations to identify representative opinions among hundreds of reviews.Se-mAE is also able to perform controllable summarization to generate aspect-specific summaries.We report strong performance on SPACE and AMAZON datasets, and perform experiments to investigate the functioning of our model.

Pretrained language models (PLMs) have been shown to accumulate factual knowledge during pretraining (Petroni et al., 2019).Recent works probe PLMs for the extent of this knowledge through prompts either in discrete or continuous forms.However, these methods do not consider symmetry of the task: object prediction and subject prediction.In this work, we propose Symmetrical Prompt Enhancement (SPE), a continuous prompt-based method for factual probing in PLMs that leverages the symmetry of the task by constructing symmetrical prompts for subject and object prediction.Our results on a popular factual probing dataset, LAMA, show significant improvement of SPE over previous probing methods.

In this paper, we introduce the task of modeling interpersonal relationships for story generation.For addressing this task, we propose Relationships as Latent Variables for Story Generation, (RELIST).RELIST generates stories sentence by sentence and has two major components -a relationship selector and a story continuer.The relationship selector specifies a latent variable to pick the relationship to exhibit in the next sentence and the story continuer generates the next sentence while expressing the selected relationship in a coherent way.Our automatic and human evaluations demonstrate that RELIST is able to generate stories with relationships that are more faithful to desired relationships while maintaining the content quality.The relationship assignments to sentences during inference brings interpretability to RELIST.

Abstract Text representations learned by machine learning models often encode undesirable demographic information of the user. Predictive models based on these representations can rely on such information, resulting in biased decisions. We present a novel debiasing technique, Fairness-aware Rate Maximization (FaRM), that removes protected information by making representations of instances belonging to the same protected attribute class uncorrelated, using the rate-distortion function. FaRM is able to debias representations with or without a target task at hand. FaRM can also be adapted to remove information about multiple protected attributes simultaneously. Empirical evaluations show that FaRM achieves state-of-the-art performance on several datasets, and learned representations leak significantly less protected attribute information against an attack by a non-linear probing network.

The task of organizing a shuffled set of sentences into a coherent text has been used to evaluate a machine's understanding of causal and temporal relations.We formulate the sentence ordering task as a conditional textto-marker generation problem.We present Reorder-BART (RE-BART) that leverages a pre-trained Transformer-based model to identify a coherent order for a given set of shuffled sentences.The model takes a set of shuffled sentences with sentence-specific markers as input and generates a sequence of position markers of the sentences in the ordered text.RE-BART achieves the state-of-the-art performance across 7 datasets in Perfect Match Ratio (PMR) and Kendall's tau (τ ).We perform evaluations in a zero-shot setting, showcasing that our model is able to generalize well across other datasets.We additionally perform several experiments to understand the functioning and limitations of our framework.

Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task.We aim to scrub such undesirable attributes and learn fair representations while maintaining performance on the target task.In this paper, we present an adversarial learning framework "Adversarial Scrubber" (ADS), to debias contextual representations.We perform theoretical analysis to show that our framework converges without leaking demographic information under certain conditions.We extend previous evaluation techniques by evaluating debiasing performance using Minimum Description Length (MDL) probing.Experimental evaluations on 8 datasets show that ADS generates representations with minimal information about demographic attributes while being maximally informative about the target task.

This paper describes an experience in teaching Machine Learning (ML) and Natural Language Processing (NLP) to a group of high school students over an intense one-month period. In this work, we provide an outline of an AI course curriculum we designed for high school students and then evaluate its effectiveness by analyzing student's feedback and student outcomes. After closely observing students, evaluating their responses to our surveys, and analyzing their contribution to the course project, we identified some possible impediments in teaching AI to high school students and propose some measures to avoid them. These measures include employing a combination of objectivist and constructivist pedagogies, reviewing/introducing basic programming concepts at the beginning of the course, and addressing gender discrepancies throughout the course.

Opinion summarization from online product reviews is a challenging task, which involves identifying opinions related to various aspects of the product being reviewed. While previous works require additional human effort to identify relevant aspects, we instead apply domain knowledge from external sources to automatically achieve the same goal. This work proposes AspMem, a generative method that contains an array of memory cells to store aspect-related knowledge. This explicit memory can help obtain a better opinion representation and infer the aspect information more precisely. We evaluate this method on both aspect identification and opinion summarization tasks. Our experiments show that AspMem outperforms the state-of-the-art methods even though, unlike the baselines, it does not rely on human supervision which is carefully handcrafted for the given tasks.

