{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T02:06:34Z","timestamp":1776996394425,"version":"3.51.4"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62376018"],"award-info":[{"award-number":["62376018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62376018"],"award-info":[{"award-number":["62376018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-024-06887-z","type":"journal-article","created":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T03:30:22Z","timestamp":1736566222000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Estimating textual treatment effect via causal disentangled representation learning"],"prefix":"10.1007","volume":"81","author":[{"given":"Zhimi","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,11]]},"reference":[{"issue":"1","key":"6887_CR1","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1111\/j.1468-0262.2006.00655.x","volume":"74","author":"Alberto Abadie","year":"2006","unstructured":"Abadie Alberto, Imbens Guido W. (2006) Large sample properties of matching estimators for average treatment effects. Econometrica 74(1):235\u2013267. https:\/\/doi.org\/10.1111\/j.1468-0262.2006.00655.x","journal-title":"Econometrica"},{"issue":"10","key":"6887_CR2","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1038\/nmeth.3587","volume":"12","author":"N Altman","year":"2015","unstructured":"Altman N, Krzywinski M (2015) Points of significance: association, correlation and causation. Nat Methods 12(10):899\u2013900. https:\/\/doi.org\/10.1038\/nmeth.3587","journal-title":"Nat Methods"},{"key":"6887_CR3","unstructured":"Araci D (2019) Finbert: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:1908.10063"},{"key":"6887_CR4","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s41237-016-0008-2","volume":"44","author":"K Chalupka","year":"2017","unstructured":"Chalupka K, Eberhardt F, Perona P (2017) Causal feature learning: an overview. Behaviormetrika 44:137\u2013164. https:\/\/doi.org\/10.1007\/s41237-016-0008-2","journal-title":"Behaviormetrika"},{"key":"6887_CR5","doi-asserted-by":"publisher","unstructured":"Cheng D, Xie Y, Xu Z, et\u00a0al (2023) Disentangled latent representation learning for tackling the confounding m-bias problem in causal inference. In: 2023 IEEE International Conference on Data Mining (ICDM), IEEE, pp 51\u201360, https:\/\/doi.org\/10.1109\/ICDM58522.2023.00014","DOI":"10.1109\/ICDM58522.2023.00014"},{"key":"6887_CR6","doi-asserted-by":"publisher","unstructured":"Cheng M, Liao X, Liu Q, et\u00a0al (2022) Learning disentangled representations for counterfactual regression via mutual information minimization. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp 1802\u20131806, https:\/\/doi.org\/10.1145\/3477495.3532011","DOI":"10.1145\/3477495.3532011"},{"key":"6887_CR7","unstructured":"Cheng P, Hao W, Dai S, et\u00a0al (2020) Club: A contrastive log-ratio upper bound of mutual information. In: International Conference on Machine Learning, PMLR, pp 1779\u20131788"},{"issue":"1","key":"6887_CR8","doi-asserted-by":"publisher","first-page":"C1","DOI":"10.1111\/ectj.12097","volume":"21","author":"V Chernozhukov","year":"2018","unstructured":"Chernozhukov V, Chetverikov D, Demirer M et al (2018) Double\/debiased machine learning for treatment and structural parameters. Economet J 21(1):C1\u2013C68. https:\/\/doi.org\/10.1111\/ectj.12097","journal-title":"Economet J"},{"key":"6887_CR9","doi-asserted-by":"publisher","unstructured":"Chowdhary K, Chowdhary K (2020) Natural language processing. Fundamentals of artificial intelligence pp 603\u2013649. https:\/\/doi.org\/10.1007\/978-81-322-3972-7_19","DOI":"10.1007\/978-81-322-3972-7_19"},{"key":"6887_CR10","doi-asserted-by":"crossref","unstructured":"Daoud A, Jerzak CT, Johansson R (2022) Conceptualizing treatment leakage in text-based causal inference. arXiv preprint arXiv:2205.00465","DOI":"10.18653\/v1\/2022.naacl-main.413"},{"key":"6887_CR11","unstructured":"Deng Z, Zheng X, Tian H, et\u00a0al (2022) Deep causal learning: representation, discovery and inference. arXiv preprint arXiv:2211.03374"},{"key":"6887_CR12","unstructured":"Devlin J, Chang MW, Lee K, et\u00a0al (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"issue":"42","key":"6887_CR13","doi-asserted-by":"publisher","first-page":"eabg2652","DOI":"10.1126\/sciadv.abg2652","volume":"8","author":"N Egami","year":"2022","unstructured":"Egami N, Fong CJ, Grimmer J, Roberts ME, Stewart BM (2022) How to make causal inferences using texts. Sci Adv 8(42):eabg2652. https:\/\/doi.org\/10.1126\/sciadv.abg2652","journal-title":"Sci Adv"},{"key":"6887_CR14","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.1162\/tacl_a_00511","volume":"10","author":"A Feder","year":"2022","unstructured":"Feder A, Keith KA, Manzoor E et al (2022) Causal inference in natural language processing: estimation, prediction, interpretation and beyond. Trans Assoc Comput Linguist 10:1138\u20131158. https:\/\/doi.org\/10.1162\/tacl_a_00511","journal-title":"Trans Assoc Comput Linguist"},{"key":"6887_CR15","doi-asserted-by":"crossref","unstructured":"Fong C, Grimmer J (2016) Discovery of treatments from text corpora. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 1600\u20131609","DOI":"10.18653\/v1\/P16-1151"},{"key":"6887_CR16","doi-asserted-by":"publisher","unstructured":"Gill M, Hall A (2015) How judicial identity changes the text of legal rulings. Available at SSRN 262078. https:\/\/doi.org\/10.2139\/ssrn.2620781","DOI":"10.2139\/ssrn.2620781"},{"issue":"2","key":"6887_CR17","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1111\/biom.12788","volume":"74","author":"J H\u00e4ggstr\u00f6m","year":"2018","unstructured":"H\u00e4ggstr\u00f6m J (2018) Data-driven confounder selection via Markov and Bayesian networks. Biometrics 74(2):389\u2013398. https:\/\/doi.org\/10.1111\/biom.12788","journal-title":"Biometrics"},{"issue":"4","key":"6887_CR18","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1017\/S0033291720005127","volume":"51","author":"G Hammerton","year":"2021","unstructured":"Hammerton G, Munaf\u00f2 MR (2021) Causal inference with observational data: the need for triangulation of evidence. Psychological Med 51(4):563\u2013578. https:\/\/doi.org\/10.1017\/S0033291720005127","journal-title":"Psychological Med"},{"key":"6887_CR19","unstructured":"Hassanpour N, Greiner R (2019) Learning disentangled representations for counterfactual regression. In: International Conference on Learning Representations"},{"key":"6887_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41259-7","volume-title":"Statistical causal inferences and their applications in public health research","author":"H He","year":"2016","unstructured":"He H, Wu P, Chen DG et al (2016) Statistical causal inferences and their applications in public health research. Springer"},{"key":"6887_CR21","unstructured":"Higgins I, Matthey L, Pal A, et\u00a0al (2017) beta-vae: Learning basic visual concepts with a constrained variational framework. ICLR (Poster) 3"},{"issue":"1","key":"6887_CR22","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1198\/jcgs.2010.08162","volume":"20","author":"JL Hill","year":"2011","unstructured":"Hill JL (2011) Bayesian nonparametric modeling for causal inference. J Comput Graph Stat 20(1):217\u2013240. https:\/\/doi.org\/10.1198\/jcgs.2010.08162","journal-title":"J Comput Graph Stat"},{"key":"6887_CR23","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139025751","volume-title":"Causal inference in statistics, social, and biomedical sciences","author":"GW Imbens","year":"2015","unstructured":"Imbens GW, Rubin DB (2015) Causal inference in statistics, social, and biomedical sciences. Cambridge University Press"},{"key":"6887_CR24","doi-asserted-by":"publisher","first-page":"15169","DOI":"10.1007\/s11042-018-6894-4","volume":"78","author":"H Jelodar","year":"2019","unstructured":"Jelodar H, Wang Y, Yuan C et al (2019) Latent dirichlet allocation (lda) and topic modeling: models, applications, a survey. Multimed Tools Appl 78:15169\u201315211. https:\/\/doi.org\/10.1007\/s11042-018-6894-4","journal-title":"Multimed Tools Appl"},{"key":"6887_CR25","unstructured":"Johansson F, Shalit U, Sontag D (2016) Learning representations for counterfactual inference. In: International Conference on Machine Learning, PMLR, pp 3020\u20133029"},{"issue":"4","key":"6887_CR26","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1214\/07-sts227","volume":"22","author":"JDY Kang","year":"2007","unstructured":"Kang JDY, Schafer JL (2007) Demystifying double robustness: a comparison of alternative strategies for estimating a population mean from incomplete data. Stat Sci 22(4):523\u2013539. https:\/\/doi.org\/10.1214\/07-sts227","journal-title":"Stat Sci"},{"key":"6887_CR27","doi-asserted-by":"publisher","unstructured":"Keith K, Jensen D, O\u2019Connor B (2020) Text and causal inference: A review of using text to remove confounding from causal estimates. In: Jurafsky D, Chai J, Schluter N, et\u00a0al (eds) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, pp 5332\u20135344, https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.474","DOI":"10.18653\/v1\/2020.acl-main.474"},{"key":"6887_CR28","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114"},{"key":"6887_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.yjbinx.2019.100058","volume":"100","author":"A