{"type":"ScholarlyArticle","title":"Knowledge Enhanced Event Causality Identification with Mention Masking Generalizations","authors":[{"name":"Jian Liu","slug":"jian-liu","given":"Jian","family":"Liu","affiliation":"National Laboratory of Pattern Recognition , Institute of Automation Chinese Academy of Sciences , Beijing , 100190 , China; School of Artificial Intelligence , University of Chinese Academy of Sciences , Beijing , 100049 , China"},{"name":"Yubo Chen","slug":"yubo-chen","given":"Yubo","family":"Chen","affiliation":"National Laboratory of Pattern Recognition , Institute of Automation Chinese Academy of Sciences , Beijing , 100190 , China; School of Artificial Intelligence , University of Chinese Academy of Sciences , Beijing , 100049 , China"},{"name":"Jun Zhao","slug":"jun-zhao","given":"Jun","family":"Zhao","affiliation":"National Laboratory of Pattern Recognition , Institute of Automation Chinese Academy of Sciences , Beijing , 100190 , China; School of Artificial Intelligence , University of Chinese Academy of Sciences , Beijing , 100049 , China"}],"abstract":"Identifying causal relations of events is a crucial language understanding task. Despite many efforts for this task, existing methods lack the ability to adopt background knowledge, and they typically generalize poorly to new, previously unseen data. In this paper, we present a new method for event causality identification, aiming to address limitations of previous methods. On the one hand, our model can leverage external knowledge for reasoning, which can greatly enrich the representation of events; On the other hand, our model can mine event-agnostic, context-specific patterns, via a mechanism called event mention masking generalization, which can greatly enhance the ability of our model to handle new, previously unseen cases. In experiments, we evaluate our model on three benchmark datasets and show our model outperforms previous methods by a significant margin. Moreover, we perform 1) cross-topic adaptation, 2) exploiting unseen predicates, and 3) cross-task adaptation to evaluate the generalization ability of our model. Experimental results show that our model demonstrates a definite advantage over previous methods.","doi":"10.24963/ijcai.2020/499","url":"https://ijcai.org/proceedings/2020/499","pdf":"https://ijcai.org/proceedings/2020/0499.pdf","markdown":"https://ijcai.org/proceedings/2020/499.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/499","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Natural Language Processing","track":"Main track","number":499,"pages":{"first":3608,"last":3614},"keywords":["Natural Language Processing: Discourse","Natural Language Processing: Information Extraction","Natural Language Processing: Knowledge Extraction"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24820/file_24820.m3u8","length_sec":260,"provider":"hls"}],"references":[{"position":1,"raw":"[Beamer and Girju, 2009] Brandon Beamer and Roxana Girju. Using a bigram event model to predict causal po- tential. In COLING, pages 430-441, 2009.","title":"Using a bigram event model to predict causal potential","authors":"Girju Beamer, Brandon Beamer, Roxana Girju","year":"2009","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Berant et al., 2014] Jonathan Berant, Vivek Srikumar, Pei- Chun Chen, Abby Vander Linden, Brittany Harding, Brad Huang, Peter Clark, and Christopher D. Manning. Mod- eling biological processes for reading comprehension. In EMNLP, pages 1499-1510, 2014.","title":"Modeling biological processes for reading comprehension","authors":"Jonathan Berant, Vivek Srikumar, Pei-Chun Chen, Abby Vander Linden, Brittany Harding, Brad Huang, Peter Clark, Christopher D Manning","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Caselli and Vossen, 2017] Tommaso Caselli and Piek Vossen. The event StoryLine corpus: A new benchmark for causal and temporal relation extraction. In ACL Workshop, pages 77-86, 2017.","title":"The event StoryLine corpus: A new benchmark for causal and temporal relation extraction","authors":"Tommaso Caselli, Piek Vossen","year":"2017","venue":"ACL Workshop","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cheng and Miyao, 2017] Fei Cheng and Yusuke Miyao. Classifying temporal relations by bidirectional LSTM over dependency paths. In ACL, pages 1-6, 2017.","title":"Classifying temporal relations by bidirectional LSTM over dependency paths","authors":"Miyao ; ] Fei Cheng, Yusuke Cheng, Miyao","year":"2017","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Choubey and Huang, 2017] Prafulla Kumar Choubey and Ruihong Huang. A sequential model for classifying tem- poral relations between intra-sentence events. In EMNLP, pages 