{"type":"ScholarlyArticle","title":"GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension","authors":[{"name":"Yu Chen","slug":"yu-chen","given":"Yu","family":"Chen","affiliation":"Rensselaer Polytechnic Institute"},{"name":"Lingfei Wu","slug":"lingfei-wu","given":"Lingfei","family":"Wu","affiliation":"IBM Research"},{"name":"Mohammed J. Zaki","slug":"mohammed-j-zaki","given":"Mohammed J.","family":"Zaki","affiliation":"Rensselaer Polytechnic Institute"}],"abstract":"Conversational machine comprehension (MC) has proven significantly more challenging compared to traditional MC since it requires better utilization of conversation history. However, most existing approaches do not effectively capture conversation history and thus have trouble handling questions involving coreference or ellipsis. Moreover, when reasoning over passage text, most of them simply treat it as a word sequence without exploring rich semantic relationships among words. In this paper, we first propose a simple yet effective graph structure learning technique to dynamically construct a question and conversation history aware context graph at each conversation turn. Then we propose a novel Recurrent Graph Neural Network, and based on that, we introduce a flow mechanism to model the temporal dependencies in a sequence of context graphs. The proposed GraphFlow model can effectively capture conversational flow in a dialog, and shows competitive performance compared to existing state-of-the-art methods on CoQA, QuAC and DoQA benchmarks. In addition, visualization experiments show that our proposed model can offer good interpretability for the reasoning process.","doi":"10.24963/ijcai.2020/171","url":"https://ijcai.org/proceedings/2020/171","pdf":"https://ijcai.org/proceedings/2020/0171.pdf","markdown":"https://ijcai.org/proceedings/2020/171.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/171","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":"Data Mining","track":"Main track","number":171,"pages":{"first":1230,"last":1236},"keywords":["Natural Language Processing: Dialogue","Natural Language Processing: Question Answering","Data Mining: Mining Graphs, Semi Structured Data, Complex Data"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25308/file_25308.m3u8","length_sec":280,"provider":"hls"}],"references":[{"position":1,"raw":"[Campos et al., 2019] Jon Ander Campos, Arantxa Otegi, Aitor Soroa, Jan Deriu, Mark Cieliebak, and Eneko Agirre. Conver- sational qa for faqs. In NeurIPS, 2019.","title":"Conversational qa for faqs","authors":"Campos","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chen et al., 2017] Danqi Chen, Adam Fisch, Jason Weston, and Antoine Bordes. Reading wikipedia to answer open-domain questions. arXiv preprint arXiv:1704.00051, 2017.","title":"Reading wikipedia to answer open-domain questions","authors":"Chen","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2019a] Yu Chen, Lingfei Wu, and Mohammed J Zaki. Deep iterative and adaptive learning for graph neural networks. arXiv preprint arXiv:1912.07832, 2019.","title":"Deep iterative and adaptive learning for graph neural networks","authors":"Chen","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2019b] Yu Chen, Lingfei Wu, and Mohammed J Zaki. Reinforcement learning based graph-to-sequence model for natu- ral question generation. arXiv preprint arXiv:1908.04942, 2019.","title":"Reinforcement learning based graph-to-sequence model for natural question generation","authors":"Chen","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2020] Yu Chen, Lingfei Wu, and Mohammed J Zaki. Toward subgraph guided knowledge graph question generation with graph neural networks. arXiv preprint arXiv:2004.06015, 2020.","title":"Toward subgraph guided knowledge graph question generation with graph neural networks","authors":"Yu Chen, Lingfei Wu, Mohammed J Zaki","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. In EMNLP, pages 1724-1734, 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Choi et al., 2018] Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, and Luke Zettle- moyer. Quac: Question answering in context. arXiv preprint arXiv:1808.07036, 2018.","title":"Quac: Question answering in context","authors":"Choi","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[De Cao et al., 2018] Nicola De Cao, Wilker Aziz, and Ivan Titov. Question answering by reasoning across documents with graph convolutional networks. arXiv preprint arXiv:1808.09920, 2018.","title":"Question answering by reasoning across documents with graph convolutional networks","authors":"Nicola De Cao, Wilker Aziz, Ivan Titov","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Devlin et al., 2018] Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirec- tional transformers for language understanding. 