{"type":"ScholarlyArticle","title":"Extracting Entities and Events as a Single Task Using a Transition-Based Neural Model","authors":[{"name":"Junchi Zhang","slug":"junchi-zhang","given":"Junchi","family":"Zhang","affiliation":"School of Computer , Wuhan University , China"},{"name":"Yanxia Qin","slug":"yanxia-qin","given":"Yanxia","family":"Qin","affiliation":"School of Computer Science and Technology , Donghua University , China"},{"name":"Yue Zhang","slug":"yue-zhang","given":"Yue","family":"Zhang","affiliation":"School of Engineering , Westlake University , China; Institute of Advanced Technology , Westlake Institute for Advanced Study , China"},{"name":"Mengchi Liu","slug":"mengchi-liu","given":"Mengchi","family":"Liu","affiliation":"School of Computer , Wuhan University , China"},{"name":"Donghong Ji","slug":"donghong-ji","given":"Donghong","family":"Ji","affiliation":"School of Cyber Science and Engineering , Wuhan University , China"}],"abstract":"The task of event extraction contains subtasks including detections for entity mentions, event triggers and argument roles. Traditional methods solve them as a pipeline, which does not make use of task correlation for their mutual benefits. There have been recent efforts towards building a joint model for all tasks. However, due to technical challenges, there has not been work predicting the joint output structure as a single task. We build a first model to this end using a neural transition-based framework, incrementally predicting complex joint structures in a state-transition process. Results on standard benchmarks show the benefits of the joint model, which gives the best result in the literature.","doi":"10.24963/ijcai.2019/753","url":"https://ijcai.org/proceedings/2019/753","pdf":"https://ijcai.org/proceedings/2019/0753.pdf","markdown":"https://ijcai.org/proceedings/2019/753.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/753","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":753,"pages":{"first":5422,"last":5428},"keywords":["Natural Language Processing: Information Extraction","Natural Language Processing: Natural Language Processing"],"videos":[],"references":[{"position":1,"raw":"[Chen et al., 2015] Yubo Chen, Liheng Xu, Kang Liu, Dao- jian Zeng, and Jun Zhao. Event extraction via dynamic multi-pooling convolutional neural networks. In ACL, 2015.","title":"Event extraction via dynamic multi-pooling convolutional neural networks","authors":"Yubo Chen, Liheng Xu, Kang Liu, Daojian Zeng, Jun Zhao","year":"2015","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2018] Yubo Chen, Hang Yang, Kang Liu, Jun Zhao, and Yantao Jia. Collective event detection via a hier- archical and bias tagging networks with gated multi-level attention mechanisms. In EMNLP, 2018.","title":"Collective event detection via a hierarchical and bias tagging networks with gated multi-level attention mechanisms","authors":"Yubo Chen, Hang Yang, Kang Liu, Jun Zhao, Yantao Jia","year":"2018","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Choi and McCallum, 2013] Jinho D Choi and Andrew Mc- Callum. Transition-based dependency parsing with selec- tional branching. In ACL, 2013.","title":"Transition-based dependency parsing with selectional branching","authors":"D Jinho, Andrew Choi, Mc-Callum","year":"2013","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Devlin et al., 2018] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understand- ing. arXiv preprint arXiv:1810.04805, 2018.","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ding et al., 2014] Xiao Ding, Yue Zhang, Ting Liu, and Junwen Duan. Using structured events to predict stock price movement: An empirical investigation. In EMNLP, 2014.","title":"Using structured events to predict stock price movement: An empirical investigation","authors":"Xiao Ding, Yue Zhang, Ting Liu, Junwen Duan","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dyer et al., 2015] Chris Dyer, Miguel Ballesteros, Wang Ling, Austin Matthews, and Noah A Smith. Transition- based dependency parsing with stack long short-term memory. In ACL, 2015.","title":"Transitionbased dependency parsing with stack long short-term memory","authors":"Chris Dyer, Miguel Ballesteros, Wang Ling, Austin Matthews, Noah A Smith","year":"2015","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Grishman et al., 2005] Ralph Grishman, David Westbrook, and Adam Meyers. Nyu's english ace 2005 system de- scription. ACE, 2005.","title":"Nyu's english ace 2005 system description","authors":"Ralph Grishman, David Westbrook, Adam Meyers","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hong et al., 2011] Yu Hong, Jianfeng Zhang, Bin Ma, Jian- min Yao, Guodong Zhou, and Qiaoming Zhu. Using cross- entity inference to improve event extraction. In ACL, 2011.","title":"Using crossentity inference to improve event extraction","authors":"Yu Hong, Jianfeng Zhang, Bin Ma, Jianmin Yao, Guodong Zhou, Qiaoming Zhu","year":"2011","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Ji and Grishman, 2008] Heng Ji and Ralph Grishman. Re- fining event extraction through cross-document inference. ACL-08, 2008.","title":"Refining event extraction through cross-document inference","authors":"Ji, Grishman ; Heng, Ji, Ralph Grishman","year":"2008","venue":"ACL-08","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Judea and Strube, 2016] Alex Judea and Michael Strube. Incremental global event extraction. In COLING, 2016.","title":"Incremental global event extraction","authors":"Alex Judea, Michael Strube","year":"2016","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lample et al., 2016] Guillaume Lample, Miguel Balles- teros, Sandeep Subramanian, Kazuya Kawakami, and Chris Dyer. Neural architectures for named entity recog- nition. In NAACL-HLT, 2016.","title":"Neural architectures for named entity recognition","authors":"Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, Chris Dyer","year":"2016","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2013] Qi Li, Heng Ji, and Liang Huang. Joint event extraction via structured prediction with global features. In ACL, 2013.","title":"Joint event extraction via structured prediction with