{"type":"ScholarlyArticle","title":"Efficient Document-level Event Extraction via Pseudo-Trigger-aware Pruned Complete Graph","authors":[{"name":"Tong Zhu","slug":"tong-zhu","given":"Tong","family":"Zhu","affiliation":"Institute of Artificial Intelligence , School of Computer Science and Technology , Soochow University , China"},{"name":"Xiaoye Qu","slug":"xiaoye-qu","given":"Xiaoye","family":"Qu","affiliation":"Huawei Cloud , China"},{"name":"Wenliang Chen","slug":"wenliang-chen","given":"Wenliang","family":"Chen","affiliation":"Institute of Artificial Intelligence , School of Computer Science and Technology , Soochow University , China"},{"name":"Zhefeng Wang","slug":"zhefeng-wang","given":"Zhefeng","family":"Wang","affiliation":"Huawei Cloud , China"},{"name":"Baoxing Huai","slug":"baoxing-huai","given":"Baoxing","family":"Huai","affiliation":"Huawei Cloud , China"},{"name":"Nicholas Yuan","slug":"nicholas-yuan","given":"Nicholas","family":"Yuan","affiliation":"Huawei Cloud , China"},{"name":"Min Zhang","slug":"min-zhang","given":"Min","family":"Zhang","affiliation":"Institute of Artificial Intelligence , School of Computer Science and Technology , Soochow University , China"}],"abstract":"Most previous studies of document-level event extraction mainly focus on building argument chains in an autoregressive way, which achieves a certain success but is inefficient in both training and inference.\r\nIn contrast to the previous studies, we propose a fast and lightweight model named as PTPCG.\r\nIn our model, we design a novel strategy for event argument combination together with a non-autoregressive decoding algorithm via pruned complete graphs, which are constructed under the guidance of the automatically selected pseudo triggers.\r\nCompared to the previous systems, our system achieves competitive results with 19.8% of parameters and much lower resource consumption, taking only 3.8% GPU hours for training and up to 8.5 times faster for inference.\r\nBesides, our model shows superior compatibility for the datasets with (or without) triggers and the pseudo triggers can be the supplements for annotated triggers to make further improvements.\r\nCodes are available at https://github.com/Spico197/DocEE .","doi":"10.24963/ijcai.2022/632","url":"https://ijcai.org/proceedings/2022/632","pdf":"https://ijcai.org/proceedings/2022/0632.pdf","markdown":"https://ijcai.org/proceedings/2022/632.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/632","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Natural Language Processing","track":"Main Track","number":632,"pages":{"first":4552,"last":4558},"keywords":["Natural Language Processing: Information Extraction","Natural Language Processing: Knowledge Extraction"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986703","length_sec":89,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984846","length_sec":341,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Bengio et al., 2015] Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer. Scheduled sampling for se- quence prediction with recurrent neural networks. In Proc. of NeurIPS, pages 1171-1179, 2015.","title":"Scheduled sampling for sequence prediction with recurrent neural networks","authors":"Samy Bengio, Oriol Vinyals, Navdeep Jaitly, Noam Shazeer","year":"2015","venue":"Proc. of NeurIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bron and Kerbosch, 1973] Coen Bron and Joep Kerbosch. Algorithm 457: Finding all cliques of an undirected graph. Commun. ACM, 16(9):575-577, September 1973.","title":"Algorithm 457: Finding all cliques of an undirected graph","authors":"Kerbosch Bron, Coen Bron, Joep Kerbosch","year":"1973","venue":"Commun. ACM","doi":null,"url":null,"internal_url":null},{"position":3,"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 Proc. of ACL-IJCNLP, pages 167-176, Beijing, China, July 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":"Proc. of ACL-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2017] Yubo Chen, Shulin Liu, Xiang Zhang, Kang Liu, and Jun Zhao. Automatically labeled data gen- eration for large scale event extraction. In Proc. of ACL, pages 409-419, Vancouver, Canada, July 2017.","title":"Automatically labeled data generation for large scale event extraction","authors":"Yubo Chen, Shulin Liu, Xiang Zhang, Kang Liu, Jun Zhao","year":"2017","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Devlin et al., 2019] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understand- ing. In Proc. of NAACL-HLT, 2019.","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2019","venue":"Proc. of NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Du and Cardie, 2020] Xinya Du and Claire Cardie. Event extraction by answering (almost) natural questions. In Proc. of EMNLP, pages 671-683, Online, November 2020. Association for Computational Linguistics.","title":"Xinya Du and Claire Cardie. Event extraction by answering (almost) natural questions","authors":"Cardie Du","year":"2020","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ebner et al., 2020] Seth Ebner, Patrick Xia, Ryan Culkin, Kyle Rawlins, and Benjamin Van Durme. Multi-sentence argument linking. In Proc. of ACL, pages 8057-8077, 2020.","title":"Multi-sentence argument linking","authors":"Seth Ebner, Patrick Xia, Ryan Culkin, Kyle Rawlins, Benjamin Van Durme","year":"2020","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Huang and Jia, 2021] Yusheng Huang and Weijia Jia. Ex- ploring sentence community for document-level event ex- traction. In Findings of EMNLP, pages 340-351, Punta Cana, Dominican Republic, November 2021.","title":"Exploring sentence community for document-level event extraction","authors":"Jia ; ] Yusheng Huang, Weijia Huang, Jia","year":"2021","venue":"Findings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kingma and Ba, 2015] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In Proc. of