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":10,"raw":"[Gilmer et al., 2017] Justin Gilmer, Samuel S Schoenholz, Patrick F Riley, Oriol Vinyals, and George E Dahl. Neural message passing for quantum chemistry. In ICML-Volume 70, pages 1263-1272. JMLR. org, 2017.","title":"Neural message passing for quantum chemistry","authors":"Justin Gilmer, S Samuel, Patrick F Schoenholz, Oriol Riley, George E Vinyals, Dahl","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hamilton et al., 2017] Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. In NIPS, pages 1024-1034, 2017.","title":"Inductive representation learning on large graphs","authors":"Hamilton","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":12,"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":"Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Huang et al., 2018] Hsin-Yuan Huang, Eunsol Choi, and Wen-tau Yih. Flowqa: Grasping flow in history for conversational ma- chine comprehension. arXiv preprint arXiv:1810.06683, 2018.","title":"Flowqa: Grasping flow in history for conversational machine comprehension","authors":"Hsin-Yuan Huang, Eunsol Choi, Wen-Tau Yih","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ju et al., 2019] Ying Ju, Fubang Zhao, Shijie Chen, Bowen Zheng, Xuefeng Yang, and Yunfeng Liu. Technical report on conver- sational question answering. arXiv preprint arXiv:1909.10772, 2019.","title":"Technical report on conversational question answering","authors":"Ying Ju, Fubang Zhao, Shijie Chen, Bowen Zheng, Xuefeng Yang, Yunfeng Liu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kingma and Ba, 2014] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kipf and Welling, 2016] Thomas N Kipf and Max Welling. Semi- supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.","title":"Semisupervised classification with graph convolutional networks","authors":"N Thomas, Max Kipf, Welling","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lee et al., 2016] Kenton Lee, Shimi Salant, Tom Kwiatkowski, Ankur Parikh, Dipanjan Das, and Jonathan Berant. Learning re- current span representations for extractive question answering. arXiv preprint arXiv:1611.01436, 2016.","title":"Learning recurrent span representations for extractive question answering","authors":"Kenton Lee, Shimi Salant, Tom Kwiatkowski, Ankur Parikh, Dipanjan Das, Jonathan Berant","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Li et al., 2015] Yujia Li, Daniel Tarlow, Marc Brockschmidt, and Richard Zemel. Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493, 2015.","title":"Gated graph sequence neural networks","authors":"Yujia Li, Daniel Tarlow, Marc Brockschmidt, Richard Zemel","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Liu et al., 2018] Pengfei Liu, Shuaichen Chang, Xuanjing Huang, Jian Tang, and Jackie Chi Kit Cheung. Contextualized non- local neural networks for sequence learning. arXiv preprint arXiv:1811.08600, 2018.","title":"Contextualized nonlocal neural networks for sequence learning","authors":"Pengfei Liu, Shuaichen Chang, Xuanjing Huang, Jian Tang, Jackie Chi, Kit Cheung","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pennington et al., 2014] Jeffrey Pennington, Richard Socher, and Christopher Manning. Glove: Global vectors for word represen- tation. In EMNLP, pages 1532-1543, 2014.","title":"Glove: Global vectors for word representation","authors":"Jeffrey Pennington, Richard Socher, Christopher Manning","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Qu et al., 2019] Chen Qu, Liu Yang, Minghui Qiu, Yongfeng Zhang, Cen Chen, W Bruce Croft, and Mohit Iyyer. Attentive his- tory selection for conversational question answering. In CIKM, pages 1391-1400, 2019.","title":"Attentive history selection for