{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T23:53:54Z","timestamp":1781913234775,"version":"3.54.5"},"reference-count":99,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Recent advances in deep learning have improved the performance of many Natural Language Processing (NLP) tasks such as translation, question-answering, and text classification. However, this improvement comes at the expense of model explainability. Black-box models make it difficult to understand the internals of a system and the process it takes to arrive at an output. Numerical (LIME, Shapley) and visualization (saliency heatmap) explainability techniques are helpful; however, they are insufficient because they require specialized knowledge. These factors led rationalization to emerge as a more accessible explainable technique in NLP. Rationalization justifies a model's output by providing a natural language explanation (rationale). Recent improvements in natural language generation have made rationalization an attractive technique because it is intuitive, human-comprehensible, and accessible to non-technical users. Since rationalization is a relatively new field, it is disorganized. As the first survey, rationalization literature in NLP from 2007 to 2022 is analyzed. This survey presents available methods, explainable evaluations, code, and datasets used across various NLP tasks that use rationalization. Further, a new subfield in Explainable AI (XAI), namely, Rational AI (RAI), is introduced to advance the current state of rationalization. A discussion on observed insights, challenges, and future directions is provided to point to promising research opportunities.<\/jats:p>","DOI":"10.3389\/frai.2023.1225093","type":"journal-article","created":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T05:35:12Z","timestamp":1695706512000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":47,"title":["Rationalization for explainable NLP: a survey"],"prefix":"10.3389","volume":"6","author":[{"given":"Sai","family":"Gurrapu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajay","family":"Kulkarni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lifu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ismini","family":"Lourentzou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feras A.","family":"Batarseh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,9,25]]},"reference":[{"key":"B1","first-page":"1955","article-title":"\u201cAnalyzing the behavior of visual question answering models,\u201d","author":"Agrawal","year":"2016","journal-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, Texas, USA, November 1-4, 2016"},{"key":"B2","doi-asserted-by":"crossref","first-page":"85","DOI":"10.18653\/v1\/W18-5513","article-title":"\u201cWhere is your evidence: Improving fact-checking by justification modeling,\u201d","volume-title":"Proceedings of the First Workshop on Fact Extraction and VERification (FEVER)","author":"Alhindi","year":"2018"},{"key":"B3","first-page":"412","article-title":"\u201ccausal framework for explaining the predictions of black-box sequence-to-sequence models,\u201d","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Alvarez-Melis","year":"2017"},{"key":"B4","first-page":"761","article-title":"\u201cRationalization through concepts,\u201d","author":"Antognini","year":"2021"},{"key":"B5","doi-asserted-by":"publisher","first-page":"12507","DOI":"10.1609\/aaai.v35i14.17483","article-title":"\u201cMulti-dimensional explanation of target variables from documents","volume":"35","author":"Antognini","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intelli"},{"key":"B6","volume-title":"Mindreaders the Cognitive Basis of Theory of Mind","author":"Apperly","year":"2011"},{"key":"B7","doi-asserted-by":"crossref","first-page":"7352","DOI":"10.18653\/v1\/2020.acl-main.656","article-title":"\u201cGenerating fact checking explanations,\u201d","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Atanasova","year":"2020"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S1351324921000395","article-title":"A survey on machine reading comprehension systems","volume":"2022","author":"Baradaran","year":"2022","journal-title":"Nat. Lang. Eng"},{"key":"B9","doi-asserted-by":"crossref","first-page":"2963","DOI":"10.18653\/v1\/P19-1284","article-title":"\u201cInterpretable neural predictions with differentiable binary variables,\u201d","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Bastings","year":"2019"},{"key":"B10","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/s40537-021-00445-7","article-title":"A survey on artificial intelligence assurance","volume":"8","author":"Batarseh","year":"2021","journal-title":"J. Big Data"},{"key":"B11","first-page":"632","article-title":"\u201cA large annotated corpus