Elamur Research⌕
☰
home / papers / 2026 / Exploring Multilingual Pre-trained Language Model for Aspect-based Sentiment Analysis

Exploring Multilingual Pre-trained Language Model for Aspect-based Sentiment Analysis

Paper · 2026 · Ye Wang, Ruijun Jiang, Zhongqing Wang et al.

Summary

This work targets aspect-based sentiment analysis (ABSA) framed as quadruple prediction (aspect, opinion, category, polarity). Labeled data for this task is scarce, especially outside English, and even English