Yiyang Gu, Junwei Yang, Junyu Luo, Ye Yuan, Bin Feng, Yingce Xia, Shufang Xie, Kaili Liu, Bohan Wu, Qi Shi, Haoran Li, Beier Xiao, Zhiping Xiao, Xiao Luo, Weizhi Zhang, Philip S. Yu, Zequn Liu, Ming Zhang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Drug-Target binding Affinity (DTA) prediction is essential for drug discovery. Despite the application of deep learning methods to DTA prediction, the achieved accuracy remain suboptimal. In this work, inspired by the recent success of retrieval methods, we propose kNN-DTA, a non-parametric embedding-based retrieval method adopted on a pre-trained DTA prediction model, which can extend the power of the DTA model with no or negligible cost. Different from existing methods, we introduce two neighbor aggregation ways from both embedding space and label space that are integrated into a unified framework. Specifically, we propose a label aggregation with pair-wise retrieval and a representation aggregation with point-wise retrieval of the nearest neighbors. This method executes in the inference phase and can efficiently boost the DTA prediction performance with no training cost. In addition, we propose an extension, Ada-kNN-DTA, an instance-wise and adaptive aggregation with lightweight learning. Results on four benchmark datasets show that kNN-DTA brings significant improvements, outperforming previous state-of-the-art (SOTA) results, e.g, on BindingDB IC50 and Ki testbeds, kNN-DTA obtains new records of RMSE 0.684 and 0.750 . The extended Ada-kNN-DTA further improves the performance to be 0.675 and 0.735 RMSE. These results strongly prove the effectiveness of our method. Results in other settings and comprehensive studies/analyses also show the great potential of our kNN-DTA approach.

Retrosynthesis, which predicts the reactants of a given target molecule, is an essential task for drug discovery. In recent years, the machine learing based retrosynthesis methods have achieved promising results. In this work, we introduce RetroKNN, a local reaction template retrieval method to further boost the performance of template-based systems with non-parametric retrieval. We first build an atom-template store and a bond-template store that contains the local templates in the training data, then retrieve from these templates with a k-nearest-neighbor (KNN) search during inference. The retrieved templates are combined with neural network predictions as the final output. Furthermore, we propose a lightweight adapter to adjust the weights when combing neural network and KNN predictions conditioned on the hidden representation and the retrieved templates. We conduct comprehensive experiments on two widely used benchmarks, the USPTO-50K and USPTO-MIT. Especially for the top-1 accuracy, we improved 7.1% on the USPTO-50K dataset and 12.0% on the USPTO-MIT dataset.These results demonstrate the effectiveness of our method.

one setup is more effective than another. In this work, we uncover the underlying characteristics of effective sets. For each training instance, we form a large, diverse pool of candidates and systematically vary the subsets used for calibration fine-tuning. Each selection strategy targets distinct aspects of the sets, such as lexical diversity or the size of the gap between positive and negatives. On three diverse scientific long-form summarization datasets (spanning biomedical, clinical, and chemical domains), we find, among others, that faithfulness calibration is optimal when the negative sets are extractive and more likely to be generated, whereas for relevance calibration, the metric margin between candidates should be maximized and surprise-the disagreement between model and metric defined candidate rankings-minimized. Code to create, select, and optimize calibration sets is available at https://github.com/griff4692/calibrating-summaries.

Recent advancements in biological research leverage the integration of molecules, proteins, and natural language to enhance drug discovery.However, current models exhibit several limitations, such as the generation of invalid molecular SMILES, underutilization of contextual information, and equal treatment of structured and unstructured knowledge.To address these issues, we propose BioT5, a comprehensive pretraining framework that enriches cross-modal integration in biology with chemical knowledge and natural language associations.BioT5 utilizes SELFIES for 100% robust molecular representations and extracts knowledge from the surrounding context of bio-entities in unstructured biological literature.Furthermore, BioT5 distinguishes between structured and unstructured knowledge, leading to more effective utilization of information.After fine-tuning, BioT5 shows superior performance across a wide range of tasks, demonstrating its strong capability of capturing underlying relations and properties of bio-entities.Our code is available at https://github.com/QizhiPei/BioT5.

Retrosynthesis, which aims to find a route to synthesize a target molecule from commercially available starting materials, is a critical task in drug discovery and materials design. Recently, the combination of ML-based single-step reaction predictors with multi-step planners has led to promising results. However, the single-step predictors are mostly trained offline to optimize the single-step accuracy, without considering complete routes. Here, we leverage reinforcement learning (RL) to improve the single-step predictor, by using a tree-shaped MDP to optimize complete routes. Specifically, we propose a novel online training algorithm, called Planning with Dual Value Networks (PDVN), which alternates between the planning phase and updating phase. In PDVN, we construct two separate value networks to predict the synthesizability and cost of molecules, respectively. To maintain the single-step accuracy, we design a two-branch network structure for the single-step predictor. On the widely-used USPTO dataset, our PDVN algorithm improves the search success rate of existing multi-step planners (e.g., increasing the success rate from 85.79% to 98.95% for Retro$^{\ast}$, and reducing the number of model calls by half while solving 99.47% molecules for RetroGraph). Additionally, PDVN helps find shorter synthesis routes (e.g., reducing the average route length from 5.76 to 4.83 for Retro$^{\ast}$, and from 5.63 to 4.78 for RetroGraph).