for learning natural language inference,\u201d","volume-title":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","author":"Bowman","year":""},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075","article-title":"A large annotated corpus for learning natural language inference","author":"Bowman","year":"","journal-title":"arXiv"},{"key":"B13","first-page":"1877","article-title":"\u201cLanguage models are few-shot learners,\u201d","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems, volume 33"},{"key":"B14","first-page":"9539","article-title":"\u201ce-snli: Natural language inference with natural language explanations,\u201d","author":"Camburu","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bigscience-1.5","article-title":"Unirex: a unified learning framework for language model rationale extraction","author":"Chan","year":"2021","journal-title":"CoRR"},{"key":"B16","first-page":"1448","article-title":"\u201cInvariant rationalization,\u201d","author":"Chang","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning"},{"key":"B17","first-page":"10055","article-title":"\u201cA game theoretic approach to class-wise selective rationalization,\u201d","author":"Chang","year":"2019","journal-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019"},{"key":"B18","first-page":"447","article-title":"\u201cA survey of the state of explainable AI for natural language processing,\u201d","volume-title":"Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing","author":"Danilevsky","year":"2020"},{"key":"B19","first-page":"510","article-title":"\u201cLeveraging rationales to improve human task performance,\u201d","volume-title":"Proceedings of the 25th International Conference on Intelligent User Interfaces, IUI '20","author":"Das","year":"2020"},{"key":"B20","first-page":"4171","article-title":"\u201cBERT: Pre-training of deep bidirectional transformers for language understanding,\u201d","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin","year":"2019"},{"key":"B21","doi-asserted-by":"crossref","first-page":"4443","DOI":"10.18653\/v1\/2020.acl-main.408","article-title":"\u201cERASER: A benchmark to evaluate rationalized NLP models,\u201d","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"DeYoung","year":"2020"},{"key":"B22","article-title":"Towards a rigorous science of interpretable machine learning","author":"Doshi-Velez","year":"2017","journal-title":"arXiv"},{"key":"B23","first-page":"150","author":"Du","year":"2019"},{"key":"B24","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1145\/3278721.3278736","article-title":"\u201cRationalization: A neural machine translation approach to generating natural language explanations,\u201d","volume-title":"Proceedings of the 2018 AAAI\/ACM Conference on AI, Ethics, and Society, AIES '18","author":"Ehsan","year":"2018"},{"key":"B25","doi-asserted-by":"publisher","first-page":"113679","DOI":"10.1016\/j.eswa.2020.113679","article-title":"Automatic text summarization: A comprehensive survey","volume":"165","author":"El-Kassas","year":"2021","journal-title":"Expert Syst. Appl"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1287","DOI":"10.1126\/science.aaw4399","article-title":"Adversarial attacks on medical machine learning","volume":"363","author":"Finlayson","year":"2019","journal-title":"Science"},{"key":"B27","volume-title":"Translation Error Detection As Rationale Extraction","author":"Fomicheva Specia","year":"2021"},{"key":"B28","first-page":"1","article-title":"\u201cThe science of usability testing,\u201d","volume-title":"Proceedings of the 2015 Federal Committee on Statistical Methodology (FCSM) Research Conference","author":"Fox","year":"2015"},{"key":"B29","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/DSAA.2018.00018","article-title":"\u201cExplaining explanations: an overview of interpretability of machine learning,\u201d","author":"Gilpin","year":"2018","journal-title":"2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA)"},{"key":"B30","volume-title":"The Rise of Fact-Checking Sites in Europe","author":"Graves","year":"2016"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1145\/3236009","article-title":"A survey of methods for explaining black box models","author":"Guidotti","year":"2018","journal-title":"ACM Comput. Surv"},{"key":"B32","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.eswa.2018.12.011","article-title":"Abstractive summarization: an overview of the state of the art","volume":"121","author":"Gupta","year":"2019","journal-title":"Expert Syst. Appl"},{"key":"B33","doi-asserted-by":"crossref","DOI":"10.1109\/STC55697.2022.00012","article-title":"\u201cExclaim: Explainable neural claim verification using rationalization,\u201d","volume-title":"2022 IEEE 29th Annual Software Technology