{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T09:24:26Z","timestamp":1743067466798,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819981830"},{"type":"electronic","value":"9789819981847"}],"license":[{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8184-7_5","type":"book-chapter","created":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T07:02:41Z","timestamp":1700895761000},"page":"54-66","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Can You Really Reason: A Novel Framework for\u00a0Assessing Natural Language Reasoning Datasets and\u00a0Models"],"prefix":"10.1007","author":[{"given":"Shanshan","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,26]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Bowman, S., Angeli, G., Potts, C., Manning, C.D.: A large annotated corpus for learning natural language inference. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 632\u2013642 (2015)","DOI":"10.18653\/v1\/D15-1075"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Clark, C., Yatskar, M., Zettlemoyer, L.: Don\u2019t take the easy way out: ensemble based methods for avoiding known dataset biases. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 4060\u20134073 (2019)","DOI":"10.18653\/v1\/D19-1418"},{"key":"5_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Gururangan, S., Swayamdipta, S., Levy, O., Schwartz, R., Bowman, S., Smith, N.A.: Annotation artifacts in natural language inference data. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 2 (Short Papers), pp. 107\u2013112 (2018)","DOI":"10.18653\/v1\/N18-2017"},{"key":"5_CR5","first-page":"132","volume":"2019","author":"H He","year":"2019","unstructured":"He, H., Zha, S., Wang, H.: Unlearn dataset bias in natural language inference by fitting the residual. EMNLP-IJCNLP 2019, 132 (2019)","journal-title":"EMNLP-IJCNLP"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Lai, G., Xie, Q., Liu, H., Yang, Y., Hovy, E.: RACE: large-scale reading comprehension dataset from examinations. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 785\u2013794 (2017)","DOI":"10.18653\/v1\/D17-1082"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Lowe, R., Pow, N., Serban, I.V., Pineau, J.: The ubuntu dialogue corpus: a large dataset for research in unstructured multi-turn dialogue systems. In: Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 285\u2013294 (2015)","DOI":"10.18653\/v1\/W15-4640"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"McCoy, T., Pavlick, E., Linzen, T.: Right for the wrong reasons: diagnosing syntactic heuristics in natural language inference. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 3428\u20133448 (2019)","DOI":"10.18653\/v1\/P19-1334"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Mostafazadeh, N., et al.: A corpus and cloze evaluation for deeper understanding of commonsense stories. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 839\u2013849 (2016)","DOI":"10.18653\/v1\/N16-1098"},{"key":"5_CR10","unstructured":"Naik, A., Ravichander, A., Sadeh, N., Rose, C., Neubig, G.: Stress test evaluation for natural language inference. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 2340\u20132353 (2018)"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Niven, T., Kao, H.Y.: Probing neural network comprehension of natural language arguments. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4658\u20134664 (2019)","DOI":"10.18653\/v1\/P19-1459"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Poliak, A., Naradowsky, J., Haldar, A., Rudinger, R., Van Durme, B.: Hypothesis only baselines in natural language inference. In: Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, pp. 180\u2013191 (2018)","DOI":"10.18653\/v1\/S18-2023"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Wu, T., Guestrin, C., Singh, S.: Beyond accuracy: Behavioral testing of NLP models with checklist. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5\u201310, 2020, pp. 4902\u20134912 (2020)","DOI":"10.18653\/v1\/2020.acl-main.442"},{"key":"5_CR14","unstructured":"Roemmele, M., Bejan, C.A., Gordon, A.S.: Choice of plausible alternatives: an evaluation of commonsense causal reasoning. In: 2011 AAAI Spring Symposium Series (2011)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Sanchez, I., Mitchell, J., Riedel, S.: Behavior analysis of NLI models: Uncovering the influence of three factors on robustness. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long Papers), pp. 1975\u20131985 (2018)","DOI":"10.18653\/v1\/N18-1179"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Schuster, T., Shah, D.J., Yeo, Y.J.S., Filizzola, D., Santus, E., Barzilay, R.: Towards debiasing fact verification models. arXiv preprint arXiv:1908.05267 (2019)","DOI":"10.18653\/v1\/D19-1341"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Sharma, R., Allen, J., Bakhshandeh, O., Mostafazadeh, N.: Tackling the story ending biases in the story cloze test. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 752\u2013757 (2018)","DOI":"10.18653\/v1\/P18-2119"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Srinivasan, S., Arora, R., Riedl, M.: A simple and effective approach to the story cloze test. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 2 (Short Papers), pp. 92\u201396 (2018)","DOI":"10.18653\/v1\/N18-2015"},{"key":"5_CR19","unstructured":"Talmor, A., Herzig, J., Lourie, N., Berant, J.: CommonsenseQA: a question answering challenge targeting commonsense knowledge. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 4149\u20134158 (2019)"},{"key":"5_CR20","first-page":"353","volume":"2018","author":"A Wang","year":"2018","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. EMNLP 2018, 353 (2018)","journal-title":"EMNLP"},{"key":"5_CR21","unstructured":"Yaghoobzadeh, Y., Tachet, R., Hazen, T., Sordoni, A.: Robust natural language inference models with example forgetting. arXiv preprint arXiv:1911.03861 (2019)"},{"key":"5_CR22","unstructured":"Yu, W., Jiang, Z., Dong, Y., Feng, J.: Reclor: A reading comprehension dataset requiring logical reasoning. arXiv preprint arXiv:2002.04326 (2020)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Schwartz, R., Choi, Y.: Swag: A large-scale adversarial dataset for grounded commonsense inference. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 93\u2013104 (2018)","DOI":"10.18653\/v1\/D18-1009"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8184-7_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T06:02:55Z","timestamp":1711346575000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8184-7_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,26]]},"ISBN":["9789819981830","9789819981847"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8184-7_5","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023,11,26]]},"assertion":[{"value":"26 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"650","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"51% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.14","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.46","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}