{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:19:27Z","timestamp":1776115167259,"version":"3.50.1"},"reference-count":118,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T00:00:00Z","timestamp":1666224000000},"content-version":"vor","delay-in-days":292,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,18]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>A fundamental goal of scientific research is to learn about causal relationships. However, despite its critical role in the life and social sciences, causality has not had the same importance in Natural Language Processing (NLP), which has traditionally placed more emphasis on predictive tasks. This distinction is beginning to fade, with an emerging area of interdisciplinary research at the convergence of causal inference and language processing. Still, research on causality in NLP remains scattered across domains without unified definitions, benchmark datasets and clear articulations of the challenges and opportunities in the application of causal inference to the textual domain, with its unique properties. In this survey, we consolidate research across academic areas and situate it in the broader NLP landscape. We introduce the statistical challenge of estimating causal effects with text, encompassing settings where text is used as an outcome, treatment, or to address confounding. In addition, we explore potential uses of causal inference to improve the robustness, fairness, and interpretability of NLP models. We thus provide a unified overview of causal inference for the NLP community.1<\/jats:p>","DOI":"10.1162\/tacl_a_00511","type":"journal-article","created":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T14:52:36Z","timestamp":1666277556000},"page":"1138-1158","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":115,"title":["Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond"],"prefix":"10.1162","volume":"10","author":[{"given":"Amir","family":"Feder","sequence":"first","affiliation":[{"name":"Technion - Israel Institute of Technology, Israel"},{"name":"Princeton University, USA"}]},{"given":"Katherine A.","family":"Keith","sequence":"additional","affiliation":[{"name":"Williams College, USA"}]},{"given":"Emaad","family":"Manzoor","sequence":"additional","affiliation":[{"name":"University of Wisconsin - Madison, USA"}]},{"given":"Reid","family":"Pryzant","sequence":"additional","affiliation":[{"name":"Microsoft, USA"}]},{"given":"Dhanya","family":"Sridhar","sequence":"additional","affiliation":[{"name":"Columbia University, Canada"}]},{"given":"Zach","family":"Wood-Doughty","sequence":"additional","affiliation":[{"name":"Northwestern University, USA"}]},{"given":"Jacob","family":"Eisenstein","sequence":"additional","affiliation":[{"name":"Google Research, USA"}]},{"given":"Justin","family":"Grimmer","sequence":"additional","affiliation":[{"name":"Stanford University, USA"}]},{"given":"Roi","family":"Reichart","sequence":"additional","affiliation":[{"name":"Technion - Israel Institute of Technology, Israel"}]},{"given":"Margaret E.","family":"Roberts","sequence":"additional","affiliation":[{"name":"University of California San Diego, USA"}]},{"given":"Brandon M.","family":"Stewart","sequence":"additional","affiliation":[{"name":"Princeton University, USA"}]},{"given":"Victor","family":"Veitch","sequence":"additional","affiliation":[{"name":"Google Research, USA"},{"name":"University of Chicago, USA"}]},{"given":"Diyi","family":"Yang","sequence":"additional","affiliation":[{"name":"Georgia Tech, USA"}]}],"member":"281","published-online":{"date-parts":[[2022,10,18]]},"reference":[{"key":"2022102014515973800_bib1","article-title":"Fairness and robustness in invariant learning: A case study in toxicity classification","author":"Adragna","year":"2020","journal-title":"arXiv preprint arXiv: 2011.06485"},{"key":"2022102014515973800_bib2","doi-asserted-by":"publisher","first-page":"1889","DOI":"10.18653\/v1\/2021.acl-long.148","article-title":"Bad seeds: Evaluating lexical methods for bias measurement","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Antoniak","year":"2021"},{"key":"2022102014515973800_bib3","article-title":"Invariant risk minimization","author":"Arjovsky","year":"2019","journal-title":"arXiv preprint arXiv:1907.02893"},{"key":"2022102014515973800_bib4","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv preprint arXiv:1409.0473"},{"key":"2022102014515973800_bib5","volume-title":"Fairness and Machine Learning","author":"Barocas","year":"2019"},{"issue":"1","key":"2022102014515973800_bib6","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10994-009-5152-4","article-title":"A theory of learning from different domains","volume":"79","author":"Ben-David","year":"2010","journal-title":"Machine Learning"},{"issue":"Jan","key":"2022102014515973800_bib7","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"Journal