Lijun Wu


pdf bib
CReSE: Benchmark Data and Automatic Evaluation Framework for Recommending Eligibility Criteria from Clinical Trial Information
Siun Kim | Jung-Hyun Won | David Lee | Renqian Luo | Lijun Wu | Tao Qin | Howard Lee
Findings of the Association for Computational Linguistics: EACL 2024

Eligibility criteria (EC) refer to a set of conditions an individual must meet to participate in a clinical trial, defining the study population and minimizing potential risks to patients. Previous research in clinical trial design has been primarily focused on searching for similar trials and generating EC within manual instructions, employing similarity-based performance metrics, which may not fully reflect human judgment. In this study, we propose a novel task of recommending EC based on clinical trial information, including trial titles, and introduce an automatic evaluation framework to assess the clinical validity of the EC recommendation model. Our new approach, known as CReSE (Contrastive learning and Rephrasing-based and Clinical Relevance-preserving Sentence Embedding), represents EC through contrastive learning and rephrasing via large language models (LLMs). The CReSE model outperforms existing language models pre-trained on the biomedical domain in EC clustering. Additionally, we have curated a benchmark dataset comprising 3.2M high-quality EC-title pairs extracted from 270K clinical trials available on The EC recommendation models achieve commendable performance metrics, with 49.0% precision@1 and 44.2% MAP@5 on our evaluation framework. We expect that our evaluation framework built on the CReSE model will contribute significantly to the development and assessment of the EC recommendation models in terms of clinical validity.


pdf bib
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations
Qizhi Pei | Wei Zhang | Jinhua Zhu | Kehan Wu | Kaiyuan Gao | Lijun Wu | Yingce Xia | Rui Yan
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

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 pre-training 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

pdf bib
Dynamic and Efficient Inference for Text Generation via BERT Family
Xiaobo Liang | Juntao Li | Lijun Wu | Ziqiang Cao | Min Zhang
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Despite the excellent performance of Pre-trained Language Models on many text generation tasks, they suffer from inefficient inference on computation and memory due to their large-scale parameters and the universal autoregressive decoding paradigm. In this work, we propose a novel fine-tuning method DEER, which can make a single pre-trained model support Dynamic and Efficient infERence and achieve an adaptive trade-off between model performance and latency. In particular, our critical insight is to jointly utilize the non-autoregressive (NAR) generation and dynamic parameter pruning techniques, which can flexibly control the decoding iteration steps and model sizes according to memory and latency limitations. Besides, we also explore the effectiveness of the pre-trained MLMs (i.e., the BERT family) for text generation tasks since their bidirectional attention nature is more suitable for the NAR training objective. Extensive experiments on both monolingual and multilingual pre-trained MLMs demonstrate the effectiveness of our proposed DEER method by consistently achieving (1) higher BLEU scores than the strong autoregressive Transformer model on three neural machine translation tasks with 3 12 times speedup, (2) competitive performance (but with much faster inference speed) compared with the BART model on four GLGE benchmark tasks. Our code will be publicly available at GitHub

pdf bib
MolXPT: Wrapping Molecules with Text for Generative Pre-training
Zequn Liu | Wei Zhang | Yingce Xia | Lijun Wu | Shufang Xie | Tao Qin | Ming Zhang | Tie-Yan Liu
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Generative pre-trained Transformer (GPT) has demonstrates its great success in natural language processing and related techniques have been adapted into molecular modeling. Considering that text is the most important record for scientific discovery, in this paper, we propose MolXPT, a unified language model of text and molecules pre-trained on SMILES (a sequence representation of molecules) wrapped by text. Briefly, we detect the molecule names in each sequence and replace them to the corresponding SMILES. In this way, the SMILES could leverage the information from surrounding text, and vice versa. The above wrapped sequences, text sequences from PubMed and SMILES sequences from PubChem are all fed into a language model for pre-training. Experimental results demonstrate that MolXPT outperforms strong baselines of molecular property prediction on MoleculeNet, performs comparably to the best model in text-molecule translation while using less than half of its parameters, and enables zero-shot molecular generation without finetuning.


pdf bib
Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Change
Zhaochen Su | Zecheng Tang | Xinyan Guan | Lijun Wu | Min Zhang | Juntao Li
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Recent research has revealed that neural language models at scale suffer from poor temporal generalization capability, i.e., language model pre-trained on static data from past years performs worse over time on emerging data. Existing methods mainly perform continual training to mitigate such a misalignment. While effective to some extent but is far from being addressed on both the language modeling and downstream tasks. In this paper, we empirically observe that temporal generalization is closely affiliated with lexical semantic change, which is one of the essential phenomena of natural languages. Based on this observation, we propose a simple yet effective lexical-level masking strategy to post-train a converged language model. Experiments on two pre-trained language models, two different classification tasks, and four benchmark datasets demonstrate the effectiveness of our proposed method over existing temporal adaptation methods, i.e., continual training with new data. Our code is available at