Conference","author":"Gurrapu","year":"2022"},{"key":"B34","doi-asserted-by":"crossref","first-page":"493","DOI":"10.18653\/v1\/K19-1046","article-title":"\u201cA richly annotated corpus for different tasks in automated fact-checking,\u201d","volume-title":"Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)","author":"Hanselowski","year":"2019"},{"key":"B35","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1145\/1735223.1735255","article-title":"Number of people required for usability evaluation: the 10\u00b12 rule","volume":"53","author":"Hwang","year":"2010","journal-title":"Commun. ACM"},{"key":"B36","doi-asserted-by":"crossref","first-page":"12","DOI":"10.18653\/v1\/W18-1703","article-title":"\u201cMulti-hop inference for sentence-level TextGraphs: How challenging is meaningfully combining information for science question answering?,\u201d","volume-title":"Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12)","author":"Jansen","year":"2018"},{"key":"B37","doi-asserted-by":"crossref","first-page":"8730","DOI":"10.18653\/v1\/2020.acl-main.771","article-title":"\u201cNILE : Natural language inference with faithful natural language explanations,\u201d","author":"Kumar","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"},{"key":"B38","doi-asserted-by":"crossref","first-page":"3712","DOI":"10.18653\/v1\/2021.emnlp-main.301","article-title":"\u201cFiD-ex: Improving sequence-to-sequence models for extractive rationale generation,\u201d","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Lakhotia","year":"2021"},{"key":"B39","doi-asserted-by":"crossref","first-page":"107","DOI":"10.18653\/v1\/D16-1011","article-title":"\u201cRationalizing neural predictions,\u201d","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Lei","year":"2016"},{"key":"B40","doi-asserted-by":"crossref","first-page":"7871","DOI":"10.18653\/v1\/2020.acl-main.703","article-title":"\u201cBART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension,\u201d","author":"Lewis","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"},{"key":"B41","article-title":"Teaching pretrained models with commonsense reasoning: A preliminary kb-based approach","author":"Li","year":"2019","journal-title":"arXiv"},{"key":"B42","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1145\/3523227.3546783","article-title":"\u201cSelf-supervised bot play for transcript-free conversational recommendation with rationales,\u201d","volume-title":"Proceedings of the 16th ACM Conference on Recommender Systems, RecSys '22","author":"Li","year":"2022"},{"key":"B43","first-page":"74","article-title":"\u201cRouge: A package for automatic evaluation of summaries,\u201d","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"B44","doi-asserted-by":"crossref","first-page":"158","DOI":"10.18653\/v1\/P17-1015","article-title":"\u201cProgram induction by rationale generation: Learning to solve and explain algebraic word problems,\u201d","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Ling","year":"2017"},{"key":"B45","first-page":"249","article-title":"\u201cClinically accurate chest x-ray report generation,\u201d","author":"Liu","year":"","journal-title":"Proceedings of the 4th Machine Learning for Healthcare Conference"},{"key":"B46","first-page":"5570","article-title":"\u201cTowards explainable NLP: A generative explanation framework for text classification,\u201d","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Liu","year":""},{"key":"B47","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1387","article-title":"\u201cText summarization with pretrained encoders,\u201d","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Liu","year":"2019"},{"key":"B48","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B49","article-title":"\u201cA unified approach to interpreting model predictions,\u201d","author":"Lundberg","year":"","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B50","author":"Luo","year":"2021","journal-title":"Local Interpretations for Explainable Natural Language Processing: A Survey"},{"key":"B51","first-page":"142","article-title":"\u201cLearning word vectors for sentiment analysis,\u201d","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies","author":"Maas","year":"2011"},{"key":"B52","volume-title":"Natural Logic and Natural Language","author":"MacCartney","year":"2009"},{"key":"B53","author":"Madsen","year":"2021","journal-title":"Post-Hoc Interpretability for Neural nlp: A Survey"},{"key":"B54","author":"Majumder","year":"2021","journal-title":"Rationale-Inspired Natural Language Explanations with commonsense"},{"key":"B55","doi-asserted-by":"crossref","first-page":"1020","DOI":"10.1109\/ICDM.2012.110","article-title":"\u201cLearning attitudes and attributes from multi-aspect reviews,\u201d","author":"McAuley","year":"2012","journal-title":"2012 