{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:44:25Z","timestamp":1779101065064,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,3,8]],"date-time":"2021-03-08T00:00:00Z","timestamp":1615161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["832921 and 871042"],"award-info":[{"award-number":["832921 and 871042"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,3,8]]},"DOI":"10.1145\/3437963.3441758","type":"proceedings-article","created":{"date-parts":[[2021,3,6]],"date-time":"2021-03-06T04:36:17Z","timestamp":1615005377000},"page":"418-426","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":34,"title":["Explain and Predict, and then Predict Again"],"prefix":"10.1145","author":[{"given":"Zijian","family":"Zhang","sequence":"first","affiliation":[{"name":"L3S Research Center, Hannover, Germany"}]},{"given":"Koustav","family":"Rudra","sequence":"additional","affiliation":[{"name":"L3S Research Center, Hannover, Germany"}]},{"given":"Avishek","family":"Anand","sequence":"additional","affiliation":[{"name":"L3S Research Center, Hannover, Germany"}]}],"member":"320","published-online":{"date-parts":[[2021,3,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"karpathy2015visualizingJ. Johnson A. Karpathy and F. Li. 2015. Visualizing and understanding recurrent networks. arXiv preprint arXiv:1506.02078.  karpathy2015visualizingJ. Johnson A. Karpathy and F. Li. 2015. Visualizing and understanding recurrent networks. arXiv preprint arXiv:1506.02078."},{"key":"e_1_3_2_1_2_1","first-page":"2963","volume-title":"Proc. ACL","author":"Bastings J.","unstructured":"bastings2019interpretable J. Bastings , W. Aziz , and I. Titov . 2019. Interpretable neural predictions with differentiable binary variables . In Proc. ACL , pages 2963 -- 2977 . bastings2019interpretableJ. Bastings, W. Aziz, and I. Titov. 2019. Interpretable neural predictions with differentiable binary variables. In Proc. ACL, pages 2963--2977."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"caruana1997multitaskRich Caruana. 1997. Multitask learning. Machine learning 28(1):41--75.  caruana1997multitaskRich Caruana. 1997. Multitask learning. Machine learning 28(1):41--75.","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_3_2_1_5_1","first-page":"593","volume-title":"Proc. ACL","author":"Cui Y.","unstructured":"cui2016attention Y. Cui , Z. Chen , S. Wei , S. Wang , T. Liu , and G. Hu . 2017. Attention-over-attention neural networks for reading comprehension . In Proc. ACL , pages 593 -- 602 . cui2016attentionY. Cui, Z. Chen, S. Wei, S. Wang, T. Liu, and G. Hu. 2017. Attention-over-attention neural networks for reading comprehension. In Proc. ACL, pages 593--602."},{"key":"e_1_3_2_1_6_1","first-page":"4171","volume-title":"Proc. NAACL-HLT","author":"Devlin J.","unstructured":"devlin2018bert J. Devlin , M. Chang , K. Lee , and K. Toutanova . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding . In Proc. NAACL-HLT , pages 4171 -- 4186 . devlin2018bertJ. Devlin, M. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proc. NAACL-HLT, pages 4171--4186."},{"key":"e_1_3_2_1_7_1","first-page":"4443","volume-title":"Proc. ACL","author":"DeYoung J.","unstructured":"deyoung2019eraser J. DeYoung , S. Jain , N. F. Rajani , E. Lehman , C. Xiong , R. Socher , and B. C. Wallace . 2020. ERASER: A benchmark to evaluate rationalized NLP models . In Proc. ACL , pages 4443 -- 4458 . deyoung2019eraserJ. DeYoung, S. Jain, N. F. Rajani, E. Lehman, C. Xiong, R. Socher, and B. C. Wallace. 2020. ERASER: A benchmark to evaluate rationalized NLP models. In Proc. ACL, pages 4443--4458."},{"key":"e_1_3_2_1_8_1","first-page":"2736","volume-title":"The World Wide Web Conference","author":"Fetahu B.","unstructured":"fetahu2019tablenet B. Fetahu , A. Anand , and M. Koutraki . 