pdf bib
JANUS: Joint Autoregressive and Non-autoregressive Training with Auxiliary Loss for Sequence Generation
Xiaobo Liang | Lijun Wu | Juntao Li | Min Zhang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Transformer-based autoregressive and non-autoregressive models have played an essential role in sequence generation tasks. The autoregressive model can obtain excellent performance, while the non-autoregressive model brings fast decoding speed for inference. In this paper, we propose JANUS, a Joint Autoregressive and Non-autoregressive training method using aUxiliary losS to enhance the model performance in both AR and NAR manner simultaneously and effectively alleviate the problem of distribution discrepancy.Further, we pre-train BART with JANUS on a large corpus with minimal cost (16 GPU days) and make the BART-JANUS capable of non-autoregressive generation, demonstrating that our approach can transfer the AR knowledge to NAR. Empirically, we show our approach and BART-JANUS can achieve significant improvement on multiple generation tasks, including machine translation and GLGE benchmarks. Our code is available at Github.


pdf bib
UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost
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

Transformer architecture achieves great success in abundant natural language processing tasks. The over-parameterization of the Transformer model has motivated plenty of works to alleviate its overfitting for superior performances. With some explorations, we find simple techniques such as dropout, can greatly boost model performance with a careful design. Therefore, in this paper, we integrate different dropout techniques into the training of Transformer models. Specifically, we propose an approach named UniDrop to unites three different dropout techniques from fine-grain to coarse-grain, i.e., feature dropout, structure dropout, and data dropout. Theoretically, we demonstrate that these three dropouts play different roles from regularization perspectives. Empirically, we conduct experiments on both neural machine translation and text classification benchmark datasets. Extensive results indicate that Transformer with UniDrop can achieve around 1.5 BLEU improvement on IWSLT14 translation tasks, and better accuracy for the classification even using strong pre-trained RoBERTa as backbone.

pdf bib
How to leverage the multimodal EHR data for better medical prediction?
Bo Yang | Lijun Wu
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Healthcare is becoming a more and more important research topic recently. With the growing data in the healthcare domain, it offers a great opportunity for deep learning to improve the quality of service and reduce costs. However, the complexity of electronic health records (EHR) data is a challenge for the application of deep learning. Specifically, the data produced in the hospital admissions are monitored by the EHR system, which includes structured data like daily body temperature and unstructured data like free text and laboratory measurements. Although there are some preprocessing frameworks proposed for specific EHR data, the clinical notes that contain significant clinical value are beyond the realm of their consideration. Besides, whether these different data from various views are all beneficial to the medical tasks and how to best utilize these data remain unclear. Therefore, in this paper, we first extract the accompanying clinical notes from EHR and propose a method to integrate these data, we also comprehensively study the different models and the data leverage methods for better medical task prediction performance. The results on two prediction tasks show that our fused model with different data outperforms the state-of-the-art method without clinical notes, which illustrates the importance of our fusion method and the clinical note features.

pdf bib
mixSeq: A Simple Data Augmentation Methodfor Neural Machine Translation
Xueqing Wu | Yingce Xia | Jinhua Zhu | Lijun Wu | Shufang Xie | Yang Fan | Tao Qin
Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)

Data augmentation, which refers to manipulating the inputs (e.g., adding random noise,masking specific parts) to enlarge the dataset,has been widely adopted in machine learning. Most data augmentation techniques operate on a single input, which limits the diversity of the training corpus. In this paper, we propose a simple yet effective data augmentation technique for neural machine translation, mixSeq, which operates on multiple inputs and their corresponding targets. Specifically, we randomly select two input sequences,concatenate them together as a longer input aswell as their corresponding target sequencesas an enlarged target, and train models on theaugmented dataset. Experiments on nine machine translation tasks demonstrate that such asimple method boosts the baselines by a non-trivial margin. Our method can be further combined with single input based data augmentation methods to obtain further improvements.


pdf bib
Microsoft Research Asia’s Systems for WMT19
Yingce Xia | Xu Tan | Fei Tian | Fei Gao | Di He | Weicong Chen | Yang Fan | Linyuan Gong | Yichong Leng | Renqian Luo | Yiren Wang | Lijun Wu | Jinhua Zhu | Tao Qin | Tie-Yan Liu
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

We Microsoft Research Asia made submissions to 11 language directions in the WMT19 news translation tasks. We won the first place for 8 of the 11 directions and the second place for the other three. Our basic systems are built on Transformer, back translation and knowledge distillation. We integrate several of our rececent techniques to enhance the baseline systems: multi-agent dual learning (MADL), masked sequence-to-sequence pre-training (MASS), neural architecture optimization (NAO), and soft contextual data augmentation (SCA).

pdf bib
Soft Contextual Data Augmentation for Neural Machine Translation
Fei Gao | Jinhua Zhu | Lijun Wu | Yingce Xia | Tao Qin | Xueqi Cheng | Wengang Zhou | Tie-Yan Liu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

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 one-hot 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 data sets demonstrate the superiority of our method over strong baselines.

pdf bib
Depth Growing for Neural Machine Translation
Lijun Wu | Yiren Wang | Yingce Xia | Fei Tian | Fei Gao | Tao Qin | Jianhuang Lai | Tie-Yan Liu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

