Bo Wang


pdf bib
Dynamic Prefix-Tuning for Generative Template-based Event Extraction
Xiao Liu | Heyan Huang | Ge Shi | Bo Wang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We consider event extraction in a generative manner with template-based conditional generation.Although there is a rising trend of casting the task of event extraction as a sequence generation problem with prompts, these generation-based methods have two significant challenges, including using suboptimal prompts and static event type information.In this paper, we propose a generative template-based event extraction method with dynamic prefix (GTEE-DynPref) by integrating context information with type-specific prefixes to learn a context-specific prefix for each context.Experimental results show that our model achieves competitive results with the state-of-the-art classification-based model OneIE on ACE 2005 and achieves the best performances on ERE.Additionally, our model is proven to be portable to new types of events effectively.

pdf bib
A sequence-to-sequence approach for document-level relation extraction
John Giorgi | Gary Bader | Bo Wang
Proceedings of the 21st Workshop on Biomedical Language Processing

Motivated by the fact that many relations cross the sentence boundary, there has been increasing interest in document-level relation extraction (DocRE). DocRE requires integrating information within and across sentences, capturing complex interactions between mentions of entities. Most existing methods are pipeline-based, requiring entities as input. However, jointly learning to extract entities and relations can improve performance and be more efficient due to shared parameters and training steps. In this paper, we develop a sequence-to-sequence approach, seq2rel, that can learn the subtasks of DocRE (entity extraction, coreference resolution and relation extraction) end-to-end, replacing a pipeline of task-specific components. Using a simple strategy we call entity hinting, we compare our approach to existing pipeline-based methods on several popular biomedical datasets, in some cases exceeding their performance. We also report the first end-to-end results on these datasets for future comparison. Finally, we demonstrate that, under our model, an end-to-end approach outperforms a pipeline-based approach. Our code, data and trained models are available at An online demo is available at

pdf bib
Dataset Debt in Biomedical Language Modeling
Jason Fries | Natasha Seelam | Gabriel Altay | Leon Weber | Myungsun Kang | Debajyoti Datta | Ruisi Su | Samuele Garda | Bo Wang | Simon Ott | Matthias Samwald | Wojciech Kusa
Proceedings of BigScience Episode #5 -- Workshop on Challenges & Perspectives in Creating Large Language Models

Large-scale language modeling and natural language prompting have demonstrated exciting capabilities for few and zero shot learning in NLP. However, translating these successes to specialized domains such as biomedicine remains challenging, due in part to biomedical NLP’s significant dataset debt – the technical costs associated with data that are not consistently documented or easily incorporated into popular machine learning frameworks at scale. To assess this debt, we crowdsourced curation of datasheets for 167 biomedical datasets. We find that only 13% of datasets are available via programmatic access and 30% lack any documentation on licensing and permitted reuse. Our dataset catalog is available at:


pdf bib
CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge Graphs
Jinfeng Zhou | Bo Wang | Ruifang He | Yuexian Hou
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Although paths of user interests shift in knowledge graphs (KGs) can benefit conversational recommender systems (CRS), explicit reasoning on KGs has not been well considered in CRS, due to the complex of high-order and incomplete paths. We propose CRFR, which effectively does explicit multi-hop reasoning on KGs with a conversational context-based reinforcement learning model. Considering the incompleteness of KGs, instead of learning single complete reasoning path, CRFR flexibly learns multiple reasoning fragments which are likely contained in the complete paths of interests shift. A fragments-aware unified model is then designed to fuse the fragments information from item-oriented and concept-oriented KGs to enhance the CRS response with entities and words from the fragments. Extensive experiments demonstrate CRFR’s SOTA performance on recommendation, conversation and conversation interpretability.

pdf bib
Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction
Bo Wang | Tao Shen | Guodong Long | Tianyi Zhou | Yi Chang
Findings of the Association for Computational Linguistics: EMNLP 2021

