Elamur Research⌕
☰
home / papers / 2026 / MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis

MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis

Paper · 2026 · Chengyan Wu, Bolei Ma, Ningyuan Deng et al.

Summary

The paper addresses cross-lingual aspect-based sentiment analysis (ABSA). A model trained on labeled English data must find aspect terms and their sentiment polarity in other languages that have no annotations. The authors argue that earlier translation-based approaches align languages only coarsely and do not match aspect terms closely enough.

Their framework, MSMO, treats ABSA as sequence labeling with a multilingual encoder and trains in two stages:

  • Stage 1: a Wasserstein-style language discriminator with gradient reversal aligns whole sentences. It is trained on translated parallel data and on code-switched sentences in which aspect terms are swapped between languages.
  • Stage 2: the model jointly optimizes supervised cross-entropy and a KL-based consistency loss, so that aspect terms sharing a sentiment get similar predictions across languages.

The framework is also extended to a multilingual setting, and knowledge distillation on unlabeled target-language text adds further gains. On benchmarks covering five languages, MSMO reaches state-of-the-art results with both mBERT and XLM-R. Its best variant also outperforms zero-shot and LoRA-tuned LLMs. This matters for low-resource languages, where ABSA annotation is costly.

Key points

  • The source language is English, and the target languages are French, Spanish, Dutch and Russian. The authors test cross-lingual and multilingual settings with mBERT and XLM-R encoders.
  • The code-switched data comes in two directions: target-language aspect terms placed into source sentences, and the reverse. This data feeds both the discriminator and the consistency module.
  • The best variant is MTL-MSMO-DISTLL on XLM-R, with an average F1 of 66.20 (FR 63.23, ES 70.95, NL 66.24, RU 64.36). The same variant on mBERT averages 57.00.
  • For comparison, the strongest LLMs average 48.36 F1 for GPT-4o zero-shot and 61.58 for Qwen2.5-7B + LoRA. Other LLMs tested were Gemma-2 9B, Llama-3.1 8B and Mistral 7B. Across languages, Spanish tends to score highest and French lowest.
  • Code is available at github.com/swaggy66/MSMO.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Ludwig-Maximilians-Universität MünchenMunich · Germany113 works · 56,817 citations🎓South China Normal UniversityGuangzhou · China8 works · 24 citations

Also on the byline: Institute of Scientific and Technical Information of China.

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 2Research subjects and languages the work is about.Sentiment & emotion · 1,035 worksMultilingual & cross-lingual NLP · 882 works

Cite

Cite as Chengyan Wu, Bolei Ma, Ningyuan Deng, He Yanqing, Yun Xue and Liu Xiaoyong. 2026. MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.851

@inproceedings{wu2026msmo,
  title = {{MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis}},
  author = {Chengyan Wu, Bolei Ma, Ningyuan Deng, He Yanqing, Yun Xue and Liu Xiaoyong},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.851},
  url = {https://doi.org/10.18653/v1/2026.acl-long.851}
}