2019. Tablenet: An approach for determining fine-grained relations for wikipedia tables . In The World Wide Web Conference , pages 2736 -- 2742 . fetahu2019tablenetB. Fetahu, A. Anand, and M. Koutraki. 2019. Tablenet: An approach for determining fine-grained relations for wikipedia tables. In The World Wide Web Conference, pages 2736--2742."},{"key":"e_1_3_2_1_9_1","first-page":"190","volume-title":"Advances in Neural Information Processing Systems 26","author":"Hermans M.","unstructured":"NIPS2013_5166 M. Hermans and B. Schrauwen . 2013. Training and analysing deep recurrent neural networks. In M. Welling C. J. C. Burges, L. Bottou, Z. Ghahramani, and K. Q. Weinberger, editors , Advances in Neural Information Processing Systems 26 , pages 190 -- 198 . NIPS2013_5166M. Hermans and B. Schrauwen. 2013. Training and analysing deep recurrent neural networks. In M. Welling C. J. C. Burges, L. Bottou, Z. Ghahramani, and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems 26, pages 190--198."},{"key":"e_1_3_2_1_10_1","first-page":"289","volume-title":"Proceedings of the 2017 ACM on Web Science Conference","author":"Holzmann H.","unstructured":"holzmann2017exploring H. Holzmann , W. Nejdl , and A. Anand . 2017. Exploring web archives through temporal anchor texts . In Proceedings of the 2017 ACM on Web Science Conference , pages 289 -- 298 . holzmann2017exploringH. Holzmann, W. Nejdl, and A. Anand. 2017. Exploring web archives through temporal anchor texts. In Proceedings of the 2017 ACM on Web Science Conference, pages 289--298."},{"key":"e_1_3_2_1_11_1","first-page":"551","volume-title":"Proc. EMNLP","author":"Cheng L.","unstructured":"cheng2016long L. Dong J. Cheng and M. Lapata . 2016. Long short-term memory-networks for machine reading . In Proc. EMNLP , pages 551 -- 561 . cheng2016longL. Dong J. Cheng and M. Lapata. 2016. Long short-term memory-networks for machine reading. In Proc. EMNLP, pages 551--561."},{"key":"e_1_3_2_1_12_1","first-page":"11","volume-title":"Attention is not explanation","author":"Wallace C","unstructured":"jain2019attentionSarthak Jain and Byron C Wallace . 2019. Attention is not explanation . pages 11 -- 20 . jain2019attentionSarthak Jain and Byron C Wallace. 2019. Attention is not explanation. pages 11--20."},{"key":"e_1_3_2_1_13_1","first-page":"252","volume-title":"Proc. NAACL-HLT","author":"Khashabi D.","unstructured":"khashabi2018looking D. Khashabi , S. Chaturvedi , M. Roth , S. Upadhyay , and D. Roth . 2018. Looking beyond the surface: A challenge set for reading comprehension over multiple sentences . In Proc. NAACL-HLT , pages 252 -- 262 . khashabi2018lookingD. Khashabi, S. Chaturvedi, M. Roth, S. Upadhyay, and D. Roth. 2018. Looking beyond the surface: A challenge set for reading comprehension over multiple sentences. In Proc. NAACL-HLT, pages 252--262."},{"key":"e_1_3_2_1_14_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings.","author":"Kingma D.","unstructured":"kingma2014adam D. Kingma and J. Ba . 2015. Adam: A method for stochastic optimization . In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings. kingma2014adamD. Kingma and J. Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings."},{"key":"e_1_3_2_1_15_1","first-page":"1885","volume-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70","author":"Koh P. W.","unstructured":"koh2017understanding P. W. Koh and P. Liang . 2017. Understanding black-box predictions via influence functions . In Proceedings of the 34th International Conference on Machine Learning-Volume 70 , pages 1885 -- 1894 . koh2017understandingP. W. Koh and P. Liang. 2017. Understanding black-box predictions via influence functions. In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pages 1885--1894."},{"key":"e_1_3_2_1_16_1","unstructured":"lage2019evaluationI. Lage E. Chen J. He M. Narayanan S. Gershman B. Kim and F. Doshi-Velez. 