Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
AbstractA 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 o...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The MIT Press
2022-01-01
|
| Series: | Transactions of the Association for Computational Linguistics |
| Online Access: | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00511/113490/Causal-Inference-in-Natural-Language-Processing |
| _version_ | 1797990199324573696 |
|---|---|
| author | Amir Feder Katherine A. Keith Emaad Manzoor Reid Pryzant Dhanya Sridhar Zach Wood-Doughty Jacob Eisenstein Justin Grimmer Roi Reichart Margaret E. Roberts Brandon M. Stewart Victor Veitch Diyi Yang |
| author_facet | Amir Feder Katherine A. Keith Emaad Manzoor Reid Pryzant Dhanya Sridhar Zach Wood-Doughty Jacob Eisenstein Justin Grimmer Roi Reichart Margaret E. Roberts Brandon M. Stewart Victor Veitch Diyi Yang |
| author_sort | Amir Feder |
| collection | DOAJ |
| description |
AbstractA 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 |
| first_indexed | 2024-04-11T08:32:44Z |
| format | Article |
| id | doaj.art-ce20dd42414b496493ce8c27322a7d13 |
| institution | Directory Open Access Journal |
| issn | 2307-387X |
| language | English |
| last_indexed | 2024-04-11T08:32:44Z |
| publishDate | 2022-01-01 |
| publisher | The MIT Press |
| record_format | Article |
| series | Transactions of the Association for Computational Linguistics |
| spelling | doaj.art-ce20dd42414b496493ce8c27322a7d132022-12-22T04:34:27ZengThe MIT PressTransactions of the Association for Computational Linguistics2307-387X2022-01-01101138115810.1162/tacl_a_00511Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and BeyondAmir Feder0Katherine A. Keith1Emaad Manzoor2Reid Pryzant3Dhanya Sridhar4Zach Wood-Doughty5Jacob Eisenstein6Justin Grimmer7Roi Reichart8Margaret E. Roberts9Brandon M. Stewart10Victor Veitch11Diyi Yang12Technion - Israel Institute of Technology, IsraelWilliams College, USAUniversity of Wisconsin - Madison, USAMicrosoft, USAColumbia University, CanadaNorthwestern University, USAGoogle Research, USAStanford University, USATechnion - Israel Institute of Technology, IsraelUniversity of California San Diego, USAPrinceton University, USAGoogle Research, USAGeorgia Tech, USA AbstractA 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.1https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00511/113490/Causal-Inference-in-Natural-Language-Processing |
| spellingShingle | Amir Feder Katherine A. Keith Emaad Manzoor Reid Pryzant Dhanya Sridhar Zach Wood-Doughty Jacob Eisenstein Justin Grimmer Roi Reichart Margaret E. Roberts Brandon M. Stewart Victor Veitch Diyi Yang Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond Transactions of the Association for Computational Linguistics |
| title | Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond |
| title_full | Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond |
| title_fullStr | Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond |
| title_full_unstemmed | Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond |
| title_short | Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond |
| title_sort | causal inference in natural language processing estimation prediction interpretation and beyond |
| url | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00511/113490/Causal-Inference-in-Natural-Language-Processing |
| work_keys_str_mv | AT amirfeder causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT katherineakeith causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT emaadmanzoor causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT reidpryzant causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT dhanyasridhar causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT zachwooddoughty causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT jacobeisenstein causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT justingrimmer causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT roireichart causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT margareteroberts causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT brandonmstewart causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT victorveitch causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond AT diyiyang causalinferenceinnaturallanguageprocessingestimationpredictioninterpretationandbeyond |