IEEE 12th International Conference on Data Mining"},{"key":"B56","doi-asserted-by":"crossref","first-page":"2381","DOI":"10.18653\/v1\/D18-1260","article-title":"\u201cCan a suit of armor conduct electricity? a new dataset for open book question answering,\u201d","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Mihaylov","year":"2018"},{"key":"B57","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","article-title":"Explanation in artificial intelligence: Insights from the social sciences","volume":"267","author":"Miller","year":"","journal-title":"Artif. Intell"},{"key":"B58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","article-title":"Explanation in artificial intelligence: insights from the social sciences","volume":"267","author":"Miller","year":"","journal-title":"Artif. Intell"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.1145\/3439726","article-title":"Deep learning-based text classification: a comprehensive review","author":"Minaee","year":"2021","journal-title":"ACM Comput. Surv"},{"key":"B60","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1145\/3287560.3287574","article-title":"\u201cExplaining explanations in AI,\u201d","author":"Mittelstadt","year":"2019","journal-title":"Proceedings of the Conference on Fairness, Accountability, and Transparency"},{"key":"B61","article-title":"Wt5?! training text-to-text models to explain their predictions","author":"Narang","year":"2020","journal-title":"ArXiv"},{"key":"B62","first-page":"311","article-title":"\u201cBleu: a method for automatic evaluation of machine translation,\u201d","author":"Papineni","year":"2002","journal-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics"},{"key":"B63","author":"Plyler","year":"2022","journal-title":"Making a (counterfactual) Difference One Rationale at a Time"},{"key":"B64","first-page":"1","article-title":"Exploring the need for explainable artificial intelligence (xai) in intelligent tutoring systems (its)","volume":"19","author":"Putnam","year":"2019","journal-title":"IUI Workshops"},{"key":"B65","volume-title":"Improving Language Understanding by Generative Pre-Training","author":"Radford","year":"2018"},{"key":"B66","author":"Radford","year":"2019","journal-title":"Language Models are Unsupervised Multitask Learners"},{"key":"B67","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"B68","doi-asserted-by":"crossref","first-page":"4932","DOI":"10.18653\/v1\/P19-1487","article-title":"\u201cExplain yourself! leveraging language models for commonsense reasoning,\u201d","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Rajani","year":"2019"},{"key":"B69","author":"Rana","year":"2022","journal-title":"Rerrfact: Reduced Evidence Retrieval Representations for Scientific Claim Verification"},{"key":"B70","first-page":"1135","author":"Ribeiro","year":"2016"},{"key":"B71","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1002\/hbe2.117","article-title":"Human-centered artificial intelligence and machine learning","volume":"1","author":"Riedl","year":"2019","journal-title":"Human Behav. Emerg. Technol"},{"key":"B72","author":"Russell","year":"2002","journal-title":"Artificial Intelligence: A Modern Approach"},{"key":"B73","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"ArXiv"},{"key":"B74","doi-asserted-by":"crossref","first-page":"27","DOI":"10.18653\/v1\/2020.acl-tutorials.7","article-title":"\u201cCommonsense reasoning for natural language processing,\u201d","author":"Sap","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts"},{"key":"B75","doi-asserted-by":"crossref","first-page":"5263","DOI":"10.18653\/v1\/2020.emnlp-main.425","article-title":"\u201cA computational approach to understanding empathy expressed in text-based mental health support,\u201d","author":"Sharma","year":"2020","journal-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"B76","doi-asserted-by":"crossref","first-page":"69","DOI":"10.18653\/v1\/K17-1009","article-title":"\u201cTell me why: Using question answering as distant supervision for answer justification,\u201d","volume-title":"Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)","author":"Sharp","year":"2017"},{"key":"B77","doi-asserted-by":"crossref","DOI":"10.1111\/cgf.14329","volume-title":"A Survey of Human-Centered Evaluations in Human-Centered Machine Learning","author":"Sperrle","year":"2021"},{"key":"B78","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-13437-1_112","article-title":"\u201cPslc datashop: a data analysis service for the learning science community,\u201d","volume-title":"International Conference on Intelligent Tutoring Systems","author":"Stamper","year":"2010"},{"key":"B79","first-page":"56","author":"Strout","year":"2019","journal-title":"Do Human Rationales Improve Machine