Antibodies are proteins that effectively protect the human body by binding to pathogens. Recently, deep learning-based computational antibody design has attracted popular attention since it automatically mines the antibody patterns from data that could be complementary to human experiences. However, the computational methods heavily rely on high-quality antibody structure data, which is quite limited. Besides, the complementarity-determining region (CDR), which is the key component of an antibody that determines the specificity and binding affinity, is highly variable and hard to predict. Therefore, the limited availability of high-quality antibody structure data exacerbates the difficulty of CDR generation. Fortunately, there is a large amount of sequence data for antibodies that can help model the CDR and reduce reliance on structure data. By witnessing the success of pre-training models for protein modeling, in this paper, we develop the antibody pre-training language model and incorporate it into the antigen-specific antibody design model in a systemic way. Specifically, we first pre-train a novel antibody language model based on the sequence data, then propose a one-shot way for sequence and structure generation of CDR to mitigate the high cost and error propagation associated with autoregressive methods, and finally leverage the pre-trained antibody model for the antigen-specific antibody generation model with some carefully designed modules. Our experiments demonstrate the superiority of our method over previous baselines in tasks such as sequence and structure generation, CDR-H3 design for antigen binding, and antibody optimization1. The code is available at https://github.com/KyGao/ABGNN.

Molecular pre-training, which is about to learn an effective representation for molecules on large amount of data, has attracted substantial attention in cheminformatics and bioinformatics. A molecule can be viewed as either a graph (where atoms are connected by bonds) or a SMILES sequence (where depth-first-search is applied to the molecular graph with specific rules). The Transformer and graph neural networks (GNN) are two representative methods to deal with the sequential data and the graphic data, which can globally and locally model the molecules respectively and are supposed to be complementary. In this work, we propose to leverage both representations and design a new pre-training algorithm, dual-view molecule pre-training (briefly, DVMP), that can effectively combine the strengths of both types of molecule representations. DVMP has a Transformer branch and a GNN branch, and the two branches are pre-trained to maintain the semantic consistency of molecules. After pre-training, we can use either the Transformer branch (this one is recommended according to empirical results), the GNN branch, or both for downstream tasks. DVMP is tested on 11 molecular property prediction tasks and outperforms strong baselines. Furthermore, we test DVMP on three retrosynthesis tasks and it achieves state-of-the-art results. Our code is released at https://github.com/microsoft/DVMP.

Modeling the interaction between proteins and ligands and accurately predicting their binding structures is a critical yet challenging task in drug discovery. Recent advancements in deep learning have shown promise in addressing this challenge, with sampling-based and regression-based methods emerging as two prominent approaches. However, these methods have notable limitations. Sampling-based methods often suffer from low efficiency due to the need for generating multiple candidate structures for selection. On the other hand, regression-based methods offer fast predictions but may experience decreased accuracy. Additionally, the variation in protein sizes often requires external modules for selecting suitable binding pockets, further impacting efficiency. In this work, we propose FABind, an end-to-end model that combines pocket prediction and docking to achieve accurate and fast protein-ligand binding. FABind incorporates a unique ligand-informed pocket prediction module, which is also leveraged for docking pose estimation. The model further enhances the docking process by incrementally integrating the predicted pocket to optimize protein-ligand binding, reducing discrepancies between training and inference. Through extensive experiments on benchmark datasets, our proposed FABind demonstrates strong advantages in terms of effectiveness and efficiency compared to existing methods. Our code is available at https://github.com/QizhiPei/FABind.

Dialogue summarization, which aims to generate a summary for an input dialogue, plays a vital role in intelligent dialogue systems. The end-to-end models have achieved satisfactory performance in summarization, but the success is built upon enough annotated data, which is costly to obtain, especially in the dialogue summarization. To leverage the rich external data, previous works first pre-train the model on the other domain data (e.g., the news domain), and then fine-tune it directly on the dialogue domain. The data from different domains are equally treated during the training process, while the vast differences between dialogues (usually informal, repetitive, and with multiple speakers) and conventional articles (usually formal and concise) are neglected. In this work, we propose to use a disentangled representation method to reduce the deviation between data in different domains, where the input data is disentangled into domain-invariant and domain-specific representations. The domain-invariant representation carries context information that is supposed to be the same across domains (e.g., news, dialogue) and the domain-specific representation indicates the input data belongs to a particular domain. We use adversarial learning and contrastive learning to constrain the disentangled representations to the target space. Furthermore, we propose two novel reconstruction strategies, namely backtracked and cross-track reconstructions, which aim to reduce the domain characteristics of out-of-domain data and mitigate the domain bias of the model. Experimental results on three public datasets show that our model significantly outperforms the strong baselines.

Precisely predicting the drug-drug interaction (DDI) is an important application and host research topic in drug discovery, especially for avoiding the adverse effect when using drug combination treatment for patients. Nowadays, machine learning and deep learning methods have achieved great success in DDI prediction. However, we notice that most of the works ignore the importance of the relation type when building the DDI prediction models. In this work, we propose a novel R$^2$-DDI framework, which introduces a relation-aware feature refinement module for drug representation learning. The relation feature is integrated into drug representation and refined in the framework. With the refinement features, we also incorporate the consistency training method to regularize the multi-branch predictions for better generalization. Through extensive experiments and studies, we demonstrate our R$^2$-DDI approach can significantly improve the DDI prediction performance over multiple real-world datasets and settings, and our method shows better generalization ability with the help of the feature refinement design.

Accurate prediction of drug-target affinity (DTA) is of vital importance in early-stage drug discovery, facilitating the identification of drugs that can effectively interact with specific targets and regulate their activities. While wet experiments remain the most reliable method, they are time-consuming and resource-intensive, resulting in limited data availability that poses challenges for deep learning approaches. Existing methods have primarily focused on developing techniques based on the available DTA data, without adequately addressing the data scarcity issue. To overcome this challenge, we present the Semi-Supervised Multi-task training (SSM) framework for DTA prediction, which incorporates three simple yet highly effective strategies: (1) A multi-task training approach that combines DTA prediction with masked language modeling using paired drug-target data. (2) A semi-supervised training method that leverages large-scale unpaired molecules and proteins to enhance drug and target representations. This approach differs from previous methods that only employed molecules or proteins in pre-training. (3) The integration of a lightweight cross-attention module to improve the interaction between drugs and targets, further enhancing prediction accuracy. Through extensive experiments on benchmark datasets such as BindingDB, DAVIS and KIBA, we demonstrate the superior performance of our framework. Additionally, we conduct case studies on specific drug-target binding activities, virtual screening experiments, drug feature visualizations and real-world applications, all of which showcase the significant potential of our work. In conclusion, our proposed SSM-DTA framework addresses the data limitation challenge in DTA prediction and yields promising results, paving the way for more efficient and accurate drug discovery processes.