2018. An evaluation of the human-interpretability of explanation.  lage2019evaluationI. Lage E. Chen J. He M. Narayanan S. Gershman B. Kim and F. Doshi-Velez. 2018. An evaluation of the human-interpretability of explanation."},{"key":"e_1_3_2_1_17_1","first-page":"3705","volume-title":"Proc. NAACL","author":"Lehman E.","unstructured":"lehman2019inferring E. Lehman , J. DeYoung , R. Barzilay , and B. C. Wallace . 2019. Inferring which medical treatments work from reports of clinical trials . In Proc. NAACL , pages 3705 -- 3717 . lehman2019inferringE. Lehman, J. DeYoung, R. Barzilay, and B. C. Wallace. 2019. Inferring which medical treatments work from reports of clinical trials. In Proc. NAACL, pages 3705--3717."},{"key":"e_1_3_2_1_18_1","first-page":"107","volume-title":"Proc. EMNLP","author":"Lei T.","unstructured":"lei2016rationalizing T. Lei , R. Barzilay , and T. Jaakkola . 2016. Rationalizing neural predictions . In Proc. EMNLP , pages 107 -- 117 . lei2016rationalizingT. Lei, R. Barzilay, and T. Jaakkola. 2016. Rationalizing neural predictions. In Proc. EMNLP, pages 107--117."},{"key":"e_1_3_2_1_19_1","unstructured":"li2016understandingJ. Li W. Monroe and D. Jurafsky. 2016. Understanding neural networks through representation erasure. arXiv preprint arXiv:1612.08220.  li2016understandingJ. Li W. Monroe and D. Jurafsky. 2016. Understanding neural networks through representation erasure. arXiv preprint arXiv:1612.08220."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"liu2017entityZ. Liu M. Yang X. Wang Q. Chen B. Tang Z. Wang and H. Xu. 2017. Entity recognition from clinical texts via recurrent neural network. BMC medical informatics and decision making 17(2):67.  liu2017entityZ. Liu M. Yang X. Wang Q. Chen B. Tang Z. Wang and H. Xu. 2017. Entity recognition from clinical texts via recurrent neural network. BMC medical informatics and decision making 17(2):67.","DOI":"10.1186\/s12911-017-0468-7"},{"key":"e_1_3_2_1_21_1","unstructured":"lundberg2017unifiedS. Lundberg and S. Lee. 2017. A unified approach to interpreting model predictions. In Advances in neural information processing systems pages 4765--4774.  lundberg2017unifiedS. Lundberg and S. Lee. 2017. A unified approach to interpreting model predictions. In Advances in neural information processing systems pages 4765--4774."},{"key":"e_1_3_2_1_22_1","first-page":"1614","volume-title":"International Conference on Machine Learning","author":"Martins A.","unstructured":"martins2016softmax A. Martins and R. Astudillo . 2016. From softmax to sparsemax: A sparse model of attention and multi-label classification . In International Conference on Machine Learning , pages 1614 -- 1623 . martins2016softmaxA. Martins and R. Astudillo. 2016. From softmax to sparsemax: A sparse model of attention and multi-label classification. In International Conference on Machine Learning, pages 1614--1623."},{"key":"e_1_3_2_1_23_1","first-page":"271","volume-title":"Proceedings of the 42nd annual meeting on Association for Computational Linguistics","author":"Pang B.","unstructured":"pang2004sentimental B. Pang and L. Lee . 2004. A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts . In Proceedings of the 42nd annual meeting on Association for Computational Linguistics , page 271 . pang2004sentimentalB. Pang and L. Lee. 2004. A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. In Proceedings of the 42nd annual meeting on Association for Computational Linguistics, page 271."},{"key":"e_1_3_2_1_24_1","volume-title":"Proc. EMNLP.","author":"Petroni F.","unstructured":"hel, Lewis, Bakhtin, Wu, Miller, and Riedel]petroni2019language F. Petroni , T. Rockt\"aschel, P. Lewis , A. Bakhtin , Y. Wu , A. H. Miller , and S. Riedel . 