of machine Learning research"},{"key":"2022102014515973800_bib8","doi-asserted-by":"publisher","first-page":"5454","DOI":"10.18653\/v1\/2020.acl-main.485","article-title":"Language (technology) is power: A critical survey of \u201cbias\u201d in NLP","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Lin Blodgett","year":"2020"},{"key":"2022102014515973800_bib9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.533","article-title":"Docogen: Domain counterfactual generation for low resource domain adaptation","volume-title":"Proceedings of the 60th Annual Meeting of the Association of Computational Linguistics (ACL)","author":"Calderon","year":"2022"},{"key":"2022102014515973800_bib10","first-page":"21061","article-title":"Self-training avoids using spurious features under domain shift","volume":"33","author":"Chen","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2022102014515973800_bib11","article-title":"Overlap in observational studies with high-dimensional covariates","author":"D\u2019Amour","year":"2020","journal-title":"Journal of Econometrics"},{"key":"2022102014515973800_bib12","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2\u20137, 2019, Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019"},{"key":"2022102014515973800_bib13","doi-asserted-by":"publisher","first-page":"31","DOI":"10.18653\/v1\/P18-2006","article-title":"Hotflip: White-box adversarial examples for text classification","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Ebrahimi","year":"2018"},{"key":"2022102014515973800_bib14","article-title":"How to make causal inferences using texts","author":"Egami","year":"2018","journal-title":"arXiv preprint arXiv:1802.02163"},{"key":"2022102014515973800_bib15","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1162\/tacl_a_00359","article-title":"Amnesic probing: Behavioral explanation with amnesic counterfactuals","volume":"9","author":"Elazar","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"2","key":"2022102014515973800_bib16","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1162\/coli_a_00404","article-title":"Causalm: Causal model explanation through counterfactual language models","volume":"47","author":"Feder","year":"2021","journal-title":"Computational Linguistics"},{"key":"2022102014515973800_bib17","doi-asserted-by":"publisher","first-page":"1828","DOI":"10.18653\/v1\/2021.acl-long.144","article-title":"Causal analysis of syntactic agreement mechanisms in neural language models","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Finlayson","year":"2021"},{"key":"2022102014515973800_bib18","doi-asserted-by":"crossref","first-page":"1600","DOI":"10.18653\/v1\/P16-1151","article-title":"Discovery of treatments from text corpora","volume-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Fong","year":"2016"},{"key":"2022102014515973800_bib19","doi-asserted-by":"crossref","DOI":"10.1111\/ajps.12649","article-title":"Causal inference with latent treatments","author":"Fong","year":"2021","journal-title":"American Journal of Political Science"},{"key":"2022102014515973800_bib20","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.18653\/v1\/2020.findings-emnlp.117","article-title":"Evaluating models\u2019 local decision boundaries via contrast sets","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Gardner","year":"2020"},{"key":"2022102014515973800_bib21","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1145\/3306618.3317950","article-title":"Counterfactual fairness in text classification through robustness","volume-title":"Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society","author":"Garg","year":"2019"},{"key":"2022102014515973800_bib22","article-title":"Causal abstractions of neural networks","volume":"34","author":"Geiger","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"2022102014515973800_bib23","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1017\/S000305540808009X","article-title":"Social pressure and voter turnout: Evidence from a large-scale field experiment","volume":"102","author":"Gerber","year":"2008","journal-title":"American Political Science Review"},{"key":"2022102014515973800_bib24","doi-asserted-by":"publisher","first-page":"2551","DOI":"10.1109\/ICCV.2015.293","article-title":"Domain generalization for object recognition with multi- task autoencoders","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Ghifary","year":"2015"},{"key":"2022102014515973800_bib25","doi-asserted-by":"publisher","first-page":"1926","DOI":"10.18653\/v1\/2021.acl-long.150","article-title":"Intrinsic bias metrics do not correlate with application bias","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Goldfarb-Tarrant","year":"2021"},{"issue":"5","key":"2022102014515973800_bib26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3236009","article-title":"A survey of methods for explaining black