Scoring Multi-hop Question Decomposition Using Masked Language Models
Authors: 
Abdellah Hamouda Sidhoum, Mhamed Mataoui, Faouzi Sebbak, Adil Imad Eddine Hosni, Kamel SmailiAuthors Info & Claims
Abdellah Hamouda Sidhoum, Mhamed Mataoui, Faouzi Sebbak, Adil Imad Eddine Hosni, Kamel SmailiAuthors Info & ClaimsArticle No.: 107, Pages 1 - 21
Abstract
Question answering (QA) is a sub-field of Natural Language Processing (NLP) that focuses on developing systems capable of answering natural language queries. Within this domain, multi-hop question answering represents an advanced QA task that requires gathering and reasoning over multiple pieces of information from diverse sources or passages. To handle the complexity of multi-hop questions, question decomposition has been proven to be a valuable approach. This technique involves breaking down complex questions into simpler sub-questions, reducing the complexity of the problem. However, it’s worth noting that existing question decomposition methods often rely on training data, which may not always be readily available for low-resource languages or specialized domains. To address this issue, we propose a novel approach that utilizes pre-trained masked language models to score decomposition candidates in a zero-shot manner. The method involves generating decomposition candidates, scoring them using a pseudo-log likelihood estimation, and ranking them based on their scores. To evaluate the efficacy of the decomposition process, we conducted experiments on two datasets annotated on decomposition in two different languages, Arabic and English. Subsequently, we integrated our approach into a complete QA system and conducted a reading comprehension performance evaluation on the HotpotQA dataset. The obtained results emphasize that while the system exhibited a small drop in performance, it still maintained a significant advance compared to the baseline model. The proposed approach highlights the efficiency of the language model scoring technique in complex reasoning tasks such as multi-hop question decomposition.
References
[1]
Wissam Antoun, Fady Baly, and Hazem Hajj. 2020. AraBERT: Transformer-based model for arabic language understanding. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection. 9–15.
[2]
Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems, Curran Associates, Inc., 1877–1901. Retrieved from https://proceedings.neurips.cc/paper_files/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
[3]
Yu Cao, Meng Fang, and Dacheng Tao. 2019. BAG: Bi-directional attention entity graph convolutional network for multi-hop reasoning question answering. In Proceedings of the NAACL-HLT. 357–362.
[4]
Shih-Hsuan Chiu and Berlin Chen. 2021. Innovative BERT-based reranking language models for speech recognition. In Proceedings of the 2021 IEEE Spoken Language Technology Workshop. IEEE, 266–271.
[5]
Christopher Clark and Matt Gardner. 2018. Simple and effective multi-paragraph reading comprehension. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 845–855.
[6]
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 4171–4186.
[7]
Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, and Jie Tang. 2019. Cognitive graph for multi-hop reading comprehension at scale. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2694–2703.
[8]
Yuwei Fang, Siqi Sun, Zhe Gan, Rohit Pillai, Shuohang Wang, and Jingjing Liu. 2020. Hierarchical graph network for multi-hop question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 8823–8838.
[9]
Ruiliu Fu, Han Wang, Xuejun Zhang, Jun Zhou, and Yonghong Yan. 2021. Decomposing complex questions makes multi-hop QA easier and more interpretable. In Findings of the Association for Computational Linguistics: EMNLP 2021. 169–180.
[10]
Xiao-Yu Guo, Yuan Fang Li, and Gholamreza Haffari. 2022. Complex reading comprehension through question decomposition. In Proceedings of the The 20th Annual Workshop of the Australasian Language Technology Association. 31–40.
[11]
Abdellah Hamouda Sidhoum, M’hamed Mataoui, Faouzi Sebbak, and Kamel Smaïli. 2022. ACQAD: A dataset for arabic complex question answering. In Proceedings of the International Conference on Cyber Security, Artificial Intelligence and Theoretical Computer Science.
[12]
Viktor Hangya, Hossain Shaikh Saadi, and Alexander Fraser. 2022. Improving low-resource languages in pre-trained multilingual language models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 11993–12006.
