{"type":"ScholarlyArticle","title":"Learning by Interpreting","authors":[{"name":"Xuting Tang","slug":"xuting-tang","given":"Xuting","family":"Tang","affiliation":"Institute of Technology"},{"name":"Abdul Rafae Khan","slug":"abdul-rafae-khan","given":"Abdul Rafae","family":"Khan","affiliation":"Institute of Technology"},{"name":"Shusen Wang","slug":"shusen-wang","given":"Shusen","family":"Wang","affiliation":"Xiaohongshu Inc"},{"name":"Jia Xu","slug":"jia-xu","given":"Jia","family":"Xu","affiliation":"Institute of Technology"}],"abstract":"This paper introduces a novel way of enhancing NLP prediction accuracy by incorporating model interpretation insights. Conventional efforts often focus on balancing the trade-offs between accuracy and interpretability, for instance, sacrificing model performance to increase the explainability. Here, we take a unique approach and show that model interpretation can ultimately help improve NLP quality. Specifically, we employ our learned interpretability results using attention mechanisms, LIME, and SHAP to train our model. We demonstrate a significant increase in accuracy of up to +3.4  BLEU points on NMT and up to +4.8 points on GLUE tasks, verifying our hypothesis that it is possible to achieve better model learning by incorporating model interpretation knowledge.","doi":"10.24963/ijcai.2022/609","url":"https://ijcai.org/proceedings/2022/609","pdf":"https://ijcai.org/proceedings/2022/0609.pdf","markdown":"https://ijcai.org/proceedings/2022/609.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/609","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":609,"pages":{"first":4390,"last":4396},"keywords":["Machine Learning: Explainable/Interpretable Machine Learning","AI Ethics, Trust, Fairness: Explainability and Interpretability","Machine Learning: Attention Models","Natural Language Processing: Interpretability and Analysis of Models for NLP"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986883","length_sec":81,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985026","length_sec":341,"provider":"slideslive"}],"references":[{"position":1,"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 Proceedings of NAACL-HLT, pages 4171-4186, Minneapolis, Minnesota, June 2019. Association for Com- putational Linguistics.","title":"BERT: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2019","venue":"Proceedings of NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Du et al., 2019] Mengnan Du, Ninghao Liu, and Xia Hu. Techniques for interpretable machine learning. Commu- nications of the ACM, 63(1):68-77, 2019.","title":"Techniques for interpretable machine learning","authors":"Du","year":"2019","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Gehring et al., 2017] Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, and Yann N Dauphin. Con- volutional sequence to sequence learning. In Interna- tional Conference on Machine Learning, pages 1243- 1252. PMLR, 2017.","title":"Convolutional sequence to sequence learning","authors":"Gehring","year":"2017","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gomez et al., 2021] Tristan Gomez, Suiyi Ling, Thomas Fréour, and Harold Mouchère. Improve the inter- pretability of attention: A fast, accurate, and inter- pretable high-resolution attention model. arXiv preprint arXiv:2106.02566, 2021.","title":"Improve the interpretability of attention: A fast, accurate, and interpretable high-resolution attention model","authors":"Gomez","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Jacovi and Goldberg, 2020] Alon Jacovi and Yoav Gold- berg. Towards faithfully interpretable nlp systems: How should we define and evaluate faithfulness? arXiv preprint arXiv:2004.03685, 2020.","title":"Alon Jacovi and Yoav Goldberg","authors":"Goldberg Jacovi","year":"2020","venue":"Towards faithfully interpretable nlp systems: How should we define and evaluate faithfulness","doi":null,"url":null,"internal_url":null},{"position":6,"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":7,"raw":"[Koehn et al., 2007] Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, et al. Moses: Open source toolkit for sta- tistical machine translation. In Proceedings of the 45th annual meeting of the association for computational lin- guistics companion volume proceedings of the demo and poster sessions, pages 177-180, 2007.","title":"Moses: Open source toolkit for statistical machine translation","authors":"Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens","year":"2007","venue":"Proceedings of the 45th annual meeting of the association for computational linguistics companion volume proceedings of the demo and poster sessions","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Li et al., 2020] Jierui Li, Lemao Liu, Huayang Li, Guanlin Li, Guoping Huang, and Shuming Shi. Evaluating ex- planation methods for neural machine translation. arXiv preprint arXiv:2005.01672, 2020.","title":"Evaluating explanation methods for neural machine translation","authors":"Li","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Li