In pixel-based reinforcement learning (RL), the states are raw video frames, which are mapped into hidden representation before feeding to a policy network. To improve sample efficiency of state representation learning, recently, the most prominent work is based on contrastive unsupervised representation. Witnessing that consecutive video frames in a game are highly correlated, to further improve data efficiency, we propose a new algorithm, i.e., masked contrastive representation learning for RL (M-CURL), which takes the correlation among consecutive inputs into consideration. In our architecture, besides a CNN encoder for hidden presentation of input state and a policy network for action selection, we introduce an auxiliary Transformer encoder module to leverage the correlations among video frames. During training, we randomly mask the features of several frames, and use the CNN encoder and Transformer to reconstruct them based on context frames. The CNN encoder and Transformer are jointly trained via contrastive learning where the reconstructed features should be similar to the ground-truth ones while dissimilar to others. During policy evaluation, the CNN encoder and the policy network are used to take actions, and the Transformer module is discarded. Our method achieves consistent improvements over CURL on 14 out of 16 environments from DMControl suite and 23 out of 26 environments from Atari 2600 Games. The code is available at https://github.com/teslacool/m-curl.

In many real-world scenarios, we often deal with streaming data that is sequentially collected over time. Due to the non-stationary nature of the environment, the streaming data distribution may change in unpredictable ways, which is known as the concept drift in the literature. To handle concept drift, previous methods first detect when/where the concept drift happens and then adapt models to fit the distribution of the latest data. However, there are still many cases that some underlying factors of environment evolution are predictable, making it possible to model the future concept drift trend of the streaming data, while such cases are not fully explored in previous work. In this paper, we propose a novel method DDG-DA, that can effectively forecast the evolution of data distribution and improve the performance of models. Specifically, we first train a predictor to estimate the future data distribution, then leverage it to generate training samples, and finally train models on the generated data. We conduct experiments on three real-world tasks (forecasting on stock price trend, electricity load and solar irradiance) and obtained significant improvement on multiple widely-used models.

Retrosynthetic planning, which aims to find a reaction pathway to synthesize a target molecule, plays an important role in chemistry and drug discovery. This task is usually modeled as a search problem. Recently, data-driven methods have attracted many research interests and shown promising results for retrosynthetic planning. We observe that the same intermediate molecules are visited many times in the searching process, and they are usually independently treated in previous tree-based methods (e.g., AND-OR tree search, Monte Carlo tree search). Such redundancies make the search process inefficient. We propose a graph-based search policy that eliminates the redundant explorations of any intermediate molecules. As searching over a graph is more complicated than over a tree, we further adopt a graph neural network to guide the search over graphs. Meanwhile, our method can search a batch of targets together in the graph and remove the inter-target duplication in the tree-based search methods. Experimental results on two datasets demonstrate the effectiveness of our method. Especially on the widely used USPTO benchmark, we improve the search success rate to 99.47%, advancing previous state-of-the-art performance for 2.6 points.

Molecular representation learning has attracted much attention recently. A molecule can be viewed as a 2D graph with nodes/atoms connected by edges/bonds, and can also be represented by a 3D conformation with 3-dimensional coordinates of all atoms. We note that most previous work handles 2D and 3D information separately, while jointly leveraging these two sources may foster a more informative representation. In this work, we explore this appealing idea and propose a new representation learning method based on a unified 2D and 3D pre-training. Atom coordinates and interatomic distances are encoded and then fused with atomic representations through graph neural networks. The model is pre-trained on three tasks: reconstruction of masked atoms and coordinates, 3D conformation generation conditioned on 2D graph, and 2D graph generation conditioned on 3D conformation. We evaluate our method on 11 downstream molecular property prediction tasks: 7 with 2D information only and 4 with both 2D and 3D information. Our method achieves state-of-the-art results on 10 tasks, and the average improvement on 2D-only tasks is 8.3%. Our method also achieves significant improvement on two 3D conformation generation tasks.

Pre-trained language models have attracted increasing attention in the biomedical domain, inspired by their great success in the general natural language domain. Among the two main branches of pre-trained language models in the general language domain, i.e. BERT (and its variants) and GPT (and its variants), the first one has been extensively studied in the biomedical domain, such as BioBERT and PubMedBERT. While they have achieved great success on a variety of discriminative downstream biomedical tasks, the lack of generation ability constrains their application scope. In this paper, we propose BioGPT, a domain-specific generative Transformer language model pre-trained on large-scale biomedical literature. We evaluate BioGPT on six biomedical natural language processing tasks and demonstrate that our model outperforms previous models on most tasks. Especially, we get 44.98%, 38.42% and 40.76% F1 score on BC5CDR, KD-DTI and DDI end-to-end relation extraction tasks, respectively, and 78.2% accuracy on PubMedQA, creating a new record. Our case study on text generation further demonstrates the advantage of BioGPT on biomedical literature to generate fluent descriptions for biomedical terms.