box models","volume":"51","author":"Guidotti","year":"2018","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2022102014515973800_bib27","article-title":"In search of lost domain generalization","author":"Gulrajani","year":"2020","journal-title":"arXiv preprint arXiv:2007.01434"},{"key":"2022102014515973800_bib28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2017","article-title":"Annotation artifacts in natural language inference data","author":"Gururangan","year":"2018","journal-title":"Proceedings of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)"},{"key":"2022102014515973800_bib29","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1145\/3351095.3372826","article-title":"Towards a critical race methodology in algorithmic fairness","volume-title":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","author":"Hanna","year":"2020"},{"key":"2022102014515973800_bib30","first-page":"3315","article-title":"Equality of opportunity in supervised learning","volume":"29","author":"Hardt","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"10","key":"2022102014515973800_bib31","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1016\/j.annepidem.2016.08.016","article-title":"Does water kill? A call for less casual causal inferences","volume":"26","author":"Hern\u00e1n","year":"2016","journal-title":"Annals of Epidemiology"},{"issue":"396","key":"2022102014515973800_bib32","doi-asserted-by":"publisher","first-page":"945","DOI":"10.2307\/2289069","article-title":"Statistics and causal inference","volume":"81","author":"Holland","year":"1986","journal-title":"Journal of the American Statistical Association"},{"key":"2022102014515973800_bib33","article-title":"A causal lens for controllable text generation","volume":"34","author":"Zhiting","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2022102014515973800_bib34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.7","article-title":"Reducing sentiment bias in language models via counterfactual evaluation","author":"Huang","year":"2019","journal-title":"arXiv preprint arXiv:1911.03064"},{"key":"2022102014515973800_bib35","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139025751","volume-title":"Causal Inference in Statistics, Social, and Biomedical Sciences","author":"Imbens","year":"2015"},{"key":"2022102014515973800_bib36","doi-asserted-by":"publisher","first-page":"4198","DOI":"10.18653\/v1\/2020.acl-main.386","article-title":"Towards faithfully interpretable nlp systems: How should we define and evaluate faithfulness?","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Jacovi","year":"2020"},{"key":"2022102014515973800_bib37","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1145\/3442188.3445923","article-title":"Formalizing trust in artificial intelligence: Prerequisites, causes and goals of human trust in ai","volume-title":"Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency","author":"Jacovi","year":"2021"},{"key":"2022102014515973800_bib38","article-title":"Attention is not explanation","author":"Jain","year":"2019","journal-title":"arXiv preprint arXiv: 1902.10186"},{"key":"2022102014515973800_bib39","article-title":"Does data augmentation improve generalization in NLP?","author":"Jha","year":"2020","journal-title":"arXiv preprint arXiv: 2004.15012"},{"issue":"2","key":"2022102014515973800_bib40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3185593","article-title":"Online harassment and content moderation: The case of blocklists","volume":"25","author":"Jhaver","year":"2018","journal-title":"ACM Transactions on Computer- Human Interaction (TOCHI)"},{"key":"2022102014515973800_bib41","doi-asserted-by":"publisher","first-page":"9499","DOI":"10.18653\/v1\/2021.emnlp-main.748","article-title":"Causal direction of data collection matters: Im plications of causal and anticausal learning for NLP","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Jin","year":"2021"},{"key":"2022102014515973800_bib42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.256","article-title":"An investigation of the (in) effectiveness of counterfactually augmented data","author":"Joshi","year":"2021","journal-title":"arXiv preprint arXiv:2107 .00753"},{"key":"2022102014515973800_bib43","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1145\/3442188.3445899","article-title":"Algorithmic recourse: from counterfactual explanations to interventions","volume-title":"Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency","author":"Karimi","year":"2021"},{"key":"2022102014515973800_bib44","article-title":"Learning the difference that makes a difference with counterfactually- augmented data","author":"Kaushik","year":"2019","journal-title":"arXiv preprint arXiv:1909 .12434"},{"key":"2022102014515973800_bib45","article-title":"Explaining the efficacy of counterfactually-augmented data","author":"Kaushik","year":"2020","journal-title":"arXiv