{"type":"ScholarlyArticle","title":"Global Inference with Explicit Syntactic and Discourse Structures for Dialogue-Level Relation Extraction","authors":[{"name":"Hao Fei","slug":"hao-fei","given":"Hao","family":"Fei","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"},{"name":"Jingye Li","slug":"jingye-li","given":"Jingye","family":"Li","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"},{"name":"Shengqiong Wu","slug":"shengqiong-wu","given":"Shengqiong","family":"Wu","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"},{"name":"Chenliang Li","slug":"chenliang-li","given":"Chenliang","family":"Li","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"},{"name":"Donghong Ji","slug":"donghong-ji","given":"Donghong","family":"Ji","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"},{"name":"Fei Li","slug":"fei-li","given":"Fei","family":"Li","affiliation":"Key Laboratory of Aerospace Information Security and Trusted Computing , Ministry of Education , School of Cyber Science and Engineering , Wuhan University , China"}],"abstract":"Recent research attention for relation extraction has been paid to the dialogue scenario, i.e., dialogue-level relation extraction (DiaRE). Existing DiaRE methods either simply concatenate the utterances in a dialogue into a long piece of text, or employ naive words, sentences or entities to build dialogue graphs, while the structural characteristics in dialogues have not been fully utilized. In this work, we investigate a novel dialogue-level mixed dependency graph (D2G) and an argument reasoning graph (ARG) for DiaRE with a global relation reasoning mechanism. First, we model the entire dialogue into a unified and coherent D2G by explicitly integrating both syntactic and discourse structures, which enables richer semantic and feature learning for relation extraction. Second, we stack an ARG graph on top of D2G to further focus on argument inter-dependency learning and argument representation refinement, for sufficient argument relation inference. In our global reasoning framework, D2G and ARG work collaboratively, iteratively performing lexical, syntactic and semantic information exchange and representation learning over the entire dialogue context. On two DiaRE benchmarks, our framework shows considerable improvements over the current state-of-the-art baselines. Further analyses show that the model effectively solves the long-range dependence issue, and meanwhile gives explainable predictions.","doi":"10.24963/ijcai.2022/570","url":"https://ijcai.org/proceedings/2022/570","pdf":"https://ijcai.org/proceedings/2022/0570.pdf","markdown":"https://ijcai.org/proceedings/2022/570.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/570","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":570,"pages":{"first":4107,"last":4113},"keywords":["Natural Language Processing: Information Extraction","Natural Language Processing: Dialogue and Interactive Systems","Natural Language Processing: Knowledge Extraction","Natural Language Processing: Named Entities"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986538","length_sec":73,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984681","length_sec":345,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Carreras, 2007] Xavier Carreras. Experiments with a higher-order projective dependency parser. In EMNLP, pages 957-961, 2007.","title":"Experiments with a higher-order projective dependency parser","authors":"Xavier Carreras, Carreras","year":"2007","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2020] Hui Chen, Pengfei Hong, Wei Han, Navonil Majumder, and Soujanya Poria. Dialogue rela- tion extraction with document-level heterogeneous graph attention networks. CoRR, abs/2009.05092, 2020.","title":"Dialogue relation extraction with document-level heterogeneous graph attention networks","authors":"Hui Chen, Pengfei Hong, Wei Han, Navonil Majumder, Soujanya Poria","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[de Vries et al., 2017] Harm de Vries, Florian Strub, Jérémie Mary, Hugo Larochelle, Olivier Pietquin, and Aaron C. Courville. Modulating early visual processing by lan- guage. In NeurIPS, pages 6594-6604, 2017.","title":"Modulating early visual processing by language","authors":"De Vries","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":4,"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":5,"raw":"[Fei et al., 