conversational question answering","authors":"Chen Qu, Liu Yang, Minghui Qiu, Yongfeng Zhang, Cen Chen, Bruce Croft, Mohit Iyyer","year":"2019","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rajpurkar et al., 2016] Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. Squad: 100,000+ questions for ma- chine comprehension of text. arXiv preprint arXiv:1606.05250, 2016.","title":"Squad: 100,000+ questions for machine comprehension of text","authors":"Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, Percy Liang","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Reddy et al., 2018] Siva Reddy, Danqi Chen, and Christopher D Manning. Coqa: A conversational question answering challenge. arXiv preprint arXiv:1808.07042, 2018.","title":"Coqa: A conversational question answering challenge","authors":"Siva Reddy, Danqi Chen, Christopher D Manning","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[See et al., 2017] Abigail See, Peter J Liu, and Christopher D Man- ning. Get to the point: Summarization with pointer-generator networks. arXiv preprint arXiv:1704.04368, 2017.","title":"Get to the point: Summarization with pointer-generator networks","authors":"Abigail See, Peter J Liu, Christopher D Manning","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Song et al., 2018] Linfeng Song, Zhiguo Wang, Mo Yu, Yue Zhang, Radu Florian, and Daniel Gildea. Exploring graph- structured passage representation for multi-hop reading com- prehension with graph neural networks. arXiv preprint arXiv:1809.02040, 2018.","title":"Exploring graphstructured passage representation for multi-hop reading comprehension with graph neural networks","authors":"Song","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Sun et al., 2018] Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, and William W Cohen. Open domain question answering using early fusion of knowl- edge bases and text. arXiv preprint arXiv:1809.00782, 2018.","title":"Open domain question answering using early fusion of knowledge bases and text","authors":"Sun","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang et al., 2018] Wei Wang, Ming Yan, and Chen Wu. Multi- granularity hierarchical attention fusion networks for read- ing comprehension and question answering. arXiv preprint arXiv:1811.11934, 2018.","title":"Multigranularity hierarchical attention fusion networks for reading comprehension and question answering","authors":"Wei Wang, Ming Yan, Chen Wu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Xu et al., 2018a] Kun Xu, Lingfei Wu, Zhiguo Wang, and Vadim Sheinin. Graph2seq: Graph to sequence learning with attention- based neural networks. arXiv preprint arXiv:1804.00823, 2018.","title":"Graph2seq: Graph to sequence learning with attentionbased neural networks","authors":"Xu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Xu et al., 2018b] Kun Xu, Lingfei Wu, Zhiguo Wang, Mo Yu, Li- wei Chen, and Vadim Sheinin. Exploiting rich syntactic informa- tion for semantic parsing with graph-to-sequence model. arXiv preprint arXiv:1808.07624, 2018.","title":"Exploiting rich syntactic information for semantic parsing with graph-to-sequence model","authors":"Xu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Yatskar, 2018] Mark Yatskar. A qualitative comparison of coqa, squad 2.0 and quac. arXiv preprint arXiv:1809.10735, 2018.","title":"A qualitative comparison of coqa, squad 2.0 and quac","authors":"Mark Yatskar","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Yeh and Chen, 2019] Yi-Ting Yeh and Yun-Nung Chen. Flowdelta: Modeling flow information gain in reasoning for conversational machine comprehension. arXiv preprint arXiv:1908.05117, 2019.","title":"Flowdelta: Modeling flow information gain in reasoning for conversational machine comprehension","authors":"Chen ; ] Yi-Ting Yeh, Yun-Nung Yeh, Chen","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhu et al., 2018] Chenguang Zhu, Michael Zeng, and Xuedong Huang. Sdnet: Contextualized attention-based deep net- work for conversational question answering. arXiv preprint arXiv:1812.03593, 2018.","title":"Sdnet: Contextualized attention-based deep network for conversational question answering","authors":"Chenguang Zhu, Michael Zeng, Xuedong Huang","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}