References

48 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. This research was conducted in accordance with the ACM Code of Ethics. The dataset (Pontiki et al., 2016) that we use is publicly available. We report only aggregated results in the main paper. We have not intended or do not intend to share any Personally Identifiable Data with this paper. \#\# Acknow… find
  2. Martín Arjovsky, Soumith Chintala, and Léon Bottou. 2017. Wasserstein generative adversarial networks. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017, volume 70 of Proceedings of Machine Learning Research, pages 214–223. P… find
  3. Jeremy Barnes, Roman Klinger, and Sabine Schulte im Walde. 2018. Bilingual sentiment embeddings: Joint projection of sentiment across languages. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2483–2493, Melbourne, Australia.… find
  4. Irina Bigoulaeva, Viktor Hangya, Iryna Gurevych, and Alexander Fraser. 2023. Label modification and bootstrapping for zero-shot cross-lingual hate speech detection. Language Resources and Evaluation, 57(4):1515–1546. find
  5. David Z. Chen, Adam Faulkner, and Sahil Badyal. 2022. Unsupervised data augmentation for aspect based sentiment analysis. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6746–6751, Gyeongju, Republic of Korea. International Committee on Computational Linguisti… find
  6. Xilun Chen, Yu Sun, Ben Athiwaratkun, Claire Cardie, and Kilian Weinberger. 2018. Adversarial deep averaging networks for cross-lingual sentiment classification. Transactions of the Association for Computational Linguistics, 6:557–570.
  7. Kevin Clark, Minh-Thang Luong, Christopher D. Manning, and Quoc Le. 2018. Semi-supervised sequence modeling with cross-view training. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1914–1925, Brussels, Belgium. Association for Computational Linguisti…
  8. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association fo…
  9. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,…
  10. 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. find
  11. Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario March, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. Journal of Machine Learning Research, 17(59):1–35. find
  12. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — The Llama 3 Herd of Models
  13. Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations.
  14. Soufian Jebbara and Philipp Cimiano. 2019. Zero-shot cross-lingual opinion target extraction. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2486–2495, Minneapo… find
  15. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix,… find
  16. Joris Knoester, Flavius Frasincar, and Maria Mihaela Truşcundefined. 2022. Domain adversarial training for aspect-based sentiment analysis. In Web Information Systems Engineering – WISE 2022: 23rd International Conference, Biarritz, France, November 1–3, 2022, Proceedings, page 21–37, Berlin, Heide… find
  17. Patrik Lambert. 2015. Aspect-level cross-lingual sentiment classification with constrained SMT. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 781– 78… find
  18. Xin Li, Lidong Bing, Wenxuan Zhang, Zheng Li, and Wai Lam. 2021. Unsupervised cross-lingual adaptation for sequence tagging and beyond. Preprint, arXiv:2010.12405. — [arXiv:2010.12405](https://arxiv.org/abs/2010.12405) find
  19. Nankai Lin, Yingwen Fu, Xiaotian Lin, Dong Zhou, Aimin Yang, and Shengyi Jiang. 2023. Cl-xabsa: Contrastive learning for cross-lingual aspect-based sentiment analysis. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31:2935– 2946. find
  20. Nankai Lin, Meiyu Zeng, Xingming Liao, Weizhong Liu, Aimin Yang, and Dong Zhou. 2024. Addressing class-imbalance challenges in cross-lingual aspect-based sentiment analysis: Dynamic weighted loss and anti-decoupling. Expert Systems with Applications, 257:125059. find
  21. Bing Liu. 2012. Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers. find
  22. Mamta and Asif Ekbal. 2022. Adversarial sample generation for aspect based sentiment classification. In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, pages 478–492, Online only. Association for Computational Linguistics. find
  23. Yue Mao, Yi Shen, Chao Yu, and Longjun Cai. 2022. A joint training dual-mrc framework for aspect based sentiment analysis. Proceedings of the AAAI Conference on Artificial Intelligence, page 13543–13551. find
  24. Takeru Miyato, Shin ichi Maeda, Masanori Koyama, and Shin Ishii. 2017. Virtual adversarial training: A regularization method for supervised and semi-supervised learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41:1979–1993. find
  25. Takeru Miyato, Shin-Ichi Maeda, Masanori Koyama, and Shin Ishii. 2019. Virtual adversarial training: A regularization method for supervised and semi-supervised learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, page 1979–1993. find
  26. Ercong Nie, Shuzhou Yuan, Bolei Ma, Helmut Schmid, Michael Färber, Frauke Kreuter, and Hinrich Schuetze. 2025. Decomposed prompting: Probing multilingual linguistic structure knowledge in large language models. In Proceedings of the 14th International Joint Conference on Natural Language Processing… find