Explanations"},{"key":"B80","first-page":"3319","article-title":"\u201cAxiomatic attribution for deep networks,\u201d","author":"Sundararajan","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"B81","first-page":"3104","article-title":"\u201cSequence to sequence learning with neural networks,\u201d","author":"Sutskever","year":"2014","journal-title":"Proceedings of the 27th International Conference on Neural Information Processing Systems"},{"key":"B82","first-page":"4149","article-title":"\u201cCommonsenseQA: A question answering challenge targeting commonsense knowledge,\u201d","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Talmor","year":"2019"},{"key":"B83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86534-4_7","article-title":"Cognitive visual commonsense reasoning using dynamic working memory","author":"Tang","year":"2021","journal-title":"CoRR"},{"key":"B84","author":"Thayaparan","year":"2020","journal-title":"A Survey on Explainability in Machine Reading Comprehension"},{"key":"B85","doi-asserted-by":"publisher","first-page":"4793","DOI":"10.1109\/TNNLS.2020.3027314","article-title":"A survey on explainable artificial intelligence (xai): toward medical xai","volume":"32","author":"Tjoa","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B86","doi-asserted-by":"publisher","DOI":"10.1177\/1461444817712086","article-title":"The agenda-setting power of fake news: A big data analysis of the online media landscape from 2014 to 2016","author":"Vargo","year":"2018","journal-title":"Sage J"},{"key":"B87","article-title":"\u201cAttention is all you need,\u201d","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B88","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2020.emnlp-main.609","article-title":"\u201cFact or fiction: verifying scientific claims,\u201d","author":"Wadden","year":"2020","journal-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP"},{"key":"B89","doi-asserted-by":"crossref","first-page":"422","DOI":"10.18653\/v1\/P17-2067","article-title":"\u201cLiar, liar pants on fire: a new benchmark dataset for fake news detection,\u201d","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Wang","year":"2017"},{"key":"B90","doi-asserted-by":"crossref","first-page":"10266","DOI":"10.18653\/v1\/2021.emnlp-main.804","article-title":"\u201cMeasuring association between labels and free-text rationales,\u201d","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Wiegreffe","year":"2021"},{"key":"B91","first-page":"1112","article-title":"\u201cA broad-coverage challenge corpus for sentence understanding through inference,\u201d","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","author":"Williams","year":"2018"},{"key":"B92","first-page":"5456","article-title":"\u201cWorldtree v2: a corpus of science-domain structured explanations and inference patterns supporting multi-hop inference,\u201d","author":"Xie","year":"2020","journal-title":"Proceedings of the 12th Language Resources and Evaluation Conference"},{"key":"B93","article-title":"A survey of deep learning techniques for neural machine translation","author":"Yang","year":"2020","journal-title":"CoRR"},{"key":"B94","doi-asserted-by":"crossref","first-page":"4094","DOI":"10.18653\/v1\/D19-1420","article-title":"\u201cRethinking cooperative rationalization: Introspective extraction and complement control,\u201d","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Yu","year":"2019"},{"key":"B95","author":"Yu","year":"2021","journal-title":"Understanding Interlocking Dynamics of Cooperative Rationalization"},{"key":"B96","first-page":"260","author":"Zaidan","year":"2007","journal-title":"Using \u201cAnnotator Rationales\u201d to Improve Machine Learning for Text Categorization"},{"key":"B97","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1253","article-title":"Deep learning for sentiment analysis: a survey","author":"Zhang","year":"2018","journal-title":"Wiley Interdisc. Rev"},{"key":"B98","doi-asserted-by":"crossref","first-page":"795","DOI":"10.18653\/v1\/D16-1076","article-title":"\u201cRationale-augmented convolutional neural networks for text classification,\u201d","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Zhang","year":"2016"},{"key":"B99","first-page":"418","volume-title":"Explain and Predict, and Then Predict Again","author":"Zhang","year":"2021"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1225093\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T05:35:58Z","timestamp":1695706558000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1225093\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,25]]},"references-count":99,"alternative-id":["10.3389\/frai.2023.1225093"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1225093","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,25]]},"article-number":"1225093"}}