preprint arXiv:2010.02114"},{"key":"2022102014515973800_bib46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.474","article-title":"Text and causal inference: A review of using text to remove confounding from causal estimates","volume-title":"ACL","author":"Keith","year":"2020"},{"key":"2022102014515973800_bib47","doi-asserted-by":"publisher","first-page":"329","DOI":"10.18653\/v1\/D16-1032","article-title":"Globally coherent text generation with neural checklist models","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Kiddon","year":"2016"},{"key":"2022102014515973800_bib48","first-page":"656","article-title":"Avoiding discrimination through causal reasoning","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Kilbertus","year":"2017"},{"key":"2022102014515973800_bib49","first-page":"2668","article-title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)","volume-title":"International Conference on Machine Learning","author":"Kim","year":"2018"},{"key":"2022102014515973800_bib50","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.2139\/ssrn.3050650","article-title":"Eddie murphy and the dangers of counterfactual causal thinking about detecting racial discrimination","volume":"113","author":"Kohler-Hausmann","year":"2018","journal-title":"Nw. UL Rev."},{"key":"2022102014515973800_bib51","first-page":"4066","article-title":"Counterfactual fairness","volume-title":"Advances in Neural Information Processing Systems","author":"Kusner","year":"2017"},{"key":"2022102014515973800_bib52","first-page":"1188","article-title":"Distributed representations of sentences and documents","volume-title":"International Conference on Machine Learning","author":"Le","year":"2014"},{"key":"2022102014515973800_bib53","first-page":"912","article-title":"Representation learning using multi-task deep neural networks for semantic classification and information retrieval","volume-title":"Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Liu","year":"2015"},{"key":"2022102014515973800_bib54","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1162\/tacl_a_00005","article-title":"Learning structured text representations","volume":"6","author":"Liu","year":"2018","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2022102014515973800_bib55","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv:1907.11692"},{"key":"2022102014515973800_bib56","article-title":"Content preserving text generation with attribute controls","volume":"31","author":"Logeswaran","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2022102014515973800_bib57","doi-asserted-by":"publisher","first-page":"7052","DOI":"10.18653\/v1\/2021.emnlp-main.565","article-title":"Entity-based knowledge conflicts in question answering","volume-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","author":"Longpre","year":"2021"},{"key":"2022102014515973800_bib58","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"key":"2022102014515973800_bib59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1530","article-title":"It\u2019s all in the name: Mitigating gender bias with name- based counterfactual data substitution","author":"Maudslay","year":"2019","journal-title":"arXiv preprint arXiv:1909.00871"},{"key":"2022102014515973800_bib60","doi-asserted-by":"publisher","first-page":"152","DOI":"10.3115\/1220835.1220855","article-title":"Effective self-training for parsing","volume-title":"Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics","author":"McClosky","year":"2006"},{"key":"2022102014515973800_bib61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1334","article-title":"Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference","author":"Thomas McCoy","year":"2019","journal-title":"arXiv preprint arXiv:1902.01007"},{"key":"2022102014515973800_bib62","article-title":"Locating and editing factual knowledge in GPT","author":"Meng","year":"2022","journal-title":"arXiv preprint arXiv:2202.05262"},{"key":"2022102014515973800_bib63","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107587991","volume-title":"Counterfactuals and Causal Inference","author":"Morgan","year":"2015"},{"key":"2022102014515973800_bib64","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1145\/3351095.3372850","article-title":"Explaining machine learning classifiers through diverse counterfactual explanations","volume-title":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","author":"Mothilal","year":"2020"},{"issue":"4","key":"2022102014515973800_bib65","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1017\/pan.2020.1","article-title":"Matching with text data: An experimental evaluation of methods for matching documents and of measuring match quality","volume":"28","author":"Mozer","year":"2020","journal-title":"Political Analysis"},{"key":"2022102014515973800_bib66","first-page":"10","article-title":"Domain generalization via