While very deep neural networks have shown effectiveness for computer vision and text classification applications, how to increase the network depth of the 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 drop in 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 EnglishGerman and EnglishFrench translation tasks.

pdf bib
Exploiting Monolingual Data at Scale for Neural Machine Translation
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)

While target-side monolingual data has been proven to be very useful to improve neural machine translation (briefly, NMT) through back translation, source-side monolingual data is not well investigated. In this work, we study how to use both the source-side and target-side monolingual data for NMT, and propose an effective strategy leveraging both of them. First, we generate synthetic bitext by translating monolingual data from the two domains into the other domain using the models pretrained on genuine bitext. Next, a model is trained on a noised version of the concatenated synthetic bitext where each source sequence is randomly corrupted. Finally, the model is fine-tuned on the genuine bitext and a clean version of a subset of the synthetic bitext without adding any noise. Our approach achieves state-of-the-art results on WMT16, WMT17, WMT18 EnglishGerman translations and WMT19 GermanFrench translations, which demonstrate the effectiveness of our method. We also conduct a comprehensive study on how each part in the pipeline works.

pdf bib
Machine Translation With Weakly Paired Documents
Lijun Wu | Jinhua Zhu | Di He | Fei Gao | 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)

Neural machine translation, which achieves near human-level performance in some languages, strongly relies on the large amounts of parallel sentences, which hinders its applicability to low-resource language pairs. Recent works explore the possibility of unsupervised machine translation with monolingual data only, leading to much lower accuracy compared with the supervised one. Observing that weakly paired bilingual documents are much easier to collect than bilingual sentences, e.g., from Wikipedia, news websites or books, in this paper, we investigate training translation models with weakly paired bilingual documents. Our approach contains two components. 1) We provide a simple approach to mine implicitly bilingual sentence pairs from document pairs which can then be used as supervised training signals. 2) We leverage the topic consistency of two weakly paired documents and learn the sentence translation model by constraining the word distribution-level alignments. We evaluate our method on weakly paired documents from Wikipedia on six tasks, the widely used WMT16 GermanEnglish, WMT13 SpanishEnglish and WMT16 RomanianEnglish translation tasks. We obtain 24.1/30.3, 28.1/27.6 and 30.1/27.6 BLEU points separately, outperforming previous results by more than 5 BLEU points in each direction and reducing the gap between unsupervised translation and supervised translation up to 50%.


pdf bib
Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter
Lijun Wu | Xu Tan | Di He | Fei Tian | Tao Qin | Jianhuang Lai | Tie-Yan Liu
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Neural machine translation usually adopts autoregressive models and suffers from exposure bias as well as the consequent error propagation problem. Many previous works have discussed the relationship between error propagation and the accuracy drop (i.e., the left part of the translated sentence is often better than its right part in left-to-right decoding models) problem. In this paper, we conduct a series of analyses to deeply understand this problem and get several interesting findings. (1) The role of error propagation on accuracy drop is overstated in the literature, although it indeed contributes to the accuracy drop problem. (2) Characteristics of a language play a more important role in causing the accuracy drop: the left part of the translation result in a right-branching language (e.g., English) is more likely to be more accurate than its right part, while the right part is more accurate for a left-branching language (e.g., Japanese). Our discoveries are confirmed on different model structures including Transformer and RNN, and in other sequence generation tasks such as text summarization.

pdf bib
A Study of Reinforcement Learning for Neural Machine Translation
Lijun Wu | Fei Tian | Tao Qin | Jianhuang Lai | Tie-Yan Liu
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging, especially in real-world systems where deep models and large datasets are leveraged. In this paper, taking several large-scale translation tasks as testbeds, we conduct a systematic study on how to train better NMT models using reinforcement learning. We provide a comprehensive comparison of several important factors (e.g., baseline reward, reward shaping) in RL training. Furthermore, to fill in the gap that it remains unclear whether RL is still beneficial when monolingual data is used, we propose a new method to leverage RL to further boost the performance of NMT systems trained with source/target monolingual data. By integrating all our findings, we obtain competitive results on WMT14 English-German, WMT17 English-Chinese, and WMT17 Chinese-English translation tasks, especially setting a state-of-the-art performance on WMT17 Chinese-English translation task.

pdf bib
Efficient Sequence Learning with Group Recurrent Networks
Fei Gao | Lijun Wu | Li Zhao | Tao Qin | Xueqi Cheng | Tie-Yan Liu
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

Recurrent neural networks have achieved state-of-the-art results in many artificial intelligence tasks, such as language modeling, neural machine translation, speech recognition and so on. One of the key factors to these successes is big models. However, training such big models usually takes days or even weeks of time even if using tens of GPU cards. In this paper, we propose an efficient architecture to improve the efficiency of such RNN model training, which adopts the group strategy for recurrent layers, while exploiting the representation rearrangement strategy between layers as well as time steps. To demonstrate the advantages of our models, we conduct experiments on several datasets and tasks. The results show that our architecture achieves comparable or better accuracy comparing with baselines, with a much smaller number of parameters and at a much lower computational cost.