1796-1802, 2017.","title":"A sequential model for classifying temporal relations between intra-sentence events","authors":"Prafulla Kumar, Choubey, Ruihong Huang","year":"2017","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":6,"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 NAACL, pages 4171-4186, 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":"NAACL","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Do et al., 2011] Quang Do, Yee Seng Chan, and Dan Roth. Minimally supervised event causality identification. In EMNLP, pages 294-303, 2011.","title":"Minimally supervised event causality identification","authors":"Quang Do, Yee Seng Chan, Dan Roth","year":"2011","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fan et al., 2019] Angela Fan, Claire Gardent, Chloé Braud, and Antoine Bordes. Using local knowledge graph con- struction to scale Seq2Seq models to multi-document in- puts. In EMNLP, pages 4186-4196, 2019.","title":"Using local knowledge graph construction to scale Seq2Seq models to multi-document inputs","authors":"Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes","year":"2019","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gao et al., 2019] Lei Gao, Prafulla Kumar Choubey, and Ruihong Huang. Modeling document-level causal struc- tures for event causal relation identification. In NAACL, pages 1808-1817, 2019.","title":"Modeling document-level causal structures for event causal relation identification","authors":"Lei Gao, Prafulla Kumar Choubey, Ruihong Huang","year":"2019","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Girju, 2003] Roxana Girju. Automatic detection of causal relations for question answering. In ACL Workshop, pages 76-83, 2003.","title":"Roxana Girju. Automatic detection of causal relations for question answering","authors":"Girju","year":"2003","venue":"ACL Workshop","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hashimoto et al., 2014] Chikara Hashimoto, Kentaro Tori- sawa, Julien Kloetzer, Motoki Sano, István Varga, Jong- Hoon Oh, and Yutaka Kidawara. Toward future scenario generation: Extracting event causality exploiting semantic relation, context, and association features. In ACL, pages 987-997, 2014.","title":"Toward future scenario generation: Extracting event causality exploiting semantic relation, context, and association features","authors":"Chikara Hashimoto, Kentaro Torisawa, Julien Kloetzer, Motoki Sano, István Varga, Jong-Hoon Oh, Yutaka Kidawara","year":"2014","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hashimoto, 2019] Chikara Hashimoto. Weakly supervised multilingual causality extraction from Wikipedia. In EMNLP, pages 2988-2999, 2019.","title":"Weakly supervised multilingual causality extraction from Wikipedia","authors":"Chikara Hashimoto","year":"2019","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hu et al., 2017] Zhichao Hu, Elahe Rahimtoroghi, and Mar- ilyn Walker. Inference of fine-grained event causality from blogs and films. In ACL Workshop, pages 52-58, 2017.","title":"Inference of fine-grained event causality from blogs and films","authors":"Zhichao Hu, Elahe Rahimtoroghi, Marilyn Walker","year":"2017","venue":"ACL Workshop","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kadowaki et al., 2019] Kazuma Kadowaki, Ryu Iida, Ken- taro Torisawa, Jong-Hoon Oh, and Julien Kloetzer. Event causality recognition exploiting multiple annotators' judg- ments and background knowledge. In EMNLP, pages 5816-5822, 2019.","title":"Event causality recognition exploiting multiple annotators' judgments and background knowledge","authors":"Kazuma Kadowaki, Ryu Iida, Kentaro Torisawa, Jong-Hoon Oh, Julien Kloetzer","year":"2019","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kingma and Ba, 2015] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lehmann et al., 2014] Jens Lehmann, Robert Isele, Max Jakob, Anja Jentzsch, Dimitris Kontokostas, Pablo N. Mendes, Sebastian Hellmann, Mohamed Morsey, Patrick van Kleef, Sören Auer, and Christian Bizer. DBpedia - a large-scale, multilingual knowledge base extracted from wikipedia. Semantic Web Journal, (2):167-195, 2014.","title":"DBpediaa large-scale, multilingual knowledge base extracted from wikipedia","authors":"Lehmann","year":"2014","venue":"Semantic Web Journal","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Miller, 1995] George A. Miller. Wordnet: A lexical database for english. Commun. ACM, 1995.","title":"Wordnet: A lexical database for english","authors":"George A Miller","year":"1995","venue":"Commun. ACM","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Min et al., 2013] Bonan Min, Ralph Grishman, Li Wan, Chang Wang, and David Gondek. Distant supervision