{"type":"ScholarlyArticle","title":"Reasoning over Hybrid Chain for Table-and-Text Open Domain Question Answering","authors":[{"name":"Wanjun Zhong","slug":"wanjun-zhong","given":"Wanjun","family":"Zhong","affiliation":"The School of Computer Science and Engineering , Sun Yat-sen University"},{"name":"Junjie Huang","slug":"junjie-huang","given":"Junjie","family":"Huang","affiliation":"Beihang University"},{"name":"Qian Liu","slug":"qian-liu","given":"Qian","family":"Liu","affiliation":"Beihang University"},{"name":"Ming Zhou","slug":"ming-zhou","given":"Ming","family":"Zhou","affiliation":"Langboat Technology"},{"name":"Jiahai Wang","slug":"jiahai-wang","given":"Jiahai","family":"Wang","affiliation":"The School of Computer Science and Engineering , Sun Yat-sen University"},{"name":"Jian Yin","slug":"jian-yin","given":"Jian","family":"Yin","affiliation":"The School of Computer Science and Engineering , Sun Yat-sen University"},{"name":"Nan Duan","slug":"nan-duan","given":"Nan","family":"Duan","affiliation":"Microsoft Research Asia"}],"abstract":"Tabular and textual question answering requires systems to perform reasoning over heterogeneous information, considering table structure, and the connections among table and text. In this paper, we propose a ChAin-centric Reasoning and Pre-training framework (CARP). CARP utilizes hybrid chain to model the explicit intermediate reasoning process across table and text for question answering. We also propose a novel chain-centric pre-training method, to enhance the pre-trained model in identifying the cross-modality reasoning process and alleviating the data sparsity problem. This method constructs the large-scale reasoning corpus by synthesizing pseudo heterogeneous reasoning paths from Wikipedia and generating corresponding questions. We evaluate our system on OTT-QA, a large-scale table-and-text open-domain question answering benchmark, and our system achieves the state-of-the-art performance. Further analyses illustrate that the explicit hybrid chain offers substantial performance improvement and interpretablity of the intermediate reasoning process, and the chain-centric pre-training boosts the performance on the chain extraction.","doi":"10.24963/ijcai.2022/629","url":"https://ijcai.org/proceedings/2022/629","pdf":"https://ijcai.org/proceedings/2022/0629.pdf","markdown":"https://ijcai.org/proceedings/2022/629.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/629","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":629,"pages":{"first":4531,"last":4537},"keywords":["Natural Language Processing: Interpretability and Analysis of Models for NLP","Natural Language Processing: Information Retrieval and Text Mining","Natural Language Processing: Question Answering","Natural Language Processing: Natural Language Semantics"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987115","length_sec":90,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985258","length_sec":589,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Asai et al., 2019] Akari Asai, Kazuma Hashimoto, Han- naneh Hajishirzi, Richard Socher, and Caiming Xiong. Learning to retrieve reasoning paths over wikipedia graph for question answering. arXiv preprint arXiv:1911.10470, 2019.","title":"Learning to retrieve reasoning paths over wikipedia graph for question answering","authors":"Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher, Caiming Xiong","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Beltagy et al., 2020] Iz Beltagy, Matthew E Peters, and Ar- man Cohan. Longformer: The long-document trans- former. arXiv preprint arXiv:2004.05150, 2020.","title":"Iz Beltagy, Matthew E Peters, and Arman Cohan. Longformer: The long-document transformer","authors":"Beltagy","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2019a] Jifan Chen, Shih-ting Lin, and Greg Durrett. Multi-hop question answering via reasoning chains. arXiv preprint arXiv:1910.02610, 2019.","title":"Multi-hop question answering via reasoning chains","authors":"Chen","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2019b] Wenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang, Hong Wang, Shiyang Li, Xiyou Zhou, and William Yang Wang. Tabfact: A large-scale dataset for table-based fact verification. arXiv preprint arXiv:1909.02164, 2019.","title":"Tabfact: A large-scale dataset for table-based fact verification","authors":"Chen","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen et al., 2020a] Wenhu Chen, Ming-Wei Chang, Eva Schlinger, William Wang, and William W Cohen. Open question answering over tables and text. arXiv preprint arXiv:2010.10439, 2020.","title":"Open question answering over tables and text","authors":"Chen","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2020b] Wenhu Chen, Hanwen Zha, Zhiyu Chen, Wenhan Xiong, Hong Wang, and William Wang. Hybridqa: A dataset of multi-hop question answering over tabular and textual data. arXiv preprint arXiv:2004.07347, 2020.","title":"Hybridqa: A dataset of multi-hop question answering over tabular and textual data","authors":"Chen","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ding et al., 2019] Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, and Jie Tang. Cognitive graph for multi- hop reading comprehension at scale. arXiv preprint arXiv:1905.05460, 2019.","title":"Cognitive graph for multihop reading comprehension at scale","authors":"Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, Jie Tang","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dunn et al., 2017] Matthew Dunn, Levent Sagun, Mike Higgins, V Ugur Guney, Volkan Cirik, and Kyunghyun Cho. Searchqa: A new q&a dataset augmented with context from a search engine. arXiv preprint arXiv:1704.05179, 2017.","title":"Searchqa: A new q&a dataset augmented with context from a search engine","authors":"Matthew Dunn, Levent Sagun, Mike Higgins, V Ugur Guney, Volkan Cirik, Kyunghyun Cho","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fang et al., 2019] Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang, and Jingjing Liu. Hierarchical graph network for multi-hop question answering. arXiv preprint arXiv:1911.03631, 2019.","title":"Hierarchical graph network for multi-hop question answering","authors":"Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang, Jingjing