[13]
Yongjie Huang and Meng Yang. 2021. Breadth first reasoning graph for multi-hop question answering. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 5810–5821.
[14]
Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. ALBERT: A lite BERT for self-supervised learning of language representations. In Proceedings of the International Conference on Learning Representations.
[15]
Nayeon Lee, Yejin Bang, Andrea Madotto, and Pascale Fung. 2021. Towards few-shot fact-checking via perplexity. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 1971–1981.
[16]
Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 7871–7880.
[17]
Hang Li. 2022. Learning to Rank for Information Retrieval and Natural Language Processing. Springer Nature.
[18]
Xin-Yi Li, Wei-Jun Lei, and Yu-Bin Yang. 2023. From easy to hard: Two-stage selector and reader for multi-hop question answering. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 1–5.
[19]
Christopher Malon and Bing Bai. 2020. Generating followup questions for interpretable multi-hop question answering. arXiv:2002.12344. Retrieved from https://arxiv.org/abs/2002.12344
[20]
Sewon Min, Victor Zhong, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2019. Multi-hop reading comprehension through question decomposition and rescoring. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 6097–6109.
[21]
OpenAI Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mo Bavarian, Jeff Belgum, Irwan Bello, Jake Berdine, Gabriel Bernadett-Shapiro, Christopher Berner, Lenny Bogdonoff, Oleg Boiko, Madelaine Boyd, Anna-Luisa Brakman, Greg Brockman, Tim Brooks, Miles Brundage, Kevin Button, Trevor Cai, Rosie Campbell, Andrew Cann, Brittany Carey, Chelsea Carlson, Rory Carmichael, Brooke Chan, Che Chang, Fotis Chantzis, Derek Chen, Sully Chen, Ruby Chen, Jason Chen, Mark Chen, Benjamin Chess, Chester Cho, Casey Chu, Hyung Won Chung, Dave Cummings, Jeremiah Currier, Yunxing Dai, Cory Decareaux, Thomas Degry, Noah Deutsch, Damien Deville, Arka Dhar, David Dohan, Steve Dowling, Sheila Dunning, Adrien Ecoffet, Atty Eleti, Tyna Eloundou, David Farhi, Liam Fedus, Niko Felix, Sim’on Posada Fishman, Juston Forte, Isabella Fulford, Leo Gao, Elie Georges, Christian Gibson, Vik Goel, Tarun Gogineni, Gabriel Goh, Raphael Gontijo-Lopes, Jonathan Gordon, Morgan Grafstein, Scott Gray, Ryan Greene, Joshua Gross, Shixiang Shane Gu, Yufei Guo, Chris Hallacy, Jesse Han, Jeff Harris, Yuchen He, Mike Heaton, Johannes Heidecke, Chris Hesse, Alan Hickey, Wade Hickey, Peter Hoeschele, Brandon Houghton, Kenny Hsu, Shengli Hu, Xin Hu, Joost Huizinga, Shantanu Jain, Shawn Jain, Joanne Jang, Angela Jiang, Roger Jiang, Haozhun Jin, Denny Jin, Shino Jomoto, Billie Jonn, Heewoo Jun, Tomer Kaftan, Lukasz Kaiser, Ali Kamali, Ingmar Kanitscheider, Nitish Shirish Keskar, Tabarak Khan, Logan Kilpatrick, Jong Wook Kim, Christina Kim, Yongjik Kim, Hendrik Kirchner, Jamie Ryan Kiros, Matthew Knight, Daniel Kokotajlo, Lukasz Kondraciuk, Andrew Kondrich, Aris Konstantinidis, Kyle Kosic, Gretchen Krueger, Vishal Kuo, Michael Lampe, Ikai Lan, Teddy Lee, Jan Leike, Jade Leung, Daniel Levy, Chak Ming Li, Rachel Lim, Molly Lin, Stephanie Lin, Mateusz Litwin, Theresa Lopez, Ryan Lowe, Patricia Lue, Anna Adeola Makanju, Kim Malfacini, Sam Manning, Todor Markov, Yaniv Markovski, Bianca Martin, Katie Mayer, Andrew