Koroleva","year":"2019","unstructured":"Koroleva A, Kamath S, Paroubek P (2019) Measuring semantic similarity of clinical trial outcomes using deep pre-trained language representations. J Biomed Inf 100:100058. https:\/\/doi.org\/10.1016\/j.yjbinx.2019.100058","journal-title":"J Biomed Inf"},{"key":"6887_CR30","doi-asserted-by":"crossref","unstructured":"van\u00a0der Laan M, Rose S (2011) Targeted Learning: Causal Inference for Observational and Experimental Data. Springer Series in Statistics, Springer New York, https:\/\/books.google.com.tw\/books?id=RGnSX5aCAgQC","DOI":"10.1007\/978-1-4419-9782-1"},{"key":"6887_CR31","doi-asserted-by":"crossref","unstructured":"Liu X, Yin D, Feng Y, et\u00a0al (2021) Everything has a cause: Leveraging causal inference in legal text analysis. In: North American Chapter of the Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.naacl-main.155"},{"key":"6887_CR32","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1162\/tacl_a_00005","volume":"6","author":"Y Liu","year":"2018","unstructured":"Liu Y, Lapata M (2018) Learning structured text representations. Trans Assoc Comput Linguist 6:63\u201375. https:\/\/doi.org\/10.1162\/tacl_a_00005","journal-title":"Trans Assoc Comput Linguist"},{"key":"6887_CR33","unstructured":"Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101"},{"key":"6887_CR34","unstructured":"Louizos C, Shalit U, Mooij JM, et\u00a0al (2017) Causal effect inference with deep latent-variable models. Adv Neural Inf Process Syst 30"},{"key":"6887_CR35","unstructured":"Maiya AS (2021) Causalnlp: A practical toolkit for causal inference with text. arXiv preprint arXiv:2106.08043"},{"key":"6887_CR36","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511803161","volume-title":"Causality","author":"J Pearl","year":"2009","unstructured":"Pearl J (2009) Causality. Cambridge University Press"},{"key":"6887_CR37","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"6887_CR38","doi-asserted-by":"publisher","unstructured":"Pryzant R, Card D, Jurafsky D, et\u00a0al (2021) Causal effects of linguistic properties. In: Toutanova K, Rumshisky A, Zettlemoyer L, et\u00a0al (eds) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, pp 4095\u20134109https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.323","DOI":"10.18653\/v1\/2021.naacl-main.323"},{"issue":"4","key":"6887_CR39","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1111\/ajps.12526","volume":"64","author":"ME Roberts","year":"2020","unstructured":"Roberts ME, Stewart BM, Nielsen RA (2020) Adjusting for confounding with text matching. Am J Political Sci 64(4):887\u2013903. https:\/\/doi.org\/10.1111\/ajps.12526","journal-title":"Am J Political Sci"},{"issue":"1","key":"6887_CR40","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1093\/biomet\/70.1.41","volume":"70","author":"PR Rosenbaum","year":"1983","unstructured":"Rosenbaum PR, Rubin DB (1983) The central role of the propensity score in observational studies for causal effects. Biometrika 70(1):41\u201355. https:\/\/doi.org\/10.1093\/biomet\/70.1.41","journal-title":"Biometrika"},{"issue":"5","key":"6887_CR41","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1037\/h0037350","volume":"66","author":"DB Rubin","year":"1974","unstructured":"Rubin DB (1974) Estimating causal effects of treatments in randomized and nonrandomized studies. J Edu Psychol 66(5):688. https:\/\/doi.org\/10.1037\/h0037350","journal-title":"J Edu Psychol"},{"issue":"5","key":"6887_CR42","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1109\/JPROC.2021.3058954","volume":"109","author":"B Sch\u00f6lkopf","year":"2021","unstructured":"Sch\u00f6lkopf B, Locatello F, Bauer S et al (2021) Toward causal representation learning. Proc IEEE 109(5):612\u2013634. https:\/\/doi.org\/10.1109\/JPROC.2021.3058954","journal-title":"Proc IEEE"},{"issue":"1","key":"6887_CR43","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1093\/aje\/kww165","volume":"185","author":"MS Schuler","year":"2017","unstructured":"Schuler MS, Rose S (2017) Targeted maximum likelihood estimation for causal inference in observational studies. Am J Epidemiol 185(1):65\u201373. https:\/\/doi.org\/10.1093\/aje\/kww165","journal-title":"Am J Epidemiol"},{"key":"6887_CR44","unstructured":"Shalit U, Johansson FD, Sontag D (2017) Estimating individual treatment effect: generalization bounds and algorithms. In: International Conference on Machine Learning, PMLR, pp 3076\u20133085"},{"key":"6887_CR45","unstructured":"Shi C, Blei D, Veitch