Liu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Feng et al., 2020] Yufei Feng, Mo Yu, Wenhan Xiong, Xi- aoxiao Guo, Junjie Huang, Shiyu Chang, Murray Camp- bell, M. Greenspan, and Xiao-Dan Zhu. Learning to re- cover reasoning chains for multi-hop question answering via cooperative games. ArXiv, abs/2004.02393, 2020.","title":"Learning to recover reasoning chains for multi-hop question answering via cooperative games","authors":"Yufei Feng, Mo Yu, Wenhan Xiong, Xiaoxiao Guo, Junjie Huang, Shiyu Chang, Murray Campbell, M Greenspan, Xiao-Dan Zhu","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gao et al., 2021] Yifan Gao, Jingjing Li, Michael R Lyu, and Irwin King. Open-retrieval conversational machine reading. arXiv preprint arXiv:2102.08633, 2021.","title":"Open-retrieval conversational machine reading","authors":"Yifan Gao, Jingjing Li, Irwin Michael R Lyu, King","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Johnson et al., 2021] Jeff Johnson, M. Douze, and H. Jégou. Billion-scale similarity search with gpus. IEEE Transac- tions on Big Data, 7:535-547, 2021.","title":"Billion-scale similarity search with gpus","authors":"Jeff Johnson, M Douze, H Jégou","year":"2021","venue":"IEEE Transactions on Big Data","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Joshi et al., 2017] Mandar Joshi, Eunsol Choi, Daniel S Weld, and Luke Zettlemoyer. Triviaqa: A large scale distantly supervised challenge dataset for reading compre- hension. arXiv preprint arXiv:1705.03551, 2017.","title":"Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension","authors":"Mandar Joshi, Eunsol Choi, Daniel S Weld, Luke Zettlemoyer","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Karpukhin et al., 2020] Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906, 2020.","title":"Dense passage retrieval for open-domain question answering","authors":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-Tau Yih","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ledell et al., 2020] Wu Ledell, Petroni Fabio, Josifoski Martin, Riedel Sebastian, and Zettlemoyer Luke. Zero- shot entity linking with dense entity retrieval. In EMNLP, 2020.","title":"Zeroshot entity linking with dense entity retrieval","authors":"Petroni Wu Ledell, Josifoski Fabio, Riedel Martin, Zettlemoyer Sebastian, Luke","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lee et al., 2019] Kenton Lee, Ming-Wei Chang, and Kristina Toutanova. Latent retrieval for weakly super- vised open domain question answering. arXiv preprint arXiv:1906.00300, 2019.","title":"Latent retrieval for weakly supervised open domain question answering","authors":"Kenton Lee, Ming-Wei Chang, Kristina Toutanova","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lewis et al., 2019] Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. Bart: De- noising sequence-to-sequence pre-training for natural lan- guage generation, translation, and comprehension. arXiv preprint arXiv:1910.13461, 2019.","title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","authors":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, Luke Zettlemoyer","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Li et al., 2021] Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, and Bing Xiang. Dual reader-parser on hybrid textual and tabular evidence for open domain question answering. arXiv preprint arXiv:2108.02866, 2021.","title":"Dual reader-parser on hybrid textual and tabular evidence for open domain question answering","authors":"Alexander Hanbo, Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, Bing Xiang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Liu et al., 2019] Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, M. Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized bert pretraining approach. ArXiv, abs/1907.11692, 2019.","title":"Roberta: A robustly optimized bert pretraining approach","authors":"Liu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pasupat and Liang, 2015] Panupong Pasupat and Percy Liang. Compositional semantic parsing on semi-structured tables. arXiv preprint arXiv:1508.00305, 2015.","title":"Panupong Pasupat and Percy Liang. Compositional semantic parsing on semi-structured tables","authors":"Liang Pasupat","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Peters et al., 2017] Matthew E. Peters, Waleed Ammar, Chandra Bhagavatula, and R. Power. Semi-supervised se- quence tagging with bidirectional language models. In ACL, 2017.","title":"Semi-supervised sequence tagging with bidirectional language models","authors":"Matthew E Peters, Waleed Ammar, Chandra Bhagavatula, R Power","year":"2017","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Welbl et al., 2018] Johannes Welbl, Pontus Stenetorp, and Sebastian Riedel. Constructing datasets for multi-hop reading comprehension across documents. Transactions of the Association for Computational Linguistics, 6:287- 302, 2018.","title":"Constructing datasets for multi-hop reading comprehension across documents","authors":"Welbl","year":"2018","venue":"Transactions of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yang et al., 2018] Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. Hotpotqa: A dataset for di- verse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600, 2018.","title":"Hotpotqa: A dataset for diverse, explainable multi-hop question answering","authors":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, Christopher D Manning","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yu et al., 2018] Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, et al. Spider: A large-scale human-labeled dataset for complex and cross- domain semantic parsing and text-to-sql task. arXiv preprint arXiv:1809.08887, 2018.","title":"Spider: A large-scale human-labeled dataset for complex and crossdomain semantic parsing and text-to-sql task","authors":"Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhong et al., 2017] Victor Zhong, Caiming Xiong, and Richard Socher. Seq2sql: Generating structured queries from natural language using reinforcement learning. arXiv preprint arXiv:1709.00103, 2017.","title":"Seq2sql: Generating structured queries from natural language using reinforcement learning","authors":"Victor Zhong, Caiming Xiong, Richard Socher","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}