Aspect-level sentiment classification (ALSC) aims at identifying the sentiment polarity of a specified aspect in a sentence. ALSC is a practical setting in aspect-based sentiment analysis due to no opinion term labeling needed, but it fails to interpret why a sentiment polarity is derived for the aspect. To address this problem, recent works fine-tune pre-trained Transformer encoders for ALSC to extract an aspect-centric dependency tree that can locate the opinion words. However, the induced opinion words only provide an intuitive cue far below human-level interpretability. Besides, the pre-trained encoder tends to internalize an aspect’s intrinsic sentiment, causing sentiment bias and thus affecting model performance. In this paper, we propose a span-based anti-bias aspect representation learning framework. It first eliminates the sentiment bias in the aspect embedding by adversarial learning against aspects’ prior sentiment. Then, it aligns the distilled opinion candidates with the aspect by span-based dependency modeling to highlight the interpretable opinion terms. Our method achieves new state-of-the-art performance on five benchmarks, with the capability of unsupervised opinion extraction.

pdf bib
DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
John Giorgi | Osvald Nitski | Bo Wang | Gary Bader
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such as clustering and retrieval. Unlike word embeddings, the highest performing solutions for learning sentence embeddings require labelled data, limiting their usefulness to languages and domains where labelled data is abundant. In this paper, we present DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations. Inspired by recent advances in deep metric learning (DML), we carefully design a self-supervised objective for learning universal sentence embeddings that does not require labelled training data. When used to extend the pretraining of transformer-based language models, our approach closes the performance gap between unsupervised and supervised pretraining for universal sentence encoders. Importantly, our experiments suggest that the quality of the learned embeddings scale with both the number of trainable parameters and the amount of unlabelled training data. Our code and pretrained models are publicly available and can be easily adapted to new domains or used to embed unseen text.

pdf bib
Evaluation of Thematic Coherence in Microblogs
Iman Munire Bilal | Bo Wang | Maria Liakata | Rob Procter | Adam Tsakalidis
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Collecting together microblogs representing opinions about the same topics within the same timeframe is useful to a number of different tasks and practitioners. A major question is how to evaluate the quality of such thematic clusters. Here we create a corpus of microblog clusters from three different domains and time windows and define the task of evaluating thematic coherence. We provide annotation guidelines and human annotations of thematic coherence by journalist experts. We subsequently investigate the efficacy of different automated evaluation metrics for the task. We consider a range of metrics including surface level metrics, ones for topic model coherence and text generation metrics (TGMs). While surface level metrics perform well, outperforming topic coherence metrics, they are not as consistent as TGMs. TGMs are more reliable than all other metrics considered for capturing thematic coherence in microblog clusters due to being less sensitive to the effect of time windows.


pdf bib
Information Extraction from Swedish Medical Prescriptions with Sig-Transformer Encoder
John Pougué Biyong | Bo Wang | Terry Lyons | Alejo Nevado-Holgado
Proceedings of the 3rd Clinical Natural Language Processing Workshop

Relying on large pretrained language models such as Bidirectional Encoder Representations from Transformers (BERT) for encoding and adding a simple prediction layer has led to impressive performance in many clinical natural language processing (NLP) tasks. In this work, we present a novel extension to the Transformer architecture, by incorporating signature transform with the self-attention model. This architecture is added between embedding and prediction layers. Experiments on a new Swedish prescription data show the proposed architecture to be superior in two of the three information extraction tasks, comparing to baseline models. Finally, we evaluate two different embedding approaches between applying Multilingual BERT and translating the Swedish text to English then encode with a BERT model pretrained on clinical notes.


pdf bib
DeepGeneMD: A Joint Deep Learning Model for Extracting Gene Mutation-Disease Knowledge from PubMed Literature
Feifan Liu | Xiaoyu Zheng | Bo Wang | Catarina Kiefe
Proceedings of The 5th Workshop on BioNLP Open Shared Tasks

Understanding the pathogenesis of genetic diseases through different gene activities and their relations to relevant diseases is important for new drug discovery and drug repositioning. In this paper, we present a joint deep learning model in a multi-task learning paradigm for gene mutation-disease knowledge extraction, DeepGeneMD, which adapts the state-of-the-art hierarchical multi-task learning framework for joint inference on named entity recognition (NER) and relation extraction (RE) in the context of the AGAC (Active Gene Annotation Corpus) track at 2019 BioNLP Open Shared Tasks (BioNLP-OST). It simultaneously extracts gene mutation related activities, diseases, and their relations from the published scientific literature. In DeepGeneMD, we explore the task decomposition to create auxiliary subtasks so that more interactions between different learning subtasks can be leveraged in model training. Our model achieves the average F1 score of 0.45 on recognizing gene activities and disease entities, ranking 2nd in the AGAC NER task; and the average F1 score of 0.35 on extracting relations, ranking 1st in the AGAC RE task.