Despite the pervasiveness of clinical depression in modern society, professional help remains highly stigmatized, inaccessible, and expensive.Accurately diagnosing depression is difficult-requiring time-intensive interviews, assessments, and analysis.Hence, automated methods that can assess linguistic patterns in these interviews could help psychiatric professionals make faster, more informed decisions about diagnosis.We propose JLPC, a method that analyzes interview transcripts to identify depression while jointly categorizing interview prompts into latent categories.This latent categorization allows the model to identify high-level conversational contexts that influence patterns of language in depressed individuals.We show that the proposed model not only outperforms competitive baselines, but that its latent prompt categories provide psycholinguistic insights about depression.

Generating sequential natural language descriptions from graph-structured data (e.g., knowledge graph) is challenging, partly because of the structural differences between the input graph and the output text.Hence, popular sequence-to-sequence models, which require serialized input, are not a natural fit for this task.Graph neural networks, on the other hand, can better encode the input graph but broaden the structural gap between the encoder and decoder, making faithful generation difficult.To narrow this gap, we propose DUA-LENC, a dual encoding model that can not only incorporate the graph structure, but can also cater to the linear structure of the output text.Empirical comparisons with strong single-encoder baselines demonstrate that dual encoding can significantly improve the quality of the generated text.

Emotions and their evolution play a central role in creating a captivating story.In this paper, we present the first study on modeling the emotional trajectory of the protagonist in neural storytelling.We design methods that generate stories that adhere to given story titles and desired emotion arcs for the protagonist.Our models include Emotion Supervision (Emo-Sup) and two Emotion-Reinforced (EmoRL) models.The EmoRL models use special rewards designed to regularize the story generation process through reinforcement learning.Our automatic and manual evaluations demonstrate that these models are significantly better at generating stories that follow the desired emotion arcs compared to baseline methods, without sacrificing story quality.

Supervised machine learning assumes the availability of fully-labeled data, but in many cases, such as low-resource languages, the only data available is partially annotated.We study the problem of Named Entity Recognition (NER) with partially annotated training data in which a fraction of the named entities are labeled, and all other tokens, entities or otherwise, are labeled as non-entity by default.In order to train on this noisy dataset, we need to distinguish between the true and false negatives.To this end, we introduce a constraintdriven iterative algorithm that learns to detect false negatives in the noisy set and downweigh them, resulting in a weighted training set.With this set, we train a weighted NER model.We evaluate our algorithm with weighted variants of neural and non-neural NER models on data in 8 languages from several language and script families, showing strong ability to learn from partial data.Finally, to show real-world efficacy, we evaluate on a Bengali NER corpus annotated by non-speakers, outperforming the prior state-of-the-art by over 5 points F1.

Massive online courses occupy an important place in the educational landscape of today. We study an approach to scale predictive analytic models derived from online course discussion fora--specifically that of confusion detection--onto other courses. The primary challenge here is the lack of labeled examples in a new course and this calls for unsupervised domain adaptation (DA). As a first step in exploring DA in the education domain, we propose a simple algorithm, DiAd, which adapts a classifier trained on a course with labeled data by selectively choosing instances from a new course (with no labeled data) that are most dissimilar to the course with labeled data and on which the classifier is very confident of classification. Our algorithm is empirically validated on the confusion detection task across multiple online courses. We find that DiAd outperforms other methods on the target domain, while showing a comparable performance to a popular method that uses labeled data from the target domain.

Daniel Khashabi, Snigdha Chaturvedi, Michael Roth, Shyam Upadhyay, Dan Roth. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

Understanding inter-character relationships is fundamental for understanding character intentions and goals in a narrative. This paper addresses unsupervised modeling of relationships between characters. We model relationships as dynamic phenomenon, represented as evolving sequences of latent states empirically learned from data. Unlike most previous work our approach is completely unsupervised. This enables data-driven inference of inter-character relationship types beyond simple sentiment polarities, by incorporating lexical and semantic representations, and leveraging large quantities of raw text. We present three models based on rich sets of linguistic features that capture various cues about relationships. We compare these models with existing techniques and also demonstrate that relationship categories learned by our model are semantically coherent.