2020a] Hao Fei, Yafeng Ren, and Donghong Ji. Boundaries and edges rethinking: An end-to-end neural model for overlapping entity relation extraction. Informa- tion Processing & Management, 57(6):102311, 2020.","title":"Boundaries and edges rethinking: An end-to-end neural model for overlapping entity relation extraction","authors":"Fei","year":"2020","venue":"Information Processing & Management","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fei et al., 2020b] Hao Fei, Yafeng Ren, and Donghong Ji. Improving text understanding via deep syntax-semantics communication. In Findings of the Association for Com- putational Linguistics: EMNLP, pages 84-93, 2020.","title":"Improving text understanding via deep syntax-semantics communication","authors":"Fei","year":"2020","venue":"Findings of the Association for Computational Linguistics: EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fei et al., 2020c] Hao Fei, Yafeng Ren, and Donghong Ji. Mimic and conquer: Heterogeneous tree structure distil- lation for syntactic NLP. In Findings of the Association for Computational Linguistics: EMNLP, pages 183-193, 2020.","title":"Mimic and conquer: Heterogeneous tree structure distillation for syntactic NLP","authors":"Fei","year":"2020","venue":"Findings of the Association for Computational Linguistics: EMNLP","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fei et al., 2020d] Hao Fei, Yafeng Ren, and Donghong Ji. Retrofitting structure-aware transformer language model for end tasks. In EMNLP, pages 2151-2161, 2020.","title":"Retrofitting structure-aware transformer language model for end tasks","authors":"Fei","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fei et al., 2021a] Hao Fei, Fei Li, Bobo Li, and Donghong Ji. Encoder-decoder based unified semantic role labeling with label-aware syntax. In AAAI, pages 12794-12802, 2021.","title":"Encoder-decoder based unified semantic role labeling with label-aware syntax","authors":"Fei","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Fei et al., 2021b] Hao Fei, Shengqiong Wu, Yafeng Ren, Fei Li, and Donghong Ji. Better combine them together! integrating syntactic constituency and dependency repre- sentations for semantic role labeling. In Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021, pages 549-559, 2021.","title":"Better combine them together! integrating syntactic constituency and dependency representations for semantic role labeling","authors":"Fei","year":"2021","venue":"Findings of the Association for Computational Linguistics: ACL/IJCNLP 2021","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jia et al., 2020] Qi Jia, Yizhu Liu, Siyu Ren, Kenny Zhu, and Haifeng Tang. Multi-turn response selection using dialogue dependency relations. In EMNLP, pages 1911- 1920, 2020.","title":"Multi-turn response selection using dialogue dependency relations","authors":"Qi Jia, Yizhu Liu, Siyu Ren, Kenny Zhu, Haifeng Tang","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Katiyar and Cardie, 2016] Arzoo Katiyar and Claire Cardie. Investigating LSTMs for joint extraction of opinion enti- ties and relations. In ACL, pages 919-929, 2016.","title":"Investigating LSTMs for joint extraction of opinion entities and relations","authors":"Cardie Katiyar, Arzoo Katiyar, Claire Cardie","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Long et al., 2021] Xinwei Long, Shuzi Niu, and Yucheng Li. Consistent inference for dialogue relation extraction. In Zhi-Hua Zhou, editor, IJCAI, pages 3885-3891, 2021.","title":"Consistent inference for dialogue relation extraction","authors":"Long","year":"2021","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2021/535"},{"position":14,"raw":"[Lu et al., 2019] Junyu Lu, Chenbin Zhang, Zeying Xie, Guang Ling, Tom Chao Zhou, and Zenglin Xu. Construct- ing interpretive spatio-temporal features for multi-turn re- sponses selection. In ACL, pages 44-50, 2019.","title":"Constructing interpretive spatio-temporal features for multi-turn responses selection","authors":"Lu","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Miwa and Bansal, 2016] Makoto Miwa and Mohit Bansal. End-to-end relation extraction using LSTMs on sequences and tree structures. In ACL, pages 1105-1116, 2016.","title":"End-to-end relation extraction using LSTMs on sequences and tree structures","authors":"Bansal Miwa, Makoto Miwa, Mohit Bansal","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nan