Well understanding protein function and structure in computational biology helps in the understanding of human beings. To face the limited proteins that are annotated structurally and functionally, the scientific community embraces the self-supervised pre-training methods from large amounts of unlabeled protein sequences for protein embedding learning. However, the protein is usually represented by individual amino acids with limited vocabulary size (e.g. 20 type proteins), without considering the strong local semantics existing in protein sequences. In this work, we propose a novel pre-training modeling approach SPRoBERTa. We first present an unsupervised protein tokenizer to learn protein representations with local fragment pattern. Then, a novel framework for deep pre-training model is introduced to learn protein embeddings. After pre-training, our method can be easily fine-tuned for different protein tasks, including amino acid-level prediction task (e.g. secondary structure prediction), amino acid pair-level prediction task (e.g. contact prediction) and also protein-level prediction task (remote homology prediction, protein function prediction). Experiments show that our approach achieves significant improvements in all tasks and outperforms the previous methods. We also provide detailed ablation studies and analysis for our protein tokenizer and training framework.

MOTIVATION: Molecule generation, which is to generate new molecules, is an important problem in bioinformatics. Typical tasks include generating molecules with given properties, molecular property improvement (i.e. improving specific properties of an input molecule), retrosynthesis (i.e. predicting the molecules that can be used to synthesize a target molecule), etc. Recently, deep-learning-based methods received more attention for molecule generation. The labeled data of bioinformatics is usually costly to obtain, but there are millions of unlabeled molecules. Inspired by the success of sequence generation in natural language processing with unlabeled data, we would like to explore an effective way of using unlabeled molecules for molecule generation. RESULTS: We propose a new method, back translation for molecule generation, which is a simple yet effective semisupervised method. Let X be the source domain, which is the collection of properties, the molecules to be optimized, etc. Let Y be the target domain which is the collection of molecules. In particular, given a main task which is about to learn a mapping from the source domain X to the target domain Y, we first train a reversed model g for the Y to X mapping. After that, we use g to back translate the unlabeled data in Y to X and obtain more synthetic data. Finally, we combine the synthetic data with the labeled data and train a model for the main task. We conduct experiments on molecular property improvement and retrosynthesis, and we achieve state-of-the-art results on four molecule generation tasks and one retrosynthesis benchmark, USPTO-50k. AVAILABILITY AND IMPLEMENTATION: Our code and data are available at https://github.com/fyabc/BT4MolGen. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: The interaction between drugs and targets (DTI) in human body plays a crucial role in biomedical science and applications. As millions of papers come out every year in the biomedical domain, automatically discovering DTI knowledge from biomedical literature, which are usually triplets about drugs, targets and their interaction, becomes an urgent demand in the industry. Existing methods of discovering biological knowledge are mainly extractive approaches that often require detailed annotations (e.g. all mentions of biological entities, relations between every two entity mentions, etc.). However, it is difficult and costly to obtain sufficient annotations due to the requirement of expert knowledge from biomedical domains. RESULTS: To overcome these difficulties, we explore an end-to-end solution for this task by using generative approaches. We regard the DTI triplets as a sequence and use a Transformer-based model to directly generate them without using the detailed annotations of entities and relations. Further, we propose a semi-supervised method, which leverages the aforementioned end-to-end model to filter unlabeled literature and label them. Experimental results show that our method significantly outperforms extractive baselines on DTI discovery. We also create a dataset, KD-DTI, to advance this task and release it to the community. AVAILABILITY AND IMPLEMENTATION: Our code and data are available at https://github.com/bert-nmt/BERT-DTI. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Recently the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc. Learning to reweight, which is a specific kind of teaching that reweights training data using a teacher model, receives much attention due to its simplicity and effectiveness. In existing learning to reweight works, the teacher model only utilizes shallow/surface information such as training iteration number and loss/accuracy of the student model from training/validation sets, but ignores the internal states of the student model, which limits the potential of learning to reweight. In this work, we propose an improved data reweighting algorithm, in which the student model provides its internal states to the teacher model, and the teacher model returns adaptive weights of training samples to enhance the training of the student model. The teacher model is jointly trained with the student model using meta gradients propagated from a validation set. Experiments on image classification with clean/noisy labels and neural machine translation empirically demonstrate that our algorithm makes significant improvement over previous methods.

Sequence learning has attracted much research attention from the machine learning community in recent years. In many applications, a sequence learning task is usually associated with multiple temporally correlated auxiliary tasks, which are different in terms of how much input information to use or which future step to predict. For example, (i) in simultaneous machine translation, one can conduct translation under different latency (i.e., how many input words to read/wait before translation); (ii) in stock trend forecasting, one can predict the price of a stock in different future days (e.g., tomorrow, the day after tomorrow). While it is clear that those temporally correlated tasks can help each other, there is a very limited exploration on how to better leverage multiple auxiliary tasks to boost the performance of the main task. In this work, we introduce a learnable scheduler to sequence learning, which can adaptively select auxiliary tasks for training depending on the model status and the current training data. The scheduler and the model for the main task are jointly trained through bi-level optimization. Experiments show that our method significantly improves the performance of simultaneous machine translation and stock trend forecasting.

Zhen Wu, Lijun Wu, Qi Meng, Yingce Xia, Shufang Xie, Tao Qin, Xinyu Dai, Tie-Yan Liu. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Stylized dialogue generation, which aims to generate a given-style response for an input context, plays a vital role in intelligent dialogue systems. Considering there is no parallel data between the contexts and the responses of target style S1, existing works mainly use back translation to generate stylized synthetic data for training, where the data about context, target style S1 and an intermediate style S0 is used. However, the interaction among these texts is not fully exploited, and the pseudo contexts are not adequately modeled. To overcome the above difficulties, we propose multi-pass dual learning (MPDL), which leverages the duality among the context, response of style S1 and response of style S_0. MPDL builds mappings among the above three domains, where the context should be reconstructed by the MPDL framework, and the reconstruction error is used as the training signal. To evaluate the quality of synthetic data, we also introduce discriminators that effectively measure how a pseudo sequence matches the specific domain, and the evaluation result is used as the weight for that data. Evaluation results indicate that our method obtains significant improvement over previous baselines.

