{"type":"ScholarlyArticle","title":"Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering","authors":[{"name":"Zhenyun Deng","slug":"zhenyun-deng","given":"Zhenyun","family":"Deng","affiliation":"School of Computer Science , University of Auckland , New Zealand"},{"name":"Yonghua Zhu","slug":"yonghua-zhu","given":"Yonghua","family":"Zhu","affiliation":"School of Computer Science , University of Auckland , New Zealand"},{"name":"Yang Chen","slug":"yang-chen","given":"Yang","family":"Chen","affiliation":"School of Computer Science , University of Auckland , New Zealand"},{"name":"Michael Witbrock","slug":"michael-witbrock","given":"Michael","family":"Witbrock","affiliation":"School of Computer Science , University of Auckland , New Zealand"},{"name":"Patricia Riddle","slug":"patricia-riddle","given":"Patricia","family":"Riddle","affiliation":"School of Computer Science , University of Auckland , New Zealand"}],"abstract":"Effective multi-hop question answering (QA) requires reasoning over multiple scattered paragraphs and providing explanations for answers. Most existing approaches cannot provide an interpretable reasoning process to illustrate how these models arrive at an answer. In this paper, we propose a Question Decomposition method based on Abstract Meaning Representation (QDAMR) for multi-hop QA, which achieves interpretable reasoning by decomposing a multi-hop question into simpler subquestions and answering them in order. Since annotating the decomposition is expensive, we first delegate the complexity of understanding the multi-hop question to an AMR parser. We then achieve decomposition of a multi-hop question via segmentation of the corresponding AMR graph based on the required reasoning type. Finally, we generate sub-questions using an AMR-to-Text generation model and answer them with an off-the-shelf QA model. Experimental results on HotpotQA demonstrate that our approach is competitive for interpretable reasoning and that the sub-questions generated by QDAMR are well-formed, outperforming existing question-decomposition-based multihop QA approaches.","doi":"10.24963/ijcai.2022/568","url":"https://ijcai.org/proceedings/2022/568","pdf":"https://ijcai.org/proceedings/2022/0568.pdf","markdown":"https://ijcai.org/proceedings/2022/568.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/568","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":568,"pages":{"first":4093,"last":4099},"keywords":["Natural Language Processing: Interpretability and Analysis of Models for NLP","Natural Language Processing: Language Generation","AI Ethics, Trust, Fairness: Explainability and Interpretability","Natural Language Processing: Question Answering","Data Mining: Mining Graphs"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987077","length_sec":76,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985220","length_sec":512,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Bevilacqua et al., 2021] Michele Bevilacqua, Rexhina Blloshmi, and Roberto Navigli. One spring to rule them both: Symmetric amr semantic parsing and generation without a complex pipeline. In Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021.","title":"One spring to rule them both: Symmetric amr semantic parsing and generation without a complex pipeline","authors":"Michele Bevilacqua, Rexhina Blloshmi, Roberto Navigli","year":"2021","venue":"Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cai and Lam, 2020] Deng Cai and Wai Lam. Amr pars- ing via graph-sequence iterative inference. arXiv preprint arXiv:2004.05572, 2020.","title":"Amr parsing via graph-sequence iterative inference","authors":"Lam ; ] Deng Cai, Wai Cai, Lam","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2020] Wenhu Chen, Hanwen Zha, Zhiyu Chen, Wen- han 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":"Wenhu Chen, Hanwen Zha, Zhiyu Chen, Wenhan Xiong, Hong Wang, William Wang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"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":5,"raw":"[Fang et al., 2019] Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pil- lai, 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":6,"raw":"[Faruqui and Das, 2018] Manaal Faruqui and Dipanjan Das. Iden- tifying well-formed natural language questions. arXiv preprint arXiv:1808.09419, 2018.","title":"Manaal Faruqui and Dipanjan Das. Identifying well-formed natural language questions","authors":"Das Faruqui","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hoang et al., 2021] Thanh Lam Hoang, Gabriele Picco, Yufang Hou, Young-Suk Lee, Lam Nguyen, Dzung Phan, Vanessa López, and Ramon Fernandez Astudillo. Ensembling graph pre- dictions for amr parsing. Advances in Neural Information Pro- cessing Systems, 34, 2021.","title":"Ensembling graph predictions for amr parsing","authors":"Thanh Lam Hoang, Gabriele Picco, Yufang Hou, Young-Suk Lee, Lam Nguyen, Dzung Phan, Vanessa López, Ramon Fernandez, Astudillo","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kapanipathi et al., 2021] Pavan Kapanipathi, Ibrahim Abde- laziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramón Fernandez Astudillo, Maria Chang, Cristina Cornelio, Saswati Dana, Achille Fokoue-Nkoutche, et al. Leveraging abstract meaning representation for knowledge base question answering. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3884-3894, 2021.","title":"Leveraging abstract meaning representation for knowledge base question answering","authors":"Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramón Fernandez Astudillo, Maria Chang, Cristina Cornelio, Saswati Dana, Achille Fokoue-Nkoutche","year":"2021","venue":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lewis et al., 2019] Mike Lewis, Yinhan Liu, Naman Goyal, Mar- jan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. Bart: Denoising sequence- to-sequence pre-training for natural language generation, trans- lation, and comprehension. arXiv preprint arXiv:1910.13461, 2019.","title":"Bart: Denoising sequenceto-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":10,"raw":"[Liao et al., 2018] Kexin Liao, Logan Lebanoff, and Fei Liu. Ab- stract meaning representation for multi-document summariza- tion. arXiv preprint arXiv:1806.05655, 2018.","title":"Abstract meaning representation for multi-document summarization","authors":"Kexin Liao, Logan Lebanoff, Fei Liu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Min et al., 2019] Sewon Min, Victor Zhong, Luke Zettlemoyer, and Hannaneh Hajishirzi. Multi-hop reading comprehension through question decomposition and rescoring. arXiv preprint arXiv:1906.02916, 2019.","title":"Multi-hop reading comprehension through question decomposition and rescoring","authors":"Sewon Min, Victor Zhong, Luke Zettlemoyer, Hannaneh Hajishirzi","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Mitra and Baral, 2016] Arindam Mitra and Chitta Baral. Ad- dressing a question answering challenge by combining statisti- cal methods with inductive rule learning and reasoning. In Dale Schuurmans and Michael P. Wellman, editors, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pages 2779- 2785, 2016.","title":"Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning","authors":"Mitra, Baral ;, Arindam Mitra, Chitta Baral","year":"2016","venue":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Pan et al., 2020] Liangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, and William Yang Wang. Unsupervised multi- hop question answering by question generation. arXiv preprint arXiv:2010.12623, 2020.","title":"Unsupervised multihop question answering by question generation","authors":"Pan","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Perez et al., 2020] Ethan Perez, Patrick S. H. Lewis, Wen-tau Yih, Kyunghyun Cho, and Douwe Kiela. Unsupervised question de- composition for question answering. In EMNLP, pages 8864- 8880, 2020.","title":"Unsupervised question decomposition for question answering","authors":"Ethan Perez, S H Patrick, Wen-Tau Lewis, Kyunghyun Yih, Douwe Cho, Kiela","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Qiu et al., 2019] Lin Qiu, Yunxuan Xiao, Yanru Qu, Hao Zhou, Lei Li, Weinan Zhang, and Yong Yu. Dynamically fused graph network for multi-hop reasoning. In Proceedings of the 57th An- nual Meeting of the Association for Computational Linguistics, pages 6140-6150, 2019.","title":"Dynamically fused graph network for multi-hop reasoning","authors":"Lin Qiu, Yunxuan Xiao, Yanru Qu, Hao Zhou, Lei Li, Weinan Zhang, Yong Yu","year":"2019","venue":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Radford et al., 2019] Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.","title":"Language models are unsupervised multitask learners","authors":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever","year":"2019","venue":"OpenAI blog","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Raffel et al., 2019] Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683, 2019.","title":"Exploring the limits of transfer learning with a unified text-to-text transformer","authors":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J Liu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"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":19,"raw":"[Rakshit and Flanigan, 2021] Geetanjali Rakshit and Jeffrey Flani- gan. Asq: Automatically generating question-answer pairs using amrs. arXiv preprint arXiv:2105.10023, 2021.","title":"Asq: Automatically generating question-answer pairs using amrs","authors":"Geetanjali Rakshit, Jeffrey Flanigan","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ribeiro et al., 2020] Leonardo FR Ribeiro, Martin Schmitt, Hin- rich Schütze, and Iryna Gurevych. Investigating pretrained language models for graph-to-text generation. arXiv preprint arXiv:2007.08426, 2020.","title":"Investigating pretrained language models for graph-to-text generation","authors":"Ribeiro","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ribeiro et al., 2021] Leonardo FR Ribeiro, Yue Zhang, and Iryna Gurevych. Structural adapters in pretrained language models for amr-to-text generation. arXiv preprint arXiv:2103.09120, 2021.","title":"Structural adapters in pretrained language models for amr-to-text generation","authors":"Ribeiro","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tu et al., 2020] Ming Tu, Kevin Huang, Guangtao Wang, Jing Huang, Xiaodong He, and Bowen Zhou. Select, answer and ex- plain: Interpretable multi-hop reading comprehension over mul- tiple documents. In The Thirty-Fourth AAAI Conference on Arti- ficial Intelligence, pages 9073-9080, 2020.","title":"Select, answer and explain: Interpretable multi-hop reading comprehension over multiple documents","authors":"Ming Tu, Kevin Huang, Guangtao Wang, Jing Huang, Xiaodong He, Bowen Zhou","year":"2020","venue":"The Thirty-Fourth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Xu et al., 2021] Weiwen Xu, Huihui Zhang, Deng Cai, and Wai Lam. Dynamic semantic graph construction and reasoning for explainable multi-hop science question answering. arXiv preprint arXiv:2105.11776, 2021.","title":"Dynamic semantic graph construction and reasoning for explainable multi-hop science question answering","authors":"Weiwen Xu, Huihui Zhang, Deng Cai, Wai Lam","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yang et al., 2018a] Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christo- pher D. Manning. HotpotQA: A dataset for diverse, explainable multi-hop question answering. In ACL, pages 2369-2380, 2018.","title":"HotpotQA: A dataset for diverse, explainable multi-hop question answering","authors":"Yang","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yang et al., 2018b] Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. Hotpotqa: A dataset for diverse, ex- plainable multi-hop question answering. In EMNLP, pages 2369- 2380, 2018.","title":"Hotpotqa: A dataset for diverse, explainable multi-hop question answering","authors":"Yang","year":"2018","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhu et al., 2021] Yunchang Zhu, Liang Pang, Yanyan Lan, Huawei Shen, and Xueqi Cheng. Adaptive information seeking for open- domain question answering. arXiv preprint arXiv:2109.06747, 2021.","title":"Adaptive information seeking for opendomain question answering","authors":"Yunchang Zhu, Liang Pang, Yanyan Lan, Huawei Shen, Xueqi Cheng","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}