  27. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, and 262 others.… — GPT-4 Technical Report
  28. Maria Pontiki, Dimitris Galanis, Haris Papageorgiou, Ion Androutsopoulos, Suresh Manandhar, Mohammad AL-Smadi, Mahmoud Al-Ayyoub, Yanyan Zhao, Bing Qin, Orphée De Clercq, Véronique Hoste, Marianna Apidianaki, Xavier Tannier, Natalia Loukachevitch, Evgeniy Kotelnikov, Nuria Bel, Salud María Jiménez-Z… — SemEval-2016 Task 5: Aspect Based Sentiment Analysis
  29. Maria Pontiki, Dimitris Galanis, John Pavlopoulos, Harris Papageorgiou, Ion Androutsopoulos, and Suresh Manandhar. 2014. SemEval-2014 task 4: Aspect based sentiment analysis. In Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pages 27–35, Dublin, Ireland. Associa…
  30. Qwen, :, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, and 25 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. find
  31. Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, Johan Ferret, Peter Liu, Pouya Tafti, Abe Friesen, Michelle Casbon, Sabela Ramos, Ravin Kumar, Charline Le Lan, Sammy Jerome, and 179… find
  32. Cédric Villani. 2013. Optimal transport: Old and new. find
  33. Rui Wang and Ricardo Henao. 2021. Unsupervised paraphrasing consistency training for low resource named entity recognition. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5303–5308, Online and Punta Cana, Dominican Republic. Association for Computati… find
  34. Shuhe Wang, Xiaofei Sun, Xiaoya Li, Rongbin Ouyang, Fei Wu, Tianwei Zhang, Jiwei Li, Guoyin Wang, and Chen Guo. 2025. GPT-NER: Named entity recognition via large language models. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 4257–4275, Albuquerque, New Mexico. Assoc…
  35. Wenya Wang and Sinno Jialin Pan. 2018. Transition-based adversarial network for cross-lingual aspect extraction. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. find
  36. Xiaodong Wang, Junbao Zhuo, Shuhao Cui, Shuhui Wang, and Yuejian Fang. 2024a. Learning invariant representation with consistency and diversity for semi-supervised source hypothesis transfer. In ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), page… find
  37. Yong Wang, Ningchuang Yang, Duoqian Miao, and Qiuyi Chen. 2024b. Aspect-guided multi-graph convolutional networks for aspect-based sentiment analysis. DATA INTELLIGENCE, 6(3):771–791. find
  38. Chengyan Wu, Bolei Ma, Yihong Liu, Zheyu Zhang, Ningyuan Deng, Yanshu Li, Baolan Chen, Yi Zhang, Yun Xue, and Barbara Plank. 2025a. M-ABSA: A multilingual dataset for aspect-based sentiment analysis. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 253…
  39. Chengyan Wu, Bolei Ma, Zheyu Zhang, Ningyuan Deng, Yanqing He, and Yun Xue. 2025b. Evaluating zero-shot multilingual aspect-based sentiment analysis with large language models. International Journal of Machine Learning and Cybernetics, 16(10):8079–8101. find
  40. Qizhe Xie, Zihang Dai, Eduard Hovy, Thang Luong, and Quoc Le. 2020. Unsupervised data augmentation for consistency training. In Advances in Neural Information Processing Systems, volume 33, pages 6256–6268. Curran Associates, Inc.
  41. Kui Xu and Xiaojun Wan. 2017. Towards a universal sentiment classifier in multiple languages. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 511– 520, Copenhagen, Denmark. Association for Computational Linguistics. find
  42. Mao Zhang, Yongxin Zhu, Zhen Liu, Zhimin Bao, Yunfei Wu, Xing Sun, and Linli Xu. 2023. Span-level aspect-based sentiment analysis via table filling. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9273–9284, Toronto, Canada. A… find
  43. Wenxuan Zhang, Ruidan He, Haiyun Peng, Lidong Bing, and Wai Lam. 2021a. Cross-lingual aspect-based sentiment analysis with aspect term code-switching. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic… find
  44. Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, and Wai Lam. 2021b. Towards generative aspect-based sentiment analysis. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Shor… find
  45. Ran Zhou, Xin Li, Lidong Bing, Erik Cambria, Luo Si, and Chunyan Miao. 2022. ConNER: Consistency training for cross-lingual named entity recognition. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8438–8449, Abu Dhabi, United Arab Emirates. Associati… find
  46. Xinjie Zhou, Xiaojun Wan, and Jianguo Xiao. 2013. Collective opinion target extraction in Chinese microblogs. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1840–1850, Seattle, Washington, USA. Association for Computational Linguistics. find
  47. Xinjie Zhou, Xiaojun Wan, and Jianguo Xiao. 2015. Clopinionminer: Opinion target extraction in a cross-language scenario. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 23(4):619– 630. find
  48. Xinjie Zhou, Xiaojun Wan, and Jianguo Xiao. 2016. Cross-lingual sentiment classification with bilingual document representation learning. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1403–1412, Berlin, Germany. Association… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wu-2026-msmo-absa-multi-scale-multi/