Image-to-image translation tasks have been widely investigated with Generative Adversarial Networks (GANs). However, existing approaches are mostly designed in an unsupervised manner, while little attention has been paid to domain information within unpaired data. In this article, we treat domain information as explicit supervision and design an unpaired image-to-image translation framework, Domain-supervised GAN (DosGAN), which takes the first step towards the exploration of explicit domain supervision. In contrast to representing domain characteristics using different generators or domain codes, we pre-train a classification network to explicitly classify the domain of an image. After pre-training, this network is used to extract the domain-specific features of each image. Such features, together with the domain-independent features extracted by another encoder (shared across different domains), are used to generate image in target domain. Extensive experiments on multiple facial attribute translation, multiple identity translation, multiple season translation and conditional edges-to-shoes/handbags demonstrate the effectiveness of our method. In addition, we can transfer the domain-specific feature extractor obtained on the Facescrub dataset with domain supervision information to unseen domains, such as faces in the CelebA dataset. We also succeed in achieving conditional translation with any two images in CelebA, while previous models like StarGAN cannot handle this task.

Ensemble learning, which aggregates multiple diverse models for inference, is a common practice to improve the accuracy of machine learning tasks. However, it has been observed that the conventional ensemble methods only bring marginal improvement for neural machine translation (NMT) when individual models are strong or there are a large number of individual models. In this paper, we study how to effectively aggregate multiple NMT models under the transductive setting where the source sentences of the test set are known. We propose a simple yet effective approach named transductive ensemble learning (TEL), in which we use all individual models to translate the source test set into the target language space and then finetune a strong model on the translated synthetic corpus. We conduct extensive experiments on different settings (with/without monolingual data) and different language pairs (English↔{German, Finnish}). The results show that our approach boosts strong individual models with significant improvement and benefits a lot from more individual models. Specifically, we achieve the state-of-the-art performances on the WMT2016-2018 English↔German translations.

Dual learning has been successfully applied in many machine learning applications including machine translation, image-to-image transformation, etc. The high-level idea of dual learning is very intuitive: if we map an $x$ from one domain to another and then map it back, we should recover the original $x$. Although its effectiveness has been empirically verified, theoretical understanding of dual learning is still very limited. In this paper, we aim at understanding why and when dual learning works. Based on our theoretical analysis, we further extend dual learning by introducing more related mappings and propose multi-step dual learning, in which we leverage feedback signals from additional domains to improve the qualities of the mappings. We prove that multi-step dual learning can boost the performance of standard dual learning under mild conditions. Experiments on WMT 14 English↔German and MultiUN English↔French translations verify our theoretical findings on dual learning, and the results on the translations among English, French, and Spanish of MultiUN demonstrate the effectiveness of multi-step dual learning

Tokenization is the first step of many natural language processing (NLP) tasks and plays an important role for neural NLP models. Tokenizaton method such as byte-pair encoding (BPE), which can greatly reduce the large vocabulary and deal with out-of-vocabulary words, has shown to be effective and is widely adopted for sequence generation tasks. While various tokenization methods exist, there is no common acknowledgement which is the best. In this work, we propose to leverage the mixed representations from different tokenization methods for sequence generation tasks, in order to boost the model performance with unique characteristics and advantages of individual tokenization methods. Specifically, we introduce a new model architecture to incorporate mixed representations and a co-teaching algorithm to better utilize the diversity of different tokenization methods. Our approach achieves significant improvements on neural machine translation (NMT) tasks with six language pairs (e.g., English$\leftrightarrow$German, English$\leftrightarrow$Romanian), as well as an abstractive summarization task.

Lip reading aims to recognize text from talking lip, while lip generation aims to synthesize talking lip according to text, which is a key component in talking face generation and is a dual task of lip reading. Both tasks require a large amount of paired lip video and text training data, and perform poorly in low-resource scenarios with limited paired training data. In this paper, we develop DualLip, a system that jointly improves lip reading and generation by leveraging the task duality and using unlabeled text and lip video data. The key ideas of the DualLip include: 1) Generate lip video from unlabeled text using a lip generation model, and use the pseudo data pairs to improve lip reading; 2) Generate text from unlabeled lip video using a lip reading model, and use the pseudo data pairs to improve lip generation. To leverage the benefit of DualLip on lip generation, we further extend DualLip to talking face generation with two additionally introduced components: lip to face generation and text to speech generation, which share the same duration for synchronization. Experiments on GRID and TCD-TIMIT datasets demonstrate the effectiveness of DualLip on improving lip reading, lip generation and talking face generation by utilizing unlabeled data, especially in low-resource scenarios. Specifically, on the GRID dataset, the lip generation model in our DualLip system trained with only 10% paired data and 90% unpaired data surpasses the performance of that trained with the whole paired data, and our lip reading model achieves 1.16% character error rate and 2.71% word error rate, outperforming the state-of-the-art models using the same amount of paired data.

Neural architecture search (NAS) has played important roles in the evolution of neural architectures. However, no much attention has been paid to improve neural machine translation (NMT) through NAS approaches. In this work, we propose a gradient-based NAS algorithm for NMT, which automatically discovers architectures with better performances. Compared with previous NAS work, we jointly search the network operations (e.g., LSTM, CNN, self-attention etc) as well as dropout rates to ensure better results. We show that with reasonable resources it is possible to discover novel neural network architectures for NMT, which achieve consistently better performances than Transformer [1], the state-of-the-art NMT model, across different tasks. On WMT'14 English-to-German translation, IWSLT'14 German-to-English translation and WMT'18 Finnish-to-English translation tasks, our discovered architectures could obtain 30.1, 36.1 and 26.4 BLEU scores, which are great improvement over Transformer baselines. We also empirically verify that the discovered model on one task can be transferred to other tasks.