invariant feature representation","volume-title":"International Conference on Machine Learning","author":"Muandet","year":"2013"},{"key":"2022102014515973800_bib67","first-page":"2340","article-title":"Stress test evaluation for natural language inference","volume-title":"Proceedings of the 27th International Conference on Computational Linguistics","author":"Naik","year":"2018"},{"key":"2022102014515973800_bib68","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1162\/tacl_a_00027","article-title":"Polite dialogue generation without parallel data","volume":"6","author":"Niu","year":"2018","journal-title":"Transactions of the Association for Computational Linguistics"},{"issue":"1","key":"2022102014515973800_bib69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-73917-0","article-title":"Deep neural networks detect suicide risk from textual facebook posts","volume":"10","author":"Ophir","year":"2020","journal-title":"Scientific Reports"},{"key":"2022102014515973800_bib70","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1162\/tacl_a_00040","article-title":"Comparing bayesian models of annotation","volume":"6","author":"Paun","year":"2018","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2022102014515973800_bib71","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1162\/tacl_a_00293","article-title":"Inherent disagreements in human textual inferences","volume":"7","author":"Pavlick","year":"2019","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"2022102014515973800_bib72","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1016\/B978-1-55860-332-5.50062-6","article-title":"A probabilistic calculus of actions","volume-title":"Uncertainty Proceedings 1994","author":"Pearl","year":"1994"},{"key":"2022102014515973800_bib73","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511803161","volume-title":"Causality","author":"Pearl","year":"2009"},{"issue":"5","key":"2022102014515973800_bib74","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1111\/rssb.12167","article-title":"Causal inference using invariant prediction: identification and confidence intervals","volume":"78","author":"Peters","year":"2016","journal-title":"Journal of the Royal Statistical Society-Statistical Methodology-Series B"},{"key":"2022102014515973800_bib75","doi-asserted-by":"publisher","first-page":"2227","DOI":"10.18653\/v1\/N18-1202","article-title":"Deep contextualized word representations","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT","author":"Peters","year":"2018"},{"key":"2022102014515973800_bib76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S18-2023","article-title":"Hypothesis only baselines in natural language inference","author":"Poliak","year":"2018","journal-title":"arXiv preprint arXiv: 1805.01042"},{"key":"2022102014515973800_bib77","doi-asserted-by":"publisher","first-page":"4095","DOI":"10.18653\/v1\/2021.naacl-main.323","article-title":"Causal effects of linguistic properties","volume-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Pryzant","year":"2021"},{"key":"2022102014515973800_bib78","article-title":"Predicting sales from the language of product descriptions","volume-title":"eCOM@ SIGIR","author":"Pryzant","year":"2017"},{"key":"2022102014515973800_bib79","doi-asserted-by":"publisher","first-page":"1615","DOI":"10.18653\/v1\/N18-1146","article-title":"Deconfounded lexicon induction for interpretable social science","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":"Pryzant","year":"2018"},{"key":"2022102014515973800_bib80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.647","article-title":"Null it out: Guarding protected attributes by iterative nullspace projection","author":"Ravfogel","year":"2020","journal-title":"arXiv preprint arXiv:2004.07667"},{"key":"2022102014515973800_bib81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.conll-1.15","article-title":"Counterfactual interventions reveal the causal effect of relative clause representations on agreement prediction","author":"Ravfogel","year":"2021","journal-title":"arXiv preprint arXiv:2105.06965"},{"key":"2022102014515973800_bib82","first-page":"616","article-title":"Self- training for enhancement and domain adaptation of statistical parsers trained on small datasets","volume-title":"Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics","author":"Reichart","year":"2007"},{"key":"2022102014515973800_bib83","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1145\/2939672.2939778","article-title":"Why should I trust you?: Explaining the predictions of any classifier","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Ribeiro","year":"2016"},{"key":"2022102014515973800_bib84","doi-asserted-by":"publisher","first-page":"4902","DOI":"10.18653\/v1\/2020.acl-main.442","article-title":"Beyond accuracy: Behavioral testing of NLP models with