Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis (2402.14536v1)

Published 22 Feb 2024 in cs.CL

Abstract: Domain adaption has been widely adapted for cross-domain sentiment analysis to transfer knowledge from the source domain to the target domain. Whereas, most methods are proposed under the assumption that the target (test) domain is known, making them fail to generalize well on unknown test data that is not always available in practice. In this paper, we focus on the problem of domain generalization for cross-domain sentiment analysis. Specifically, we propose a backdoor adjustment-based causal model to disentangle the domain-specific and domain-invariant representations that play essential roles in tackling domain shift. First, we rethink the cross-domain sentiment analysis task in a causal view to model the causal-and-effect relationships among different variables. Then, to learn an invariant feature representation, we remove the effect of domain confounders (e.g., domain knowledge) using the backdoor adjustment. A series of experiments over many homologous and diverse datasets show the great performance and robustness of our model by comparing it with the state-of-the-art domain generalization baselines.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (64)
  1. Dyah Adila and Dongyeop Kang. 2021. Understanding out-of-distribution: A perspective of data dynamics. In ICBINB@NeurIPS.
  2. Invariant risk minimization. arXiv preprint arXiv:1907.02893.
  3. PADA: Example-based prompt learning for on-the-fly adaptation to unseen domains. Transactions of the Association for Computational Linguistics, 10:414–433.
  4. PERL: Pivot-based domain adaptation for pre-trained deep contextualized embedding models. Transactions of the Association for Computational Linguistics, 8:504–521.
  5. DoCoGen: Domain counterfactual generation for low resource domain adaptation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7727–7746, Dublin, Ireland. Association for Computational Linguistics.
  6. Discriminative adversarial domain generalization with meta-learning based cross-domain validation. Neurocomputing, 467:418–426.
  7. Xilun Chen and Claire Cardie. 2018. Multinomial adversarial networks for multi-domain text classification. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1226–1240, New Orleans, Louisiana. Association for Computational Linguistics.
  8. Adversarial and domain-aware BERT for cross-domain sentiment analysis. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4019–4028, Online. Association for Computational Linguistics.
  9. Probable domain generalization via quantile risk minimization. ArXiv, abs/2207.09944.
  10. Amnesic probing: Behavioral explanation with amnesic counterfactuals. Transactions of the Association for Computational Linguistics, 9:160–175.
  11. Causal inference in natural language processing: Estimation, prediction, interpretation and beyond. Transactions of the Association for Computational Linguistics, 10:1138–1158.
  12. Exploring underexplored limitations of cross-domain text-to-SQL generalization. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8926–8931, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  13. Yaroslav Ganin and Victor S. Lempitsky. 2015. Unsupervised domain adaptation by backpropagation. In Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015, volume 37 of JMLR Workshop and Conference Proceedings, pages 1180–1189. JMLR.org.
  14. Domain-adversarial training of neural networks. The journal of machine learning research, 17(1):2096–2030.
  15. Generalized but not Robust? comparing the effects of data modification methods on out-of-domain generalization and adversarial robustness. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2705–2718, Dublin, Ireland. Association for Computational Linguistics.
  16. Multi-source domain adaptation with mixture of experts. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4694–4703, Brussels, Belgium. Association for Computational Linguistics.
  17. Diederik P. Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. CoRR, abs/1412.6980.
  18. Out-of-distribution generalization via risk extrapolation (rex). In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, volume 139 of Proceedings of Machine Learning Research, pages 5815–5826. PMLR.
  19. Virgile Landeiro and Aron Culotta. 2016. Robust text classification in the presence of confounding bias. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1).
  20. Deeper, broader and artier domain generalization. 2017 IEEE International Conference on Computer Vision (ICCV), pages 5543–5551.
  21. Domain generalization with adversarial feature learning. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5400–5409.
  22. End-to-end adversarial memory network for cross-domain sentiment classification. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17, pages 2237–2243.
  23. Just train twice: Improving group robustness without training group information. In Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research, pages 6781–6792. PMLR.
  24. Challenges in generalization in open domain question answering. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2014–2029, Seattle, United States. Association for Computational Linguistics.
  25. Counterfactual data augmentation for neural machine translation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 187–197, Online. Association for Computational Linguistics.
  26. Domain confused contrastive learning for unsupervised domain adaptation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2982–2995, Seattle, United States. Association for Computational Linguistics.
  27. Mere contrastive learning for cross-domain sentiment analysis. In Proceedings of the 29th International Conference on Computational Linguistics, pages 7099–7111, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
  28. Best sources forward: Domain generalization through source-specific nets. 2018 25th IEEE International Conference on Image Processing (ICIP), pages 1353–1357.