Sharing source and target side vocabularies and word embeddings has been a popular practice in neural machine translation (briefly, NMT) for similar languages (e.g., English to French or German translation). The success of such wordlevel sharing motivates us to move one step further: we consider model-level sharing and tie the whole parts of the encoder and decoder of an NMT model. We share the encoder and decoder of Transformer (Vaswani et al. 2017), the state-of-the-art NMT model, and obtain a compact model named Tied Transformer. Experimental results demonstrate that such a simple method works well for both similar and dissimilar language pairs. We empirically verify our framework for both supervised NMT and unsupervised NMT: we achieve a 35.52 BLEU score on IWSLT 2014 German to English translation, 28.98/29.89 BLEU scores on WMT 2014 English to German translation without/with monolingual data, and a 22.05 BLEU score on WMT 2016 unsupervised German to English translation.

While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited.In this paper, we present a novel data augmentation method for neural machine translation.Different from previous augmentation methods that randomly drop, swap or replace words with other words in a sentence, we softly augment a randomly chosen word in a sentence by its contextual mixture of multiple related words.More accurately, we replace the onehot representation of a word by a distribution (provided by a language model) over the vocabulary, i.e., replacing the embedding of this word by a weighted combination of multiple semantically similar words.Since the weights of those words depend on the contextual information of the word to be replaced, the newly generated sentences capture much richer information than previous augmentation methods.Experimental results on both small scale and large scale machine translation datasets demonstrate the superiority of our method over strong baselines 1 .

While very deep neural networks have shown effectiveness for computer vision and text classification applications, how to increase the network depth of neural machine translation (NMT) models for better translation quality remains a challenging problem.Directly stacking more blocks to the NMT model results in no improvement and even reduces performance.In this work, we propose an effective two-stage approach with three specially designed components to construct deeper NMT models, which result in significant improvements over the strong Transformer baselines on WMT14 English→German and English→French translation tasks.

Xu Tan, Jiale Chen, Di He, Yingce Xia, Tao Qin, Tie-Yan Liu. 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.

Lijun Wu, Yiren Wang, Yingce Xia, Tao Qin, Jianhuang Lai, Tie-Yan Liu. 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.

Image-to-image translation, which transfers an image from a source domain to a target one, has attracted much attention in both academia and industry. The major approach is to adopt an encoder-decoder based framework, where the encoder extracts features from the input image and then the decoder decodes the features and generates an image in the target domain as the output. In this paper, we go beyond this learning framework by considering an additional polishing step on the output image. Polishing an image is very common in human's daily life, such as editing and beautifying a photo in Photoshop after taking/generating it by a digital camera. Such a deliberation process is shown to be very helpful and important in practice and thus we believe it will also be helpful for image translation. Inspired by the success of deliberation network in natural language processing, we extend deliberation process to the field of image translation. We verify our proposed method on four two-domain translation tasks and one multi-domain translation task. Both the qualitative and quantitative results demonstrate the effectiveness of our method.

Image translation across different domains has attracted much attention in both machine learning and computer vision communities. Taking the translation from a source domain to a target domain as an example, existing algorithms mainly rely on two kinds of loss for training: One is the discrimination loss, which is used to differentiate images generated by the models and natural images; the other is the reconstruction loss, which measures the difference between an original image and the reconstructed version. In this work, we introduce a new kind of loss, multi-path consistency loss, which evaluates the differences between direct translation from source domain to target domain and indirect translation from source domain to an auxiliary domain to target domain, to regularize training. For multi-domain translation (at least, three) which focuses on building translation models between any two domains, at each training iteration, we randomly select three domains, set them respectively as the source, auxiliary and target domains, build the multi-path consistency loss and optimize the network. For two-domain translation, we need to introduce an additional auxiliary domain and construct the multi-path consistency loss. We conduct various experiments to demonstrate the effectiveness of our proposed methods, including face-to-face translation, paint-to-photo translation, and de-raining/de-noising translation.

Neural machine translation models usually use the encoder-decoder framework and generate translation from left to right (or right to left) without fully utilizing the target-side global information. A few recent approaches seek to exploit the global information through two-pass decoding, yet have limitations in translation quality and model efficiency. In this work, we propose a new framework that introduces a soft prototype into the encoder-decoder architecture, which allows the decoder to have indirect access to both past and future information, such that each target word can be generated based on the better global understanding. We further provide an efficient and effective method to generate the prototype. Empirical studies on various neural machine translation tasks show that our approach brings significant improvement in generation quality over the baseline model, with little extra cost in storage and inference time, demonstrating the effectiveness of our proposed framework. Specially, we achieve state-of-the-art results on WMT2014, 2015 and 2017 English to German translation.

Neural machine translation (NMT) heavily relies on parallel bilingual corpora for training. Since large-scale, high-quality parallel corpora are usually costly to collect, it is appealing to exploit monolingual corpora to improve NMT. Inspired by the law of total probability, which connects the probability of a given target-side monolingual sentence to the conditional probability of translating from a source sentence to the target one, we propose to explicitly exploit this connection and help the training procedure of NMT models using monolingual data. The key technical challenge of this approach is that there are exponentially many source sentences for a target monolingual sentence while computing the sum of the conditional probability given each possible source sentence. We address this challenge by leveraging the reverse translation model (target-to-source translation model) to sample several mostly likely source-side sentences and avoid enumerating all possible candidate source sentences. Then we propose two different methods to leverage the law of total probability, including marginal distribution regularization and likelihood maximization of monolingual corpora. Experiment results on English-French and German-English tasks demonstrate that our methods achieve significant improvement over several strong baselines.

Neural machine translation (NMT) heavily relies on parallel bilingual data for training. Since large-scale, high-quality parallel corpora are usually costly to collect, it is appealing to exploit monolingual corpora to improve NMT. Inspired by the law of total probability, which connects the probability of a given target-side monolingual sentence to the conditional probability of translating from a source sentence to the target one, we propose to explicitly exploit this connection to learn from and regularize the training of NMT models using monolingual data. The key technical challenge of this approach is that there are exponentially many source sentences for a target monolingual sentence while computing the sum of the conditional probability given each possible source sentence. We address this challenge by leveraging the dual translation model (target-to-source translation) to sample several mostly likely source-side sentences and avoid enumerating all possible candidate source sentences. That is, we transfer the knowledge contained in the dual model to boost the training of the primal model (source-to-target translation), and we call such an approach dual transfer learning. Experiment results on English-French and German-English tasks demonstrate that dual transfer learning achieves significant improvement over several strong baselines and obtains new state-of-the-art results.