ICLR, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"Proc. of ICLR","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 Proc. of NAACL, pages 260-270, San Diego, California, June 2016.","title":"Neural architectures for named entity recognition","authors":"Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, Chris Dyer","year":"2016","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2021] Sha Li, Heng Ji, and Jiawei Han. Document- level event argument extraction by conditional generation. In Proc. of NAACL, pages 894-908, Online, June 2021.","title":"Documentlevel event argument extraction by conditional generation","authors":"Sha Li, Ji Heng, Jiawei Han","year":"2021","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li, 2021] X. et al Li. Duee-fin: A document-level event ex- traction dataset in the financial domain released by baidu. https://aistudio.baidu.com/aistudio/competition/detail/46, 2021.","title":"Duee-fin: A document-level event extraction dataset in the financial domain released by baidu","authors":"X","year":null,"venue":null,"doi":null,"url":"https://aistudio.baidu.com/aistudio/competition/detail/46,2021","internal_url":null},{"position":14,"raw":"[Lin et al., 2020] Ying Lin, Heng Ji, Fei Huang, and Lingfei Wu. A joint neural model for information extraction with global features. In Proc. of ACL, pages 7999-8009, On- line, July 2020.","title":"A joint neural model for information extraction with global features","authors":"Ying Lin, Heng Ji, Fei Huang, Lingfei Wu","year":"2020","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liu et al., 2018] Xiao Liu, Zhunchen Luo, and Heyan Huang. Jointly multiple events extraction via attention- based graph information aggregation. In Proc. of EMNLP, pages 1247-1256, Brussels, Belgium, October-November 2018.","title":"Jointly multiple events extraction via attentionbased graph information aggregation","authors":"Xiao Liu, Zhunchen Luo, Heyan Huang","year":"2018","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2019] Shulin Liu, Yang Li, Feng Zhang, Tao Yang, and Xinpeng Zhou. Event detection without trig- gers. In Proc. of NAACL, pages 735-744, Minneapolis, Minnesota, June 2019.","title":"Event detection without triggers","authors":"Shulin Liu, Yang Li, Feng Zhang, Tao Yang, Xinpeng Zhou","year":"2019","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mintz et al., 2009] Mike Mintz, Steven Bills, Rion Snow, and Daniel Jurafsky. Distant supervision for relation ex- traction without labeled data. In Proc. of ACL-IJCNLP, pages 1003-1011, 2009.","title":"Distant supervision for relation extraction without labeled data","authors":"Mike Mintz, Steven Bills, Rion Snow, Daniel Jurafsky","year":"2009","venue":"Proc. of ACL-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nguyen et al., 2016] Thien Huu Nguyen, Kyunghyun Cho, and Ralph Grishman. Joint event extraction via recurrent neural networks. In Proc. of NAACL, pages 300-309, San Diego, California, June 2016.","title":"Joint event extraction via recurrent neural networks","authors":"Thien Huu Nguyen, Kyunghyun Cho, Ralph Grishman","year":"2016","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Pouran Ben Veyseh et al., 2021] Amir Pouran Ben Veyseh, Minh Van Nguyen, Nghia Ngo Trung, Bonan Min, and Thien Huu Nguyen. Modeling document-level context for event detection via important context selection. In Proc. of EMNLP, pages 5403-5413, Online and Punta Cana, Do- minican Republic, November 2021. Association for Com- putational Linguistics.","title":"Modeling document-level context for event detection via important context selection","authors":"Ben Amir Pouran, Minh Veyseh, Nghia Van Nguyen, Bonan Ngo Trung, Thien Huu Min, Nguyen","year":"2021","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Veličković et al., 2018] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. Graph attention networks. In Proc. of ICLR, 2018.","title":"Graph attention networks","authors":"Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio","year":"2018","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wadden et al., 2019] David Wadden, Ulme Wennberg, Yi Luan, and Hannaneh Hajishirzi. Entity, relation, and event extraction with contextualized span representations. In Proc. of EMNLP-IJCNLP, pages 5784-5789, Hong Kong, China, November 2019.","title":"Entity, relation, and event extraction with contextualized span representations","authors":"David Wadden, Ulme Wennberg, Yi Luan, Hannaneh Hajishirzi","year":"2019","venue":"Proc. of EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Xu et al., 2021] Runxin Xu, Tianyu Liu, Lei Li, and Baobao Chang. Document-level event extraction via heteroge- neous graph-based interaction model with a tracker. In Proc. of ACL-IJCNLP, pages 3533-3546, Online, August 2021.","title":"Document-level event extraction via heterogeneous graph-based interaction model with a tracker","authors":"Xu","year":"2021","venue":"Proc. of ACL-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yang et al., 2018] Hang Yang, Yubo Chen, Kang Liu, Yang Xiao, and Jun Zhao. DCFEE: A document-level Chinese financial event extraction system based on automatically labeled training data. In Proc. of ACL, pages 50-55, Mel- bourne, Australia, July 2018.","title":"DCFEE: A document-level Chinese financial event extraction system based on automatically labeled training data","authors":"Hang Yang, Yubo Chen, Kang Liu, Yang Xiao, Jun Zhao","year":"2018","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zheng et al., 2019] Shun Zheng, Wei Cao, Wei Xu, and Jiang Bian. Doc2EDAG: An end-to-end document-level framework for Chinese financial event extraction. In Proc. of EMNLP-IJCNLP, pages 337-346, Hong Kong, China, November 2019.","title":"Doc2EDAG: An end-to-end document-level framework for Chinese financial event extraction","authors":"Shun Zheng, Wei Cao, Wei Xu, Jiang Bian","year":"2019","venue":"Proc. of EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}