Understanding stories -sequences of events -is a crucial yet challenging natural language understanding task.These events typically carry multiple aspects of semantics including actions, entities and emotions.Not only does each individual aspect contribute to the meaning of the story, so does the interaction among these aspects.Building on this intuition, we propose to jointly model important aspects of semantic knowledge -frames, entities and sentiments -via a semantic language model.We achieve this by first representing these aspects' semantic units at an appropriate level of abstraction and then using the resulting vector representations for each semantic aspect to learn a joint representation via a neural language model.We show that the joint semantic language model is of high quality and can generate better semantic sequences than models that operate on the word level.We further demonstrate that our joint model can be applied to story cloze test and shallow discourse parsing tasks with improved performance and that each semantic aspect contributes to the model.

Automatic story comprehension is a fundamental challenge in Natural Language Understanding, and can enable computers to learn about social norms, human behavior and commonsense.In this paper, we present a story comprehension model that explores three distinct semantic aspects: (i) the sequence of events described in the story, (ii) its emotional trajectory, and (iii) its plot consistency.We judge the model's understanding of real-world stories by inquiring if, like humans, it can develop an expectation of what will happen next in a given story.Specifically, we use it to predict the correct ending of a given short story from possible alternatives.The model uses a hidden variable to weigh the semantic aspects in the context of the story.Our experiments demonstrate the potential of our approach to characterize these semantic aspects, and the strength of the hidden variable based approach.The model outperforms the stateof-the-art approaches and achieves best results on a publicly available dataset.

The ability to comprehend wishes or desires and their fulfillment is important to Natural Language Understanding. This paper introduces the task of identifying if a desire expressed by a subject in a given short piece of text was fulfilled. We propose various unstructured and structured models that capture fulfillment cues such as the subject's emotional state and actions. Our experiments with two different datasets demonstrate the importance of understanding the narrative and discourse structure to address this task.

Studying characters plays a vital role in computationally representing and interpreting narratives. Unlike previous work, which has focused on inferring character roles, we focus on the problem of modeling their relationships. Rather than assuming a fixed relationship for a character pair, we hypothesize that relationships temporally evolve with the progress of the narrative, and formulate the problem of relationship modeling as a structured prediction problem. We propose a semi-supervised framework to learn relationship sequences from fully as well as partially labeled data. We present a Markovian model capable of accumulating historical beliefs about the relationship and status changes. We use a set of rich linguistic and semantically motivated features that incorporate world knowledge to investigate the textual content of narrative. We empirically demonstrate that such a framework outperforms competitive baselines.

Characterizing relationships between people is fundamental for the understanding of narratives. In this work, we address the problem of inferring the polarity of relationships between people in narrative summaries. We formulate the problem as a joint structured prediction for each narrative, and present a general model that combines evidence from linguistic and semantic features, as well as features based on the structure of the social community in the text. We additionally provide a clustering-based approach that can exploit regularities in narrative types. e.g., learn an affinity for love-triangles in romantic stories. On a dataset of movie summaries from Wikipedia, our structured models provide more than 30% error-reduction over a competitive baseline that considers pairs of characters in isolation.

Mohit Iyyer, Anupam Guha, Snigdha Chaturvedi, Jordan Boyd-Graber, Hal Daumé III. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016.

New scientific concepts, interpreted broadly, are continuously introduced in the literature, but relatively few concepts have a long‐term impact on society. The identification of such concepts is a challenging prediction task that would help multiple parties—including researchers and the general public—focus their attention within the vast scientific literature. In this paper we present a system that predicts the future impact of a scientific concept, represented as a technical term, based on the information available from recently published research articles. We analyze the usefulness of rich features derived from the full text of the articles through a variety of approaches, including rhetorical sentence analysis, information extraction, and time‐series analysis. The results from two large‐scale experiments with 3.8 million full‐text articles and 48 million metadata records support the conclusion that full‐text features are significantly more useful for prediction than metadata‐only features and that the most accurate predictions result from combining the metadata and full‐text features. Surprisingly, these results hold even when the metadata features are available for a much larger number of documents than are available for the full‐text features.

Instructor intervention in student discussion forums is a vital component in Massive Open Online Courses (MOOCs), where personalized interaction is limited. This paper introduces the problem of predicting instructor interventions in MOOC forums. We propose several prediction models designed to capture unique aspects of MOOCs, combining course information, forum structure and posts content. Our models abstract contents of individual posts of threads using latent categories, learned jointly with the binary intervention prediction problem. Experiments over data from two Coursera MOOCs demonstrate that incorporating the structure of threads into the learning problem leads to better predictive performance.

