{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:52:38Z","timestamp":1743126758465,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794300"},{"type":"electronic","value":"9789819794317"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-9431-7_22","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"284-297","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CausalAPM: Generalizable Literal Disentanglement for\u00a0NLU Debiasing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6013-3035","authenticated-orcid":false,"given":"Shihan","family":"Dou","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4900-0458","authenticated-orcid":false,"given":"Songyang","family":"Gao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8054-9021","authenticated-orcid":false,"given":"Tao","family":"Gui","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"issue":"8","key":"22_CR1","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR2","unstructured":"Besserve, M., Mehrjou, A., Sun, R., Sch\u00f6lkopf, B.: Counterfactuals uncover the modular structure of deep generative models. In: 8th International Conference on Learning Representations, ICLR 2020 (2020)"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, P., Min, M.R., Shen, D., Malon, C., Zhang, Y., Li, Y., Carin, L.: Improving disentangled text representation learning with information-theoretic guidance. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 (2020)","DOI":"10.18653\/v1\/2020.acl-main.673"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Clark, C., Yatskar, M., Zettlemoyer, L.: Learning to model and ignore dataset bias with mixed capacity ensembles. Findings of the Association for Computational Linguistics: EMNLP 2020, Online Event, 16-20 November 2020 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.272"},{"issue":"1","key":"22_CR5","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","volume":"35","author":"A Creswell","year":"2018","unstructured":"Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B., Bharath, A.A.: Generative adversarial networks: an overview. IEEE Signal Process. Mag. 35(1), 53\u201365 (2018)","journal-title":"IEEE Signal Process. Mag."},{"key":"22_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota, June 2019"},{"key":"22_CR7","unstructured":"Eastwood, C., Williams, C.K.: A framework for the quantitative evaluation of disentangled representations. In: International Conference on Learning Representations (2018)"},{"key":"22_CR8","unstructured":"Higgins, I., et al.: Towards a definition of disentangled representations. arXiv preprint arXiv:1812.02230 (2018)"},{"key":"22_CR9","unstructured":"Higgins, I., et al.: beta-vae: learning basic visual concepts with a constrained variational framework. In: International conference on learning representations (2017)"},{"key":"22_CR10","unstructured":"Kocaoglu, M., Snyder, C., Dimakis, A.G., Vishwanath, S.: CausalGAN: learning causal implicit generative models with adversarial training. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30\u2013May 3, 2018, Conference Track Proceedings (2018)"},{"key":"22_CR11","unstructured":"Mahabadi, R.K., Belinkov, Y., Henderson, J.: End-to-end bias mitigation by modelling biases in corpora. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, 5-10 July 2020 (2020)"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"McCoy, R.T., Pavlick, E., Linzen, T.: Right for the wrong reasons: diagnosing syntactic heuristics in natural language inference. Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers (2019)","DOI":"10.18653\/v1\/P19-1334"},{"key":"22_CR13","unstructured":"Mitrovic, J., McWilliams, B., Walker, J., Buesing, L., Blundell, C.: Representation learning via invariant causal mechanisms. In: 9th International Conference on Learning Representations, ICLR 2021 (2021)"},{"key":"22_CR14","unstructured":"Naik, A., Ravichander, A., Sadeh, N., Rose, C., Neubig, G.: Stress test evaluation for natural language inference. In: Proceedings of the 27th International Conference on Computational Linguistics, COLING 2018, Santa Fe, New Mexico, USA, 20-26 August 2018 (2018)"},{"issue":"3","key":"22_CR15","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1214\/ss\/1177010894","volume":"8","author":"J Pearl","year":"1993","unstructured":"Pearl, J.: Bayesian analysis in expert systems: comment: graphical models, causality and intervention. Stat. Sci. 8(3), 266\u2013269 (1993)","journal-title":"Stat. Sci."},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Pham, T.M., Bui, T., Mai, L., Nguyen, A.: Out of order: how important is the sequential order of words in a sentence in natural language understanding tasks? In: Findings of the Association for Computational Linguistics: ACL\/IJCNLP 2021, Online Event, 1\u20136 August 2021 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.98"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Poliak, A., Naradowsky, J., Haldar, A., Rudinger, R., Van\u00a0Durme, B.: Hypothesis only baselines in natural language inference. In: Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, pp. 180\u2013191. Association for Computational Linguistics, New Orleans, Louisiana, June 2018","DOI":"10.18653\/v1\/S18-2023"},{"key":"22_CR18","unstructured":"Sanh, V., Wolf, T., Belinkov, Y., Rush, A.M.: Learning from others\u2019 mistakes: avoiding dataset biases without modeling them. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3-7 May 2021 (2020)"},{"key":"22_CR19","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.neunet.2020.04.008","volume":"127","author":"J Schmidhuber","year":"2020","unstructured":"Schmidhuber, J.: Generative adversarial networks are special cases of artificial curiosity (1990) and also closely related to predictability minimization (1991). Neural Netw. 127, 58\u201366 (2020)","journal-title":"Neural Netw."},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Schuster, T., Shah, D., Yeo, Y.J.S., Roberto Filizzola\u00a0Ortiz, D., Santus, E., Barzilay, R.: Towards debiasing fact verification models. In: EMNLP-IJCNLP, pp. 3419\u20133425. Association for Computational Linguistics, Hong Kong, China, November 2019","DOI":"10.18653\/v1\/D19-1341"},{"key":"22_CR21","unstructured":"Sinha, K., Parthasarathi, P., Pineau, J., Williams, A.: Unnatural language inference. In: ACL\/IJCNLP 2021 (2021)"},{"key":"22_CR22","unstructured":"Suter, R., Miladinovic, D., Sch\u00f6lkopf, B., Bauer, S.: Robustly disentangled causal mechanisms: validating deep representations for interventional robustness. In: International Conference on Machine Learning, pp. 6056\u20136065. PMLR (2019)"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Thorne, J., Vlachos, A., Cocarascu, O., Christodoulopoulos, C., Mittal, A.: The fact extraction and VERification (FEVER) shared task. In: Proceedings of the First Workshop on Fact Extraction and VERification (FEVER), pp.\u00a01\u20139. Association for Computational Linguistics, Brussels, Belgium, November 2018","DOI":"10.18653\/v1\/W18-5501"},{"key":"22_CR24","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1162\/tacl_a_00335","volume":"8","author":"L Tu","year":"2020","unstructured":"Tu, L., Lalwani, G., Gella, S., He, H.: An empirical study on robustness to spurious correlations using pre-trained language models. Trans. Assoc. Comput. Linguist. 8, 621\u2013633 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Utama, P.A., Moosavi, N.S., Gurevych, I.: Mind the trade-off: Debiasing NLU models without degrading the in-distribution performance. In: ACL 202 (2020)","DOI":"10.18653\/v1\/2020.acl-main.770"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Utama, P.A., Moosavi, N.S., Gurevych, I.: Towards debiasing NLU models from unknown biases. In: EMNLP 2020 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.613"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Vasilakes, J., Zerva, C., Miwa, M., Ananiadou, S.: Learning disentangled representations of negation and uncertainty. In: ACL 2022 (2022)","DOI":"10.18653\/v1\/2022.acl-long.574"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: Glue: a multi-task benchmark and analysis platform for natural language understanding. In: ICLR 2019 (2019)","DOI":"10.18653\/v1\/W18-5446"},{"key":"22_CR29","unstructured":"Wen, Z., Xu, G., Tan, M., Wu, Q., Wu, Q.: Debiased visual question answering from feature and sample perspectives. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Williams, A., Nangia, N., Bowman, S.: A broad-coverage challenge corpus for sentence understanding through inference. In: NAACL, pp. 1112\u20131122. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/N18-1101"},{"key":"22_CR31","unstructured":"Xiong, R., Chen, Y., Pang, L., Cheng, X., Ma, Z.M., Lan, Y.: Uncertainty calibration for ensemble-based debiasing methods. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Yang, M., Liu, F., Chen, Z., Shen, X., Hao, J., Wang, J.: Causalvae: disentangled representation learning via neural structural causal models. In: CVPR, pp. 9593\u20139602 (2021)","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"22_CR33","unstructured":"Zhang, Y., Baldridge, J., He, L.: PAWS: paraphrase adversaries from word scrambling. In: NAACL, pp. 1298\u20131308. Association for Computational Linguistics, Minneapolis, Minnesota, Jun 2019"},{"key":"22_CR34","unstructured":"Zhao, S., Ren, H., Yuan, A., Song, J., Goodman, N., Ermon, S.: Bias and generalization in deep generative models: an empirical study. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-9431-7_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:32:20Z","timestamp":1730385140000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9431-7_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794300","9789819794317"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9431-7_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}