CheckList","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Ribeiro","year":"2020"},{"key":"2022102014515973800_bib85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.293","article-title":"Textsettr: Label-free text style extraction and tunable targeted restyling","author":"Riley","year":"2020","journal-title":"arXiv preprint arXiv:2010.03802"},{"issue":"4","key":"2022102014515973800_bib86","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1111\/ajps.12526","article-title":"Adjusting for confounding with text matching","volume":"64","author":"Roberts","year":"2020","journal-title":"American Journal of Political Science"},{"issue":"4","key":"2022102014515973800_bib87","doi-asserted-by":"publisher","first-page":"1064","DOI":"10.1111\/ajps.12103","article-title":"Structural topic models for open-ended survey responses","volume":"58","author":"Roberts","year":"2014","journal-title":"American Journal of Political Science"},{"issue":"477","key":"2022102014515973800_bib88","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1198\/016214506000001112","article-title":"Interference between units in randomized experiments","volume":"102","author":"Rosenbaum","year":"2007","journal-title":"Journal of the american statistical association"},{"key":"2022102014515973800_bib89","doi-asserted-by":"publisher","first-page":"61","DOI":"10.18653\/v1\/2021.acl-short.10","article-title":"Are VQA systems rad? Measuring robustness to augmented data with focused interventions","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)","author":"Rosenberg","year":"2021"},{"key":"2022102014515973800_bib90","article-title":"The risks of invariant risk minimization","volume-title":"International Conference on Learning Representations","author":"Rosenfeld","year":"2021"},{"key":"2022102014515973800_bib91","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.228","article-title":"Tailor: Generating and perturbing text with semantic controls","author":"Ross","year":"2021","journal-title":"arXiv preprint arXiv:2107.07150"},{"issue":"5","key":"2022102014515973800_bib92","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1037\/h0037350","article-title":"Estimating causal effects of treatments in randomized and nonrandomized studies.","volume":"66","author":"Rubin","year":"1974","journal-title":"Journal of Educational Psychology"},{"issue":"469","key":"2022102014515973800_bib93","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1198\/016214504000001880","article-title":"Causal inference using potential outcomes: Design, modeling, decisions","volume":"100","author":"Rubin","year":"2005","journal-title":"Journal of the American Statistical Association"},{"key":"2022102014515973800_bib94","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3313831.3376645","article-title":"Fragile masculinity: Men, gender, and online harassment","volume-title":"Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems","author":"Rubin","year":"2020"},{"key":"2022102014515973800_bib95","first-page":"1255","article-title":"On causal and anticausal learning","volume-title":"29th International Conference on Machine Learning (ICML 2012)","author":"Sch\u00f6lkopf","year":"2012"},{"key":"2022102014515973800_bib96","doi-asserted-by":"publisher","first-page":"255","DOI":"10.18653\/v1\/P17-1024","article-title":"FOIL it! Find one mismatch between image and language caption","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Shekhar","year":"2017"},{"issue":"2","key":"2022102014515973800_bib97","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2200\/S00497ED1V01Y201304HLT021","article-title":"Semi-supervised learning and domain adaptation in natural language processing","volume":"6","author":"S\u00f8gaard","year":"2013","journal-title":"Synthesis Lectures on Human Language Technologies"},{"key":"2022102014515973800_bib98","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/259","article-title":"Estimating causal effects of tone in online debates","volume-title":"International Joint Conference on Artificial Intelligence","author":"Sridhar","year":"2019"},{"key":"2022102014515973800_bib99","doi-asserted-by":"publisher","DOI":"10.3115\/1067807.1067851","article-title":"Bootstrapping statistical parsers from small datasets","volume-title":"10th Conference of the European Chapter of the Association for Computational Linguistics","author":"Steedman","year":"2003"},{"key":"2022102014515973800_bib100","doi-asserted-by":"publisher","DOI":"10.1101\/2020.09.21.20198762","article-title":"An introduction to proximal causal learning","author":"Tchetgen Tchetgen","year":"2020","journal-title":"arXiv preprint arXiv:2009.10982"},{"key":"2022102014515973800_bib101","doi-asserted-by":"publisher","first-page":"327","DOI":"10.3115\/1610075.1610122","article-title":"Get out the vote: Determining support or opposition from congressional floor-debate