et al., 2021] Xuhong Li, Haoyi Xiong, Xingjian Li, Xu- anyu Wu, Xiao Zhang, Ji Liu, Jiang Bian, and Dejing Dou. Interpretable deep learning: Interpretation, inter- pretability, trustworthiness, and beyond. arXiv preprint arXiv:2103.10689, 2021.","title":"Interpretable deep learning: Interpretation, interpretability, trustworthiness, and beyond","authors":"Xuhong Li, Haoyi Xiong, Xingjian Li, Xuanyu Wu, Xiao Zhang, Ji Liu, Jiang Bian, Dejing Dou","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lundberg and Lee, 2017] Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fer- gus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems 30, pages 4765- 4774.","title":"A unified approach to interpreting model predictions","authors":"M Scott, Su-In Lundberg, Lee","year":null,"venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"Curran Associates, Inc., 2017.","title":null,"authors":"Curran Associates, Inc","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Murdoch et al., 2019] W James Murdoch, Chandan Singh, Karl Kumbier, Reza Abbasi-Asl, and Bin Yu. Definitions, methods, and applications in interpretable machine learn- ing. Proceedings of the National Academy of Sciences, 116(44):22071-22080, 2019.","title":"Definitions, methods, and applications in interpretable machine learning","authors":"Murdoch","year":"2019","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ott et al., 2019] Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, and Michael Auli. fairseq: A fast, extensible toolkit for se- quence modeling. In Proceedings of NAACL-HLT 2019: Demonstrations, 2019.","title":"fairseq: A fast, extensible toolkit for sequence modeling","authors":"Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, Michael Auli","year":"2019","venue":"Proceedings of NAACL-HLT 2019: Demonstrations","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Post, 2018] Matt Post. A call for clarity in reporting BLEU scores. In Proceedings of the Third Conference on Ma- chine Translation: Research Papers, pages 186-191, Bel- gium, Brussels, October 2018. Association for Computa- tional Linguistics.","title":"A call for clarity in reporting BLEU scores","authors":"Matt Post","year":"2018","venue":"Proceedings of the Third Conference on Machine Translation: Research Papers","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ribeiro et al., 2016] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. \" why should i trust you?\" explain- ing the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowl- edge discovery and data mining, pages 1135-1144, 2016.","title":"why should i trust you?\" explaining the predictions of any classifier","authors":"Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2016","venue":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Sennrich and Haddow, 2016] Rico Sennrich and Barry Had- dow. Linguistic input features improve neural machine translation. arXiv preprint arXiv:1606.02892, 2016.","title":"Rico Sennrich and Barry Haddow. Linguistic input features improve neural machine translation","authors":"Haddow Sennrich","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Sennrich et al., 2015] Rico Sennrich, Barry Haddow, and Alexandra Birch. Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909, 2015.","title":"Neural machine translation of rare words with subword units","authors":"Sennrich","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Serrano and Smith, 2019] Sofia Serrano and Noah A Smith. Is attention interpretable? arXiv preprint arXiv:1906.03731, 2019.","title":"Is attention interpretable","authors":"Smith ; Serrano, Sofia Serrano, Noah A Smith","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Advances in neural information processing sys- tems, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, Illia Polosukhin","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Wang et al., 2018] Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R Bow- man. Glue: A multi-task benchmark and analysis plat- form for natural language understanding. arXiv preprint arXiv:1804.07461, 2018.","title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","authors":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, Samuel R Bowman","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wolf et al., 2020] Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Fun- towicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. Transformers: State-of- the-art natural language processing. In Proceedings of EMNLP: System Demonstrations, pages 38-45, Online, October 2020. Association for Computational Linguistics.","title":"Transformers: State-ofthe-art natural language processing","authors":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Clara Patrick Von Platen, Yacine Ma, Julien Jernite, Canwen Plu, Teven Xu, Sylvain Le Scao, Mariama Gugger, Quentin Drame, Alexander M Lhoest, Rush","year":"2020","venue":"Proceedings of EMNLP: System Demonstrations","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}