V (2019) Adapting neural networks for the estimation of treatment effects. Adv Neural Inf Process Syst 32"},{"key":"6887_CR46","doi-asserted-by":"crossref","unstructured":"Tan C, Lee L, Pang B (2014) The effect of wording on message propagation: Topic-and author-controlled natural experiments on twitter. arXiv preprint arXiv:1405.1438","DOI":"10.3115\/v1\/P14-1017"},{"key":"6887_CR47","unstructured":"Veitch V, Sridhar D, Blei D (2020) Adapting text embeddings for causal inference. In: Conference on Uncertainty in Artificial Intelligence, PMLR, pp 919\u2013928"},{"key":"6887_CR48","doi-asserted-by":"publisher","unstructured":"Vowels MJ, Camgoz NC, Bowden R (2021) Targeted vae: Variational and targeted learning for causal inference. In: 2021 IEEE International Conference on Smart Data Services (SMDS), IEEE, pp 132\u2013141, https:\/\/doi.org\/10.1109\/SMDS53860.2021.00027","DOI":"10.1109\/SMDS53860.2021.00027"},{"key":"6887_CR49","doi-asserted-by":"publisher","unstructured":"Weld G, West P, Glenski M, et\u00a0al (2022) Adjusting for confounders with text: Challenges and an empirical evaluation framework for causal inference. In: Proceedings of the International AAAI Conference on Web And Social Media, pp 1109\u20131120, https:\/\/doi.org\/10.1609\/icwsm.v16i1.19362","DOI":"10.1609\/icwsm.v16i1.19362"},{"key":"6887_CR50","doi-asserted-by":"crossref","unstructured":"Wood-Doughty Z, Shpitser I, Dredze M (2018) Challenges of using text classifiers for causal inference. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing, NIH Public Access, p 4586","DOI":"10.18653\/v1\/D18-1488"},{"issue":"5","key":"6887_CR51","doi-asserted-by":"publisher","first-page":"4989","DOI":"10.1109\/TKDE.2022.3150807","volume":"35","author":"A Wu","year":"2022","unstructured":"Wu A, Yuan J, Kuang K et al (2022) Learning decomposed representations for treatment effect estimation. IEEE Trans Knowl Data Eng 35(5):4989\u20135001. https:\/\/doi.org\/10.1109\/TKDE.2022.3150807","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"6887_CR52","unstructured":"Yao L, Li S, Li Y, et\u00a0al (2018) Representation learning for treatment effect estimation from observational data. Advances in neural information processing systems 31"},{"key":"6887_CR53","doi-asserted-by":"publisher","unstructured":"Yao L, Li S, Li Y, et\u00a0al (2019) On the estimation of treatment effect with text covariates. In: International Joint Conference on Artificial Intelligence, https:\/\/doi.org\/10.24963\/ijcai.2019\/570","DOI":"10.24963\/ijcai.2019\/570"},{"issue":"5","key":"6887_CR54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3444944","volume":"15","author":"L Yao","year":"2021","unstructured":"Yao L, Chu Z, Li S et al (2021) A survey on causal inference. ACM Trans Knowl Discov from Data (TKDD) 15(5):1\u201346. https:\/\/doi.org\/10.1145\/3444944","journal-title":"ACM Trans Knowl Discov from Data (TKDD)"},{"key":"6887_CR55","doi-asserted-by":"crossref","unstructured":"Yin W, Hay J, Roth D (2019) Benchmarking zero-shot text classification: Datasets, evaluation and entailment approach. arXiv preprint arXiv:1909.00161","DOI":"10.18653\/v1\/D19-1404"},{"key":"6887_CR56","unstructured":"Yoon J, Jordon J, Van Der\u00a0Schaar M (2018) Ganite: Estimation of individualized treatment effects using generative adversarial nets. In: International conference on learning representations"},{"key":"6887_CR57","doi-asserted-by":"publisher","unstructured":"Zhang W, Liu L, Li J (2021) Treatment effect estimation with disentangled latent factors. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 10923\u201310930, https:\/\/doi.org\/10.1609\/aaai.v35i12.17304","DOI":"10.1609\/aaai.v35i12.17304"},{"key":"6887_CR58","doi-asserted-by":"crossref","unstructured":"Zhou Y, He Y (2023) Causal inference from text: Unveiling interactions between variables. arXiv preprint arXiv:2311.05286","DOI":"10.18653\/v1\/2023.findings-emnlp.709"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06887-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06887-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06887-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T04:30:17Z","timestamp":1736569817000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06887-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,11]]},"references-count":58,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,1]]}},"alternative-id":["6887"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06887-z","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,11]]},"assertion":[{"value":"23 December 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"386"}}