transcripts","volume-title":"Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing","author":"Thomas","year":"2006"},{"key":"2022102014515973800_bib102","article-title":"Counterfactual invariance to spurious correlations: Why and how to pass stress tests","author":"Veitch","year":"2021","journal-title":"arXiv preprint arXiv:2106.00545"},{"key":"2022102014515973800_bib103","article-title":"Adapting text embeddings for causal inference","volume-title":"UAI","author":"Veitch","year":"2020"},{"key":"2022102014515973800_bib104","article-title":"Investigating gender bias in language models using causal mediation analysis","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6\u201312, 2020, virtual","author":"Vig","year":"2020"},{"key":"2022102014515973800_bib105","doi-asserted-by":"publisher","first-page":"841","DOI":"10.2139\/ssrn.3063289","article-title":"Counterfactual explanations without opening the black box: Automated decisions and the GDPR","volume":"31","author":"Wachter","year":"2017","journal-title":"Harvard Journal of Law & Technology"},{"issue":"523","key":"2022102014515973800_bib106","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1080\/01621459.2017.1319839","article-title":"Estimation and inference of heterogeneous treatment effects using random forests","volume":"113","author":"Wager","year":"2018","journal-title":"Journal of the American Statistical Association"},{"key":"2022102014515973800_bib107","article-title":"On calibration and out-of-domain generalization","author":"Wald","year":"2021","journal-title":"arXiv preprint arXiv:2102.10395"},{"key":"2022102014515973800_bib108","doi-asserted-by":"publisher","first-page":"606","DOI":"10.18653\/v1\/D16-1058","article-title":"Attention-based LSTM for aspect-level sentiment classification","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing","author":"Wang","year":"2016"},{"key":"2022102014515973800_bib109","doi-asserted-by":"crossref","DOI":"10.1609\/icwsm.v16i1.19362","article-title":"Adjusting for confounders with text: Challenges and an empirical evaluation framework for causal inference","author":"Weld","year":"2022","journal-title":"ICWSM"},{"key":"2022102014515973800_bib110","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1488","article-title":"Challenges of using text classifiers for causal inference","volume-title":"EMNLP","author":"Wood-Doughty","year":"2018"},{"key":"2022102014515973800_bib111","article-title":"Generating synthetic text data to evaluate causal inference methods","author":"Wood-Doughty","year":"2021","journal-title":"arXiv preprint arXiv:2102.05638"},{"key":"2022102014515973800_bib112","article-title":"Polyjuice: Automated, general-purpose counterfactual generation","author":"Tongshuang","year":"2021","journal-title":"arXiv preprint arXiv:2101.00288"},{"key":"2022102014515973800_bib113","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"International Conference on Machine Learning","author":"Kelvin","year":"2015"},{"issue":"CSCW2","key":"2022102014515973800_bib114","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3415202","article-title":"Quantifying the causal effects of conversational tendencies","volume":"4","author":"Zhang","year":"2020","journal-title":"Proceedings of the ACM on Human-Computer Interaction"},{"key":"2022102014515973800_bib115","article-title":"Can transformers be strong treatment effect estimators?","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv:2202.01336"},{"key":"2022102014515973800_bib116","doi-asserted-by":"publisher","first-page":"2979","DOI":"10.18653\/v1\/D17-1323","article-title":"Men also like shopping: Reducing gender bias amplification using corpus-level constraints","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"Zhao","year":"2017"},{"key":"2022102014515973800_bib117","doi-asserted-by":"publisher","first-page":"15","DOI":"10.18653\/v1\/N18-2003","article-title":"Gender bias in coreference resolution: Evaluation and debiasing methods","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)","author":"Zhao","year":"2018"},{"key":"2022102014515973800_bib118","doi-asserted-by":"publisher","first-page":"1651","DOI":"10.18653\/v1\/P19-1161","article-title":"Counterfactual data augmentation for mitigating gender stereotypes in languages with rich morphology","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Zmigrod","year":"2019"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00511\/2054690\/tacl_a_00511.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00511\/2054690\/tacl_a_00511.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T08:52:41Z","timestamp":1678351961000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00511\/113490\/Causal-Inference-in-Natural-Language-Processing"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":118,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00511","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022]]},"published":{"date-parts":[[2022]]}}}