2019. Language models as knowledge bases? In Proc. EMNLP. hel, Lewis, Bakhtin, Wu, Miller, and Riedel]petroni2019languageF. Petroni, T. Rockt\"aschel, P. Lewis, A. Bakhtin, Y. Wu, A. H. Miller, and S. Riedel. 2019. Language models as knowledge bases? In Proc. EMNLP."},{"key":"e_1_3_2_1_25_1","first-page":"1135","volume-title":"Proc. SIGKDD","author":"Ribeiro M. T.","unstructured":"ribeiro2016should:lime M. T. Ribeiro , S. Singh , and C. Guestrin . 2016. Why should i trust you?: Explaining the predictions of any classifier . In Proc. SIGKDD , pages 1135 -- 1144 . ribeiro2016should:limeM. T. Ribeiro, S. Singh, and C. Guestrin. 2016. Why should i trust you?: Explaining the predictions of any classifier. In Proc. SIGKDD, pages 1135--1144."},{"key":"e_1_3_2_1_26_1","first-page":"2662","volume-title":"Proc. IJCAI","author":"Ross A. S.","unstructured":"ross:17:right A. S. Ross , M. C. Hughes , and F. Doshi-Velez . 2017. Right for the right reasons: Training differentiable models by constraining their explanations . In Proc. IJCAI , pages 2662 -- 2670 . ross:17:rightA. S. Ross, M. C. Hughes, and F. Doshi-Velez. 2017. Right for the right reasons: Training differentiable models by constraining their explanations. In Proc. IJCAI, pages 2662--2670."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"e_1_3_2_1_28_1","first-page":"618","volume-title":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","author":"Singh J.","unstructured":"singh2020model J. Singh and A. Anand . 2020. Model agnostic interpretability of rankers via intent modelling . In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency , pages 618 -- 628 . singh2020modelJ. Singh and A. Anand. 2020. Model agnostic interpretability of rankers via intent modelling. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pages 618--628."},{"key":"e_1_3_2_1_29_1","first-page":"1105","volume-title":"Proc. SIGIR","author":"Singh J.","unstructured":"singh2016expedition J. Singh , W. Nejdl , and A. Anand . 2016. Expedition: a time-aware exploratory search system designed for scholars . In Proc. SIGIR , pages 1105 -- 1108 . singh2016expeditionJ. Singh, W. Nejdl, and A. Anand. 2016. Expedition: a time-aware exploratory search system designed for scholars. In Proc. SIGIR, pages 1105--1108."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"strout2019humanJ. Strout Y. Zhang and R. Mooney. 2019. Do human rationales improve machine explanations? pages 56--62.  strout2019humanJ. Strout Y. Zhang and R. Mooney. 2019. Do human rationales improve machine explanations? pages 56--62.","DOI":"10.18653\/v1\/W19-4807"},{"key":"e_1_3_2_1_31_1","volume-title":"Proc. NAACL-HLT.","year":"2018","unstructured":"Thorne18FeverJames Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018 . FEVER: a large-scale dataset for fact extraction and VERification . In Proc. NAACL-HLT. Thorne18FeverJames Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. In Proc. NAACL-HLT."},{"key":"e_1_3_2_1_32_1","first-page":"11","volume-title":"Proc. EMNLP-IJCNLP","author":"Wiegreffe S.","unstructured":"wiegreffe2019attention S. Wiegreffe and Y. Pinter . 2019. Attention is not not explanation . In Proc. EMNLP-IJCNLP , pages 11 -- 20 . wiegreffe2019attentionS. Wiegreffe and Y. Pinter. 2019. Attention is not not explanation. In Proc. EMNLP-IJCNLP, pages 11--20."},{"key":"e_1_3_2_1_33_1","first-page":"2048","volume-title":"International conference on machine learning","author":"Xu K.","unstructured":"xu2015show K. Xu , J. Ba , R. Kiros , K. Cho , A. Courville , R. Salakhudinov , R. Zemel , and Y. Bengio . 2015. Show, attend and tell: Neural image caption generation with visual attention . In International conference on machine learning , pages 2048 -- 2057 . xu2015showK. Xu, J. Ba, R. Kiros, K. Cho, A. Courville, R. Salakhudinov, R. Zemel, and Y. Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning, pages 2048--2057."