In this paper, we study a new learning paradigm for neural machine translation (NMT). Instead of maximizing the likelihood of the human translation as in previous works, we minimize the distinction between human translation and the translation given by an NMT model. To achieve this goal, inspired by the recent success of generative adversarial networks (GANs), we employ an adversarial training architecture and name it as Adversarial-NMT. In Adversarial-NMT, the training of the NMT model is assisted by an adversary, which is an elaborately designed $2D$ convolutional neural network (CNN). The goal of the adversary is to differentiate the translation result generated by the NMT model from that by human. The goal of the NMT model is to produce high quality translations so as to cheat the adversary. A policy gradient method is leveraged to co-train the NMT model and the adversary. Experimental results on English$\rightarrow$French and German$\rightarrow$English translation tasks show that Adversarial-NMT can achieve significantly better translation quality than several strong baselines.

Image-to-image translation tasks have been widely investigated with Generative Adversarial Networks (GANs) and dual learning. However, existing models lack the ability to control the translated results in the target domain and their results usually lack of diversity in the sense that a fixed image usually leads to (almost) deterministic translation result. In this paper, we study a new problem, conditional image-to-image translation, which is to translate an image from the source domain to the target domain conditioned on a given image in the target domain. It requires that the generated image should inherit some domain-specific features of the conditional image from the target domain. Therefore, changing the conditional image in the target domain will lead to diverse translation results for a fixed input image from the source domain, and therefore the conditional input image helps to control the translation results. We tackle this problem with unpaired data based on GANs and dual learning. We twist two conditional translation models (one translation from A domain to B domain, and the other one from B domain to A domain) together for inputs combination and reconstruction while preserving domain independent features. We carry out experiments on men's faces from-to women's faces translation and edges to shoes&bags translations. The results demonstrate the effectiveness of our proposed method.

Many artificial intelligence tasks appear in dual forms like English$\leftrightarrow$French translation and speech$\leftrightarrow$text transformation. Existing dual learning schemes, which are proposed to solve a pair of such dual tasks, explore how to leverage such dualities from data level. In this work, we propose a new learning framework, model-level dual learning, which takes duality of tasks into consideration while designing the architectures for the primal/dual models, and ties the model parameters that playing similar roles in the two tasks. We study both symmetric and asymmetric model-level dual learning. Our algorithms achieve significant improvements on neural machine translation and sentiment analysis.

Policy evaluation with linear function approximation is an important problem in reinforcement learning. When facing high-dimensional feature spaces, such a problem becomes extremely hard considering the computation efficiency and quality of approximations. We propose a new algorithm, LSTD(lambda)-RP, which leverages random projection techniques and takes eligibility traces into consideration to tackle the above two challenges. We carry out theoretical analysis of LSTD(lambda)-RP, and provide meaningful upper bounds of the estimation error, approximation error and total generalization error. These results demonstrate that LSTD(lambda)-RP can benefit from random projection and eligibility traces strategies, and LSTD(lambda)-RP can achieve better performances than prior LSTD-RP and LSTD(lambda) algorithms.

Neural Machine Translation (NMT) has achieved remarkable progress with the quick evolvement of model structures. In this paper, we propose the concept of layer-wise coordination for NMT, which explicitly coordinates the learning of hidden representations of the encoder and decoder together layer by layer, gradually from low level to high level. Specifically, we design a layer-wise attention and mixed attention mechanism, and further share the parameters of each layer between the encoder and decoder to regularize and coordinate the learning. Experiments show that combined with the state-of-the-art Transformer model, layer-wise coordination achieves improvements on three IWSLT and two WMT translation tasks. More specifically, our method achieves 34.43 and 29.01 BLEU score on WMT16 English-Romanian and WMT14 English-German tasks, outperforming the Transformer baseline.

Teaching is critical to human society: it is with teaching that prospective students are educated and human civilization can be inherited and advanced. A good teacher not only provides his/her students with qualified teaching materials (e.g., textbooks), but also sets up appropriate learning objectives (e.g., course projects and exams) considering different situations of a student. When it comes to artificial intelligence, treating machine learning models as students, the loss functions that are optimized act as perfect counterparts of the learning objective set by the teacher. In this work, we explore the possibility of imitating human teaching behaviors by dynamically and automatically outputting appropriate loss functions to train machine learning models. Different from typical learning settings in which the loss function of a machine learning model is predefined and fixed, in our framework, the loss function of a machine learning model (we call it student) is defined by another machine learning model (we call it teacher). The ultimate goal of teacher model is cultivating the student to have better performance measured on development dataset. Towards that end, similar to human teaching, the teacher, a parametric model, dynamically outputs different loss functions that will be used and optimized by its student model at different training stages. We develop an efficient learning method for the teacher model that makes gradient based optimization possible, exempt of the ineffective solutions such as policy optimization. We name our method as ``learning to teach with dynamic loss functions'' (L2T-DLF for short). Extensive experiments on real world tasks including image classification and neural machine translation demonstrate that our method significantly improves the quality of various student models.