global features","authors":"Qi Li, Ji Heng, Liang Huang","year":"2013","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2014] Qi Li, Heng Ji, HONG Yu, and Sujian Li. Constructing information networks using one single model. In EMNLP, 2014.","title":"Constructing information networks using one single model","authors":"Qi Li, Heng Ji, Hong Yu, Sujian Li","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liao and Grishman, 2010] Shasha Liao and Ralph Grish- man. Using document level cross-event inference to im- prove event extraction. In ACL, 2010.","title":"Using document level cross-event inference to improve event extraction","authors":"Grishman Liao, Shasha Liao, Ralph Grishman","year":"2010","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liu et al., 2018a] Jian Liu, Yubo Chen, Kang Liu, and Jun Zhao. Event detection via gated multilingual attention mechanism. In AAAI, 2018.","title":"Event detection via gated multilingual attention mechanism","authors":"Liu","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2018b] Xiao Liu, Zhunchen Luo, and Heyan Huang. Jointly multiple events extraction via attention- based graph information aggregation. In EMNLP, 2018.","title":"Jointly multiple events extraction via attentionbased graph information aggregation","authors":"Liu","year":"2018","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Loshchilov and Hutter, 2016] Ilya Loshchilov and Frank Hutter. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983, 2016.","title":"Ilya Loshchilov and Frank Hutter. Sgdr: Stochastic gradient descent with warm restarts","authors":"Hutter Loshchilov","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Lyu et al., 2016] Chen Lyu, Yue Zhang, and Donghong Ji. Joint word segmentation, pos-tagging and syntactic chunk- ing. In AAAI, 2016.","title":"Joint word segmentation, pos-tagging and syntactic chunking","authors":"Chen Lyu, Yue Zhang, Donghong Ji","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[McClosky et al., 2011] David McClosky, Mihai Surdeanu, and Christopher D Manning. Event extraction as depen- dency parsing. In ACL, 2011.","title":"Event extraction as dependency parsing","authors":"David Mcclosky, Mihai Surdeanu, Christopher D Manning","year":"2011","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Nguyen and Grishman, 2018] Thien Huu Nguyen and Ralph Grishman. Graph convolutional networks with argument-aware pooling for event detection. In AAAI, 2018.","title":"Graph convolutional networks with argument-aware pooling for event detection","authors":"Grishman ; Nguyen, Huu Thien, Ralph Nguyen, Grishman","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Nguyen and Nguyen, 2019] Trung Minh Nguyen and Thien Huu Nguyen. One for all: Neural joint modeling of entities and events. In AAAI, 2019.","title":"One for all: Neural joint modeling of entities and events","authors":"Nguyen ; Nguyen, Minh Trung, Thien Nguyen, Huu Nguyen","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Nguyen et al., 2016] Thien Huu Nguyen, Kyunghyun Cho, and Ralph Grishman. Joint event extraction via recurrent neural networks. In NAACL, 2016.","title":"Joint event extraction via recurrent neural networks","authors":"Thien Huu Nguyen, Kyunghyun Cho, Ralph Grishman","year":"2016","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Nivre, 2008] Joakim Nivre. Algorithms for deterministic in- cremental dependency parsing. Computational Linguis- tics, 2008.","title":"Algorithms for deterministic incremental dependency parsing","authors":"Joakim Nivre, Nivre","year":"2008","venue":"Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Qian et al., 2015] Tao Qian, Yue Zhang, Meishan Zhang, Yafeng Ren, and Donghong Ji. A transition-based model for joint segmentation, pos-tagging and normalization. In EMNLP, 2015.","title":"A transition-based model for joint segmentation, pos-tagging and normalization","authors":"Tao Qian, Yue Zhang, Meishan Zhang, Yafeng Ren, Donghong Ji","year":"2015","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sha et al., 2018] Lei Sha, Feng Qian, Baobao Chang, and Zhifang Sui. Jointly extracting event triggers and argu- ments by dependency-bridge rnn and tensor-based argu- ment interaction. In AAAI, 2018.","title":"Jointly extracting event triggers and arguments by dependency-bridge rnn and tensor-based argument interaction","authors":"Lei Sha, Feng Qian, Baobao Chang, Zhifang Sui","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Srihari and Li, 2000] Rohini Srihari and Wei Li. A question answering system supported by information extraction. In ANLP, 2000.","title":"A question answering system supported by information extraction","authors":"Rohini Srihari, Wei Li","year":"2000","venue":"ANLP","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang et al., 2018a] Shaolei Wang, Yue Zhang, Wanxiang Che, and Ting Liu. Joint extraction of entities and rela- tions based on a novel graph scheme. In IJCAI, 2018.","title":"Joint extraction of entities and relations based on a novel graph scheme","authors":"Wang","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/620"},{"position":28,"raw":"[Wang et al., 2018b] Yuxuan Wang, Wanxiang Che, Jiang Guo, and Ting Liu. A neural transition-based approach for semantic dependency graph parsing. In AAAI, 2018.","title":"A neural transition-based approach for semantic dependency graph parsing","authors":"Wang","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yang and Mitchell, 2016] Bishan Yang and Tom Mitchell. Joint extraction of events and entities within a document context. In NAACL-HLT, 2016.","title":"Joint extraction of events and entities within a document context","authors":"Yang, Mitchell ;, Bishan Yang, Tom Mitchell","year":"2016","venue":"NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhang and Clark, 2011] Yue Zhang and Stephen Clark. Syntactic processing using the generalized perceptron and beam search. Computational linguistics, 2011.","title":"Syntactic processing using the generalized perceptron and beam search","authors":"Yue Zhang, Stephen Clark","year":"2011","venue":"Computational linguistics","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}