Web searches are increasingly formulated as natural language questions, rather than keyword queries. Retrieving answers to such questions requires a degree of understanding of user expectations. An important step in this direction is to automatically infer the type of answer implied by the question, e.g., factoids, statements on a topic, instructions, reviews, etc. Answer Type taxonomies currently exist for factoid-style questions, but not for open-domain questions. Building taxonomies for non-factoid questions is a harder problem since these questions can come from a very broad semantic space. A few attempts have been made to develop taxonomies for non-factoid questions, but these tend to be too narrow or domain specific. In this paper, we address this problem by modeling the Answer Type as a latent variable that is learned in a data-driven fashion, allowing the model to be more adaptive to new domains and data sets. We propose approaches that detect the relevance of candidate answers to a user question by jointly 'clustering' questions according to the hidden variable, and modeling relevance conditioned on this hidden variable.

Abstract An important part of network analysis is understanding community structures like topological clusters and attribute‐based groups. Standard approaches for showing communities using colour, shape, rectangular bounding boxes, convex hulls or force‐directed layout algorithms remain valuable, however our Group‐in‐a‐Box meta‐layouts add a fresh strategy for presenting community membership, internal structure and inter‐cluster relationships. This paper extends the basic Group‐in‐a‐Box meta‐layout, which uses a Treemap substrate of rectangular regions whose size is proportional to community size. When there are numerous inter‐community relationships, the proposed extensions help users view them more clearly: (1) the Croissant–Doughnut meta‐layout applies empirically determined rules for box arrangement to improve space utilization while still showing inter‐community relationships, and (2) the Force‐Directed layout arranges community boxes based on their aggregate ties at the cost of additional space. Our free and open source reference implementation in NodeXL includes heuristics to choose what we have found to be the preferable Group‐in‐a‐Box meta‐layout to show networks with varying numbers or sizes of communities. Case study examples, a pilot comparative user preference study (nine participants), and a readability measure‐based evaluation of 309 Twitter networks demonstrate the utility of the proposed meta‐layouts.

Data quality is a perennial problem for many enterprise data assets. To improve data quality, businesses often employ rule based data standardization systems in which domain experts code rules for handling important and prevalent patterns. Finding these patterns is laborious and time consuming, particularly for noisy or highly specialized data sets. It is also subjective to the persons determining these patterns. In this paper we present a tool to automatically mine patterns that can help in improving the efficiency and effectiveness of these data standardization systems. The automatically extracted patterns are used by the domain and knowledge experts for rule writing. We use a greedy algorithm to extract patterns that result in a maximal coverage of data. We further group the extracted patterns such that each group represents patterns that capture similar domain knowledge. We propose a similarity measure that uses input pattern semantics to group these patterns. We demonstrate the effectiveness of our method for standardization tasks on three real world datasets.

This paper proposes a space-efficient, discriminatively enhanced topic model: a V structured topic model with an embedded log-linear component. The discriminative log-linear component reduces the number of parameters to be learnt while outperforming baseline generative models. At the same time, the explanatory power of the generative component is not compromised. We establish its superiority over a purely generative model by applying it to two different ranking tasks: (a) In the first task, we look at the problem of proposing alternative citations given textual and bibliographic evidence. We solve it as a ranking problem in itself and as a platform for further qualitative analysis of convergence of scientific phenomenon. (b) In the second task we address the problem of ranking potential email recipients based on email content and sender information.

Rule based systems for processing text data encode the knowledge of a human expert into a rule base to take decisions based on interactions of the input data and the rule base. Similarly, supervised learning based systems can learn patterns present in a given dataset to make decisions on similar and other related data. Performances of both these classes of models are largely dependent on the training examples seen by them, based on which the learning was performed. Even though trained models might fit well on training data, the accuracies they yield on a new test data may be considerably different. Computing the accuracy of the learnt models on new unlabeled datasets is a challenging problem requiring costly labeling, and which is still likely to only cover a subset of the new data because of the large sizes of datasets involved. In this paper, we present a method to estimate the accuracy of a given model on a new dataset without manually labeling the data. We verify our method on large datasets for two shallow text processing tasks: document classification and postal address segmentation, and using both supervised machine learning methods and human generated rule based models.