We study the infinitely many-armed bandit problem with budget constraints, where the number of arms can be infinite and much larger than the number of possible experiments. The player aims at maximizing his/her total expected reward under a budget constraint B for the cost of pulling arms. We introduce a weak stochastic assumption on the ratio of expected-reward to expected-cost of a newly pulled arm which characterizes its probability of being a near-optimal arm. We propose an algorithm named RCB-I to this new problem, in which the player first randomly picks K arms, whose order is sub-linear in terms of B, and then runs the algorithm for the finite-arm setting on the selected arms. Theoretical analysis shows that this simple algorithm enjoys a sub-linear regret in term of the budget B. We also provide a lower bound of any algorithm under Bernoulli setting. The regret bound of RCB-I matches the lower bound up to a logarithmic factor. We further extend this algorithm to the any-budget setting (i.e., the budget is unknown in advance) and conduct corresponding theoretical analysis.

Many supervised learning tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. text to speech, and image classification vs. image generation. Two dual tasks have intrinsic connections with each other due to the probabilistic correlation between their models. This connection is, however, not effectively utilized today, since people usually train the models of two dual tasks separately and independently. In this work, we propose training the models of two dual tasks simultaneously, and explicitly exploiting the probabilistic correlation between them to regularize the training process. For ease of reference, we call the proposed approach dual supervised learning. We demonstrate that dual supervised learning can improve the practical performances of both tasks, for various applications including machine translation, image processing, and sentiment analysis.

Recent years have witnessed the rapid development of machine learning in solving artificial intelligence (AI) tasks in many domains, including translation, speech, image, etc. Within these domains, AI tasks are usually not independent. As a specific type of relationship, structural duality does exist between many pairs of AI tasks, such as translation from one language to another vs. its opposite direction, speech recognition vs. speech synthetization, image classification vs. image generation, etc. The importance of such duality has been magnified by some recent studies, which revealed that it can boost the learning of two tasks in the dual form. However, there has been little investigation on how to leverage this invaluable relationship into the inference stage of AI tasks. In this paper, we propose a general framework of dual inference which can take advantage of both existing models from two dual tasks, without re-training, to conduct inference for one individual task. Empirical studies on three pairs of specific dual tasks, including machine translation, sentiment analysis, and image processing have illustrated that dual inference can significantly improve the performance of each of individual tasks.

Neural Machine Translation (NMT) has become a popular technology in recent years, and beam search is its de facto decoding method due to the shrunk search space and reduced computational complexity. However, since it only searches for local optima at each time step through one-step forward looking, it usually cannot output the best target sentence. Inspired by the success and methodology of AlphaGo, in this paper we propose using a prediction network to improve beam search, which takes the source sentence $x$, the currently available decoding output $y_1,\cdots, y_{t-1}$ and a candidate word $w$ at step $t$ as inputs and predicts the long-term value (e.g., BLEU score) of the partial target sentence if it is completed by the NMT model. Following the practice in reinforcement learning, we call this prediction network \emph{value network}. Specifically, we propose a recurrent structure for the value network, and train its parameters from bilingual data. During the test time, when choosing a word $w$ for decoding, we consider both its conditional probability given by the NMT model and its long-term value predicted by the value network. Experiments show that such an approach can significantly improve the translation accuracy on several translation tasks.

The encoder-decoder framework has achieved promising progress for many sequence generation tasks, including machine translation, text summarization, dialog system, image captioning, etc. Such a framework adopts an one-pass forward process while decoding and generating a sequence, but lacks the deliberation process: A generated sequence is directly used as final output without further polishing. However, deliberation is a common behavior in human's daily life like reading news and writing papers/articles/books. In this work, we introduce the deliberation process into the encoder-decoder framework and propose deliberation networks for sequence generation. A deliberation network has two levels of decoders, where the first-pass decoder generates a raw sequence and the second-pass decoder polishes and refines the raw sentence with deliberation. Since the second-pass deliberation decoder has global information about what the sequence to be generated might be, it has the potential to generate a better sequence by looking into future words in the raw sentence. Experiments on neural machine translation and text summarization demonstrate the effectiveness of the proposed deliberation networks. On the WMT 2014 English-to-French translation task, our model establishes a new state-of-the-art BLEU score of 41.5.

While neural machine translation (NMT) is making good progress in the past two years, tens of millions of bilingual sentence pairs are needed for its training. However, human labeling is very costly. To tackle this training data bottleneck, we develop a dual-learning mechanism, which can enable an NMT system to automatically learn from unlabeled data through a dual-learning game. This mechanism is inspired by the following observation: any machine translation task has a dual task, e.g., English-to-French translation (primal) versus French-to-English translation (dual); the primal and dual tasks can form a closed loop, and generate informative feedback signals to train the translation models, even if without the involvement of a human labeler. In the dual-learning mechanism, we use one agent to represent the model for the primal task and the other agent to represent the model for the dual task, then ask them to teach each other through a reinforcement learning process. Based on the feedback signals generated during this process (e.g., the language-model likelihood of the output of a model, and the reconstruction error of the original sentence after the primal and dual translations), we can iteratively update the two models until convergence (e.g., using the policy gradient methods). We call the corresponding approach to neural machine translation \emph{dual-NMT}. Experiments show that dual-NMT works very well on English$\leftrightarrow$French translation; especially, by learning from monolingual data (with 10\% bilingual data for warm start), it achieves a comparable accuracy to NMT trained from the full bilingual data for the French-to-English translation task.

We study the existence of pure Nash equilibrium (PNE) for the mechanisms used in Internet services (e.g., online reviews and question-answering websites) to incentivize users to generate high-quality content. Most existing work assumes that users are homogeneous and have the same ability. However, real-world users are heterogeneous and their abilities can be very different from each other due to their diversity in background, culture, and profession. In this work, we consider the following setting: (1) the users are heterogeneous and each of them has a private type indicating the best quality of the content he/she can generate; (2) all the users share a fixed total reward. With this setting, we study the existence of pure Nash equilibrium of several mechanisms composed by different allocation rules, action spaces, and information availability. We prove the existence of PNE for some mechanisms and the non-existence for some other mechanisms. We also discuss how to find a PNE (if exists) through either a constructive way or a search algorithm.