Mayne, Bob McGrew, Scott Mayer McKinney, Christine McLeavey, Paul McMillan, Jake McNeil, David Medina, Aalok Mehta, Jacob Menick, Luke Metz, Andrey Mishchenko, Pamela Mishkin, Vinnie Monaco, Evan Morikawa, Daniel P. Mossing, Tong Mu, Mira Murati, Oleg Murk, David M’ely, Ashvin Nair, Reiichiro Nakano, Rajeev Nayak, Arvind Neelakantan, Richard Ngo, Hyeonwoo Noh, Ouyang Long, Cullen O’Keefe, Jakub W. Pachocki, Alex Paino, Joe Palermo, Ashley Pantuliano, Giambattista Parascandolo, Joel Parish, Emy Parparita, Alexandre Passos, Mikhail Pavlov, Andrew Peng, Adam Perelman, Filipe de Avila Belbute Peres, Michael Petrov, Henrique Pondé de Oliveira Pinto, Michael Pokorny, Michelle Pokrass, Vitchyr H. Pong, Tolly Powell, Alethea Power, Boris Power, Elizabeth Proehl, Raul Puri, Alec Radford, Jack Rae, Aditya Ramesh, Cameron Raymond, Francis Real, Kendra Rimbach, Carl Ross, Bob Rotsted, Henri Roussez, Nick Ryder, Mario D. Saltarelli, Ted Sanders, Shibani Santurkar, Girish Sastry, Heather Schmidt, David Schnurr, John Schulman, Daniel Selsam, Kyla Sheppard, Toki Sherbakov, Jessica Shieh, Sarah Shoker, Pranav Shyam, Szymon Sidor, Eric Sigler, Maddie Simens, Jordan Sitkin, Katarina Slama, Ian Sohl, Benjamin D. Sokolowsky, Yang Song, Natalie Staudacher, Felipe Petroski Such, Natalie Summers, Ilya Sutskever, Jie Tang, Nikolas A. Tezak, Madeleine Thompson, Phil Tillet, Amin Tootoonchian, Elizabeth Tseng, Preston Tuggle, Nick Turley, Jerry Tworek, Juan Felipe Cer’on Uribe, Andrea Vallone, Arun Vijayvergiya, Chelsea Voss, Carroll L. Wainwright, Justin Jay Wang, Alvin Wang, Ben Wang, Jonathan Ward, Jason Wei, C. J. Weinmann, Akila Welihinda, Peter Welinder, Jiayi Weng, Lilian Weng, Matt Wiethoff, Dave Willner, Clemens Winter, Samuel Wolrich, Hannah Wong, Lauren Workman, Sherwin Wu, Jeff Wu, Michael Wu, Kai Xiao, Tao Xu, Sarah Yoo, Kevin Yu, Qiming Yuan, Wojciech Zaremba, Rowan Zellers, Chong Zhang, Marvin Zhang, Shengjia Zhao, Tianhao Zheng, Juntang Zhuang, William Zhuk, and Barret Zoph. 2023. GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023).
[22]
Ethan Perez, Patrick Lewis, Wen-tau Yih, Kyunghyun Cho, and Douwe Kiela. 2020. Unsupervised question decomposition for question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 8864–8880.
[23]
Lin Qiu, Yunxuan Xiao, Yanru Qu, Hao Zhou, Lei Li, Weinan Zhang, and Yong Yu. 2019. Dynamically fused graph network for multi-hop reasoning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 6140–6150.
[24]
Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. (2018).
[25]
Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9.
[26]
Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research 21, 1 (2020), 5485–5551.
[27]
Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2383–2392.
[28]
Julian Salazar, Davis Liang, Toan Q. Nguyen, and Katrin Kirchhoff. 2020. Masked language model scoring. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2699–2712.
[29]
Tal Schuster, Ori Ram, Regina Barzilay, and Amir Globerson. 2019. Cross-lingual alignment of contextual word embeddings, with applications to zero-shot dependency parsing. In Proceedings of the NAACL-HLT. 1599–1613.
[30]
Joonbo Shin, Yoonhyung Lee, and Kyomin Jung. 2019. Effective sentence scoring method using bert for speech recognition. In Proceedings of the Asian Conference on Machine Learning. PMLR, 1081–1093.