for relation extraction with an incomplete knowledge base. In NAACL, pages 777-782, 2013.","title":"Distant supervision for relation extraction with an incomplete knowledge base","authors":"Bonan Min, Ralph Grishman, Li Wan, Chang Wang, David Gondek","year":"2013","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Minsky, 1974] Marvin Minsky. A framework for represent- ing knowledge. Technical report, USA, 1974.","title":"A framework for representing knowledge","authors":"Marvin Minsky","year":"1974","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Mirza and Tonelli, 2016] Paramita Mirza and Sara Tonelli. CATENA: CAusal and TEmporal relation extraction from NAtural language texts. In COLING, pages 64-75, 2016.","title":"CATENA: CAusal and TEmporal relation extraction from NAtural language texts","authors":"Tonelli Mirza, Paramita Mirza, Sara Tonelli","year":"2016","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Mirza et al., 2014] Paramita Mirza, Rachele Sprugnoli, Sara Tonelli, and Manuela Speranza. Annotating causal- ity in the TempEval-3 corpus. In EACL Workshop, pages 10-19, 2014.","title":"Annotating causality in the TempEval-3 corpus","authors":"Paramita Mirza, Rachele Sprugnoli, Sara Tonelli, Manuela Speranza","year":"2014","venue":"EACL Workshop","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Mirza, 2014a] Paramita Mirza. Extracting temporal and causal relations between events. In ACL Workshop, pages 10-17, 2014.","title":"Extracting temporal and causal relations between events","authors":"Paramita Mirza, Mirza","year":"2014","venue":"ACL Workshop","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Mirza, 2014b] Paramita Mirza. Fbk-hlt-time : a complete italian temporal processing system for eventi-evalita 2014. In EVALITA 2014, pages 44-49, 2014.","title":"Paramita Mirza. Fbk-hlt-time : a complete italian temporal processing system for eventi-evalita 2014","authors":"Mirza","year":"2014","venue":"EVALITA 2014","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Ning et al., 2018] Qiang Ning, Zhili Feng, Hao Wu, and Dan Roth. Joint reasoning for temporal and causal rela- tions. In ACL, pages 2278-2288, 2018.","title":"Joint reasoning for temporal and causal relations","authors":"Qiang Ning, Zhili Feng, Hao Wu, Dan Roth","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Oh et al., 2016] Jong-Hoon Oh, Kentaro Torisawa, Chikara Hashimoto, Ryu Iida, Masahiro Tanaka, and Julien Kloet- zer. A semi-supervised learning approach to why-question answering. In AAAI, page 3022-3029, 2016.","title":"A semi-supervised learning approach to why-question answering","authors":"Jong-Hoon Oh, Kentaro Torisawa, Chikara Hashimoto, Ryu Iida, Masahiro Tanaka, Julien Kloetzer","year":"2016","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Rahman and Ng, 2011] Altaf Rahman and Vincent Ng. Coreference resolution with world knowledge. In ACL, pages 814-824, 2011.","title":"Coreference resolution with world knowledge","authors":"Ng Rahman, Altaf Rahman, Vincent Ng","year":"2011","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Riaz and Girju, 2014] Mehwish Riaz and Roxana Girju. In- depth exploitation of noun and verb semantics to identify causation in verb-noun pairs. In SIGDIAL, pages 161-170, 2014.","title":"Mehwish Riaz and Roxana Girju. Indepth exploitation of noun and verb semantics to identify causation in verb-noun pairs","authors":"Girju Riaz","year":"2014","venue":"SIGDIAL","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Speer et al., 2017] Robyn Speer, Joshua Chin, and Cather- ine Havasi. Conceptnet 5.5: An open multilingual graph of general knowledge. In AAAI, page 4444-4451, 2017.","title":"Conceptnet 5.5: An open multilingual graph of general knowledge","authors":"Speer","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yang and Mitchell, 2017] Bishan Yang and Tom Mitchell. Leveraging knowledge bases in LSTMs for improving ma- chine reading. In ACL, pages 1436-1446, July 2017.","title":"Leveraging knowledge bases in LSTMs for improving machine reading","authors":"Yang, Mitchell ;, Bishan Yang, Tom Mitchell","year":"2017","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhou et al., 2018] Hao Zhou, Tom Yang, Minlie Huang, Haizhou Zhao, Jingfang Xu, and Xiaoyan Zhu. Com- monsense knowledge aware conversation generation with graph attention. In IJCAI-ECAI, pages 4623-4629, 2018.","title":"Commonsense knowledge aware conversation generation with graph attention","authors":"Hao Zhou, Tom Yang, Minlie Huang, Haizhou Zhao, Jingfang Xu, Xiaoyan Zhu","year":"2018","venue":"IJCAI-ECAI","doi":null,"url":null,"internal_url":"/proceedings/2018/643"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}