  29. Domain adaptation with multiple sources. In NIPS.
  30. Robust semantic parsing with adversarial learning for domain generalization. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers), pages 166–173, Minneapolis, Minnesota. Association for Computational Linguistics.
  31. Sinno Jialin Pan and Qiang Yang. 2010. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10):1345–1359.
  32. Judea Pearl et al. 2000. Models, reasoning and inference. Cambridge, UK: CambridgeUniversityPress, 19(2).
  33. Cross-domain sentiment classification with target domain specific information. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2505–2513, Melbourne, Australia. Association for Computational Linguistics.
  34. Elements of causal inference: foundations and learning algorithms. The MIT Press.
  35. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. ArXiv, abs/1911.08731.
  36. Toward causal representation learning. Proceedings of the IEEE, 109:612–634.
  37. Enhancing the generalization for intent classification and out-of-domain detection in SLU. In 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), pages 2443–2453, Online. Association for Computational Linguistics.
  38. Mixup-transformer: Dynamic data augmentation for NLP tasks. In Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), December 8-13, 2020, pages 3436–3440. International Committee on Computational Linguistics.
  39. Laurens van der Maaten and Geoffrey E. Hinton. 2008. Visualizing data using t-sne. Journal of Machine Learning Research, 9:2579–2605.
  40. Counterfactual invariance to spurious correlations: Why and how to pass stress tests. ArXiv, abs/2106.00545.
  41. Causal mediation analysis for interpreting neural nlp: The case of gender bias. ArXiv, abs/2004.12265.
  42. Generalizing to unseen domains via adversarial data augmentation. In Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc.
  43. Meta-learning for domain generalization in semantic parsing. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 366–379, Online. Association for Computational Linguistics.
  44. Generalizing to unseen domains: A survey on domain generalization. IEEE Transactions on Knowledge and Data Engineering, 35:8052–8072.
  45. Counterfactual representation augmentation for cross-domain sentiment analysis. IEEE Transactions on Affective Computing.
  46. Causal intervention improves implicit sentiment analysis. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6966–6977, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
  47. Zhao Wang and Aron Culotta. 2020. Identifying spurious correlations for robust text classification. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3431–3440, Online. Association for Computational Linguistics.
  48. Dustin Wright and Isabelle Augenstein. 2020. Transformer based multi-source domain adaptation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7963–7974, Online. Association for Computational Linguistics.
  49. Hui Wu and Xiaodong Shi. 2022. Adversarial soft prompt tuning for cross-domain sentiment analysis. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2438–2447, Dublin, Ireland. Association for Computational Linguistics.
  50. De-biased court’s view generation with causality. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 763–780, Online. Association for Computational Linguistics.
  51. Yuan Wu and Yuhong Guo. 2020. Dual adversarial co-learning for multi-domain text classification. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04):6438–6445.
  52. Cross-domain review generation for aspect-based sentiment analysis. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 4767–4777, Online. Association for Computational Linguistics.
  53. Jianfei Yu and Jing Jiang. 2016. Learning sentence embeddings with auxiliary tasks for cross-domain sentiment classification. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 236–246, Austin, Texas. Association for Computational Linguistics.
  54. mixup: Beyond empirical risk minimization. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net.
  55. Sentiment analysis and opinion mining. In Synthesis Lectures on Human Language Technologies.
  56. De-biasing distantly supervised named entity recognition via causal intervention. In 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), pages 4803–4813, Online. Association for Computational Linguistics.
  57. Adversarial multiple source domain adaptation. In Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc.
  58. SentiX: A sentiment-aware pre-trained model for cross-domain sentiment analysis. In Proceedings of the 28th International Conference on Computational Linguistics, pages 568–579, Barcelona, Spain (Online). International Committee on Computational Linguistics.
  59. Yftah Ziser and Roi Reichart. 2018. Pivot based language modeling for improved neural domain adaptation. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1241–1251, New Orleans, Louisiana. Association for Computational Linguistics.
  60. Counterfactual data augmentation for mitigating gender stereotypes in languages with rich morphology. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1651–1661, Florence, Italy. Association for Computational Linguistics.
  61. Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification. Association for Computational Linguistics.
  62. Learning Word Vectors for Sentiment Analysis. Association for Computational Linguistics.
  63. Character-level Convolutional Networks for Text Classification. Curran Associates, Inc.
  64. Neural Structural Correspondence Learning for Domain Adaptation. Association for Computational Linguistics.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now