},{"key":"e_1_3_2_1_34_1","first-page":"1480","volume-title":"Proc. NAACL-HLT","author":"Yang Z.","unstructured":"yang2016hierarchical Z. Yang , D. Yang , C. Dyer , X. He , A. Smola , and E. Hovy . 2016. Hierarchical attention networks for document classification . In Proc. NAACL-HLT , pages 1480 -- 1489 . yang2016hierarchicalZ. Yang, D. Yang, C. Dyer, X. He, A. Smola, and E. Hovy. 2016. Hierarchical attention networks for document classification. In Proc. NAACL-HLT, pages 1480--1489."},{"key":"e_1_3_2_1_35_1","volume-title":"Proc. ICLR.","author":"Yoon J.","unstructured":"yoon2018:invase J. Yoon , J. Jordon , and M. van der Schaar. 2019. INVASE: Instance-wise variable selection using neural networks . In Proc. ICLR. yoon2018:invaseJ. Yoon, J. Jordon, and M. van der Schaar. 2019. INVASE: Instance-wise variable selection using neural networks. In Proc. ICLR."},{"key":"e_1_3_2_1_36_1","volume-title":"Proc. NAACL.","author":"Zaidan O.","unstructured":"zaidan2007using O. Zaidan , J. Eisner , and C. Piatko . 2007. Using ?annotator rationales? to improve machine learning for text categorization . In Proc. NAACL. zaidan2007usingO. Zaidan, J. Eisner, and C. Piatko. 2007. Using ?annotator rationales? to improve machine learning for text categorization. In Proc. NAACL."},{"key":"e_1_3_2_1_37_1","first-page":"31","volume-title":"Proc. EMNLP","author":"Zaidan O. F.","unstructured":"zaidan2008modeling O. F. Zaidan and J. Eisner . 2008. Modeling annotators: A generative approach to learning from annotator rationales . In Proc. EMNLP , pages 31 -- 40 . zaidan2008modelingO. F. Zaidan and J. Eisner. 2008. Modeling annotators: A generative approach to learning from annotator rationales. In Proc. EMNLP, pages 31--40."},{"key":"e_1_3_2_1_38_1","first-page":"795","volume-title":"Proc. EMNLP","volume":"2016","author":"Zhang Y.","unstructured":"zhang2016rationale Y. Zhang , I. Marshall , and B. C. Wallace . 2016. Rationale-augmented convolutional neural networks for text classification . In Proc. EMNLP , volume 2016 , page 795 . zhang2016rationaleY. Zhang, I. Marshall, and B. C. Wallace. 2016. Rationale-augmented convolutional neural networks for text classification. In Proc. EMNLP, volume 2016, page 795."},{"key":"e_1_3_2_1_39_1","first-page":"153","volume-title":"Proc. CSCW","author":"Zhang Z.","unstructured":"dissonance19:anand Z. Zhang , J. Singh , U. gadiraju, and A. Anand . 2019. Dissonance between human and machine understanding . In Proc. CSCW , pages 153 -- 168 . dissonance19:anandZ. Zhang, J. Singh, U. gadiraju, and A. Anand. 2019. Dissonance between human and machine understanding. In Proc. CSCW, pages 153--168."},{"key":"e_1_3_2_1_40_1","unstructured":"zhong2019fineR. Zhong S. Shao and K. McKeown. 2019. Fine-grained sentiment analysis with faithful attention. arXiv preprint arXiv:1908.06870.  zhong2019fineR. Zhong S. Shao and K. McKeown. 2019. Fine-grained sentiment analysis with faithful attention. arXiv preprint arXiv:1908.06870."}],"event":{"name":"WSDM '21: The Fourteenth ACM International Conference on Web Search and Data Mining","location":"Virtual Event Israel","acronym":"WSDM '21","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 14th ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3437963.3441758","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3437963.3441758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:35Z","timestamp":1750193255000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3437963.3441758"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,8]]},"references-count":40,"alternative-id":["10.1145\/3437963.3441758","10.1145\/3437963"],"URL":"https:\/\/doi.org\/10.1145\/3437963.3441758","relation":{},"subject":[],"published":{"date-parts":[[2021,3,8]]},"assertion":[{"value":"2021-03-08","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}