pdf bib
OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU
Jean Senellart | Dakun Zhang | Bo Wang | Guillaume Klein | Jean-Pierre Ramatchandirin | Josep Crego | Alexander Rush
Proceedings of the 2nd Workshop on Neural Machine Translation and Generation

We present a system description of the OpenNMT Neural Machine Translation entry for the WNMT 2018 evaluation. In this work, we developed a heavily optimized NMT inference model targeting a high-performance CPU system. The final system uses a combination of four techniques, all of them lead to significant speed-ups in combination: (a) sequence distillation, (b) architecture modifications, (c) precomputation, particularly of vocabulary, and (d) CPU targeted quantization. This work achieves the fastest performance of the shared task, and led to the development of new features that have been integrated to OpenNMT and available to the community.


pdf bib
TOTEMSS: Topic-based, Temporal Sentiment Summarisation for Twitter
Bo Wang | Maria Liakata | Adam Tsakalidis | Spiros Georgakopoulos Kolaitis | Symeon Papadopoulos | Lazaros Apostolidis | Arkaitz Zubiaga | Rob Procter | Yiannis Kompatsiaris
Proceedings of the IJCNLP 2017, System Demonstrations

We present a system for time sensitive, topic based summarisation of the sentiment around target entities and topics in collections of tweets. We describe the main elements of the system and illustrate its functionality with two examples of sentiment analysis of topics related to the 2017 UK general election.

pdf bib
TDParse: Multi-target-specific sentiment recognition on Twitter
Bo Wang | Maria Liakata | Arkaitz Zubiaga | Rob Procter
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers

Existing target-specific sentiment recognition methods consider only a single target per tweet, and have been shown to miss nearly half of the actual targets mentioned. We present a corpus of UK election tweets, with an average of 3.09 entities per tweet and more than one type of sentiment in half of the tweets. This requires a method for multi-target specific sentiment recognition, which we develop by using the context around a target as well as syntactic dependencies involving the target. We present results of our method on both a benchmark corpus of single targets and the multi-target election corpus, showing state-of-the art performance in both corpora and outperforming previous approaches to multi-target sentiment task as well as deep learning models for single-target sentiment.

pdf bib
SYSTRAN Purely Neural MT Engines for WMT2017
Yongchao Deng | Jungi Kim | Guillaume Klein | Catherine Kobus | Natalia Segal | Christophe Servan | Bo Wang | Dakun Zhang | Josep Crego | Jean Senellart
Proceedings of the Second Conference on Machine Translation


pdf bib
WarwickDCS: From Phrase-Based to Target-Specific Sentiment Recognition
Richard Townsend | Adam Tsakalidis | Yiwei Zhou | Bo Wang | Maria Liakata | Arkaitz Zubiaga | Alexandra Cristea | Rob Procter
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)


pdf bib
All in Strings: a Powerful String-based Automatic MT Evaluation Metric with Multiple Granularities
Junguo Zhu | Muyun Yang | Bo Wang | Sheng Li | Tiejun Zhao
Coling 2010: Posters


pdf bib
References Extension for the Automatic Evaluation of MT by Syntactic Hybridization
Bo Wang | Tiejun Zhao | Muyun Yang | Sheng Li
Proceedings of the Third Workshop on Syntax and Structure in Statistical Translation (SSST-3) at NAACL HLT 2009

pdf bib
A Statistical Machine Translation Model Based on a Synthetic Synchronous Grammar
Hongfei Jiang | Muyun Yang | Tiejun Zhao | Sheng Li | Bo Wang
Proceedings of the ACL-IJCNLP 2009 Conference Short Papers


pdf bib
Diagnostic Evaluation of Machine Translation Systems Using Automatically Constructed Linguistic Check-Points
Ming Zhou | Bo Wang | Shujie Liu | Mu Li | Dongdong Zhang | Tiejun Zhao
Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)

pdf bib
Bootstrapping Both Product Features and Opinion Words from Chinese Customer Reviews with Cross-Inducing
Bo Wang | Houfeng Wang
Proceedings of the Third International Joint Conference on Natural Language Processing: Volume-I