et al., 2021] Guoshun Nan, Guoqing Luo, Sicong Leng, Yao Xiao, and Wei Lu. Speaker-oriented latent structures for dialogue-based relation extraction. CoRR, abs/2109.05182, 2021.","title":"Speaker-oriented latent structures for dialogue-based relation extraction","authors":"Nan","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Qiu et al., 2021] Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu, and Song-Chun Zhu. SocAoG: Incremental graph parsing for social rela- tion inference in dialogues. In ACL, pages 658-670, 2021.","title":"SocAoG: Incremental graph parsing for social relation inference in dialogues","authors":"Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu, Song-Chun Zhu","year":"2021","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Song et al., 2019] Linfeng Song, Yue Zhang, Daniel Gildea, Mo Yu, Zhiguo Wang, and Jinsong Su. Leveraging de- pendency forest for neural medical relation extraction. In EMNLP, pages 208-218, 2019.","title":"Leveraging dependency forest for neural medical relation extraction","authors":"Song","year":"2019","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wu et al., 2021] Shengqiong Wu, Hao Fei, Yafeng Ren, Donghong Ji, and Jingye Li. Learn from syntax: Improv- ing pair-wise aspect and opinion terms extraction with rich syntactic knowledge. In IJCAI, pages 3957-3963, 2021.","title":"Learn from syntax: Improving pair-wise aspect and opinion terms extraction with rich syntactic knowledge","authors":"Shengqiong Wu, Hao Fei, Yafeng Ren, Donghong Ji, Jingye Li","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/545"},{"position":20,"raw":"[Xiong et al., 2020] Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, and Tie-Yan Liu. On layer nor- malization in the transformer architecture. In ICML, pages 10524-10533, 2020.","title":"On layer normalization in the transformer architecture","authors":"Xiong","year":"2020","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Xu et al., 2015] Yan Xu, Lili Mou, Ge Li, Yunchuan Chen, Hao Peng, and Zhi Jin. Classifying relations via long short term memory networks along shortest dependency paths. In EMNLP, pages 1785-1794, 2015.","title":"Classifying relations via long short term memory networks along shortest dependency paths","authors":"Yan Xu, Lili Mou, Ge Li, Yunchuan Chen, Hao Peng, Zhi Jin","year":"2015","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Xue et al., 2021] Fuzhao Xue, Aixin Sun, Hao Zhang, and Eng Siong Chng. Gdpnet: Refining latent multi-view graph for relation extraction. In AAAI, pages 14194- 14202, 2021.","title":"Gdpnet: Refining latent multi-view graph for relation extraction","authors":"Xue","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yao et al., 2019] Yuan Yao, Deming Ye, Peng Li, Xu Han, Yankai Lin, Zhenghao Liu, Zhiyuan Liu, Lixin Huang, Jie Zhou, and Maosong Sun. DocRED: A large-scale document-level relation extraction dataset. In ACL, pages 764-777, 2019.","title":"DocRED: A large-scale document-level relation extraction dataset","authors":"Yuan Yao, Deming Ye, Peng Li, Xu Han, Yankai Lin, Zhenghao Liu, Zhiyuan Liu, Lixin Huang, Jie Zhou, Maosong Sun","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yu et al., 2020] Dian Yu, Kai Sun, Claire Cardie, and Dong Yu. Dialogue-based relation extraction. In ACL, pages 4927-4940, 2020.","title":"Dialogue-based relation extraction","authors":"Dian Yu, Kai Sun, Claire Cardie, Dong Yu","year":"2020","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhao et al., 2021] Tianyang Zhao, Zhao Yan, Yunbo Cao, and Zhoujun Li. Enhancing dialogue-based relation ex- traction by speaker and trigger words prediction. In Find- ings of ACL, pages 4580-4585, 2021.","title":"Enhancing dialogue-based relation extraction by speaker and trigger words prediction","authors":"Tianyang Zhao, Zhao Yan, Yunbo Cao, Zhoujun Li","year":"2021","venue":"Findings of ACL","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhou et al., 2021] Mengjia Zhou, Donghong Ji, and Fei Li. Relation extraction in dialogues: A deep learning model based on the generality and specialty of dialogue text. IEEE ACM TASLP, 29:2015-2026, 2021.","title":"Relation extraction in dialogues: A deep learning model based on the generality and specialty of dialogue text","authors":"Zhou","year":"2021","venue":"IEEE ACM TASLP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}