[31]
Kaitao Song, Yichong Leng, Xu Tan, Yicheng Zou, Tao Qin, and Dongsheng Li. 2024. Transcormer: transformer for sentence scoring with sliding language modeling. In Proceedings of the 36th International Conference on Neural Information Processing Systems (NIPS’22), Curran Associates Inc., New Orleans, LA, USA.
[32]
Alon Talmor and Jonathan Berant. 2018. The web as a knowledge-base for answering complex questions. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 641–651.
[33]
Alexandre Tamborrino, Nicola Pellicanò, Baptiste Pannier, Pascal Voitot, and Louise Naudin. 2020. Pre-training Is (Almost) all you need: An application to commonsense reasoning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 3878–3887.
[34]
Ming Tu, Kevin Huang, Guangtao Wang, Jing Huang, Xiaodong He, and Bowen Zhou. 2020. Select, answer and explain: Interpretable multi-hop reading comprehension over multiple documents. In Proceedings of the AAAI Conference on Artificial Intelligence. 9073–9080.
[35]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17), Curran Associates Inc., Long Beach, California, USA, 6000–6010.
[36]
Alex Wang and Kyunghyun Cho. 2019. BERT has a mouth, and it must speak: BERT as a markov random field language model. In Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation. 30–36.
[37]
Yequan Wang, Jiawen Deng, Aixin Sun, and Xuying Meng. 2022. Perplexity from plm is unreliable for evaluating text quality. arXiv:2210.05892. Retrieved from https://arxiv.org/abs/2210.05892
[38]
Alex Warstadt, Alicia Parrish, Haokun Liu, Anhad Mohananey, Wei Peng, Sheng-Fu Wang, and Samuel R. Bowman. 2020. BLiMP: The benchmark of linguistic minimal pairs for English. Transactions of the Association for Computational Linguistics, Mark Johnson, Brian Roark, and Ani Nenkova (Eds.). Vol. 8, MIT Press, 377–392. https://aclanthology.org/2020.tacl-1.25
[39]
Bohong Wu, Zhuosheng Zhang, and Hai Zhao. 2021. Graph-free multi-hop reading comprehension: A select-to-guide strategy. arXiv:2107.11823. Retrieved from https://arxiv.org/abs/2107.11823
[40]
Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. HotpotQA: A dataset for diverse, explainable multi-hop question answering. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2369–2380.
[41]
Jiahao Zhang, Haiyang Zhang, Dongmei Zhang, Yong Liu, and Shen Huang. 2023. End-to-end beam retrieval for multi-hop question answering. arXiv preprint arXiv:2308.08973 (2023).
Index Terms
- Scoring Multi-hop Question Decomposition Using Masked Language Models
Recommendations
Bilingual Question Answering Using CINDI_QA at QA@CLEF 2007
Advances in Multilingual and Multimodal Information RetrievalThis article presents the first participation of the CINDI group in the Multiple Language Question Answering Cross Language Evaluation Forum (QA@CLEF). We participated in a track using French as source language and English as target language. CINDI_QA ...
Question answering using statistical language modelling
In this paper we present a statistical approach to question answering (QA). Our motivation is to build robust systems for many languages without the need for highly tuned linguistic modules. Consequently, word tokens and web data are used extensively but ...
BEDSpell: Spelling Error Correction Using BERT-Based Masked Language Model and Edit Distance
Service-Oriented Computing – ICSOC 2022 WorkshopsAbstractThe spelling correction problem, the task of automatically correcting misspellings in a text, is critical in natural language processing (NLP). Although it can be considered a standalone task, in most cases, it is an integral component of various ...
Comments
Information & Contributors
Information
Published In
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 19 July 2024
Online AM: 15 May 2024
Accepted: 09 May 2024
Revised: 08 February 2024
Received: 09 October 2023
Published in TALLIP Volume 23, Issue 7
Check for updates
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 195Total Downloads
- Downloads (Last 12 months)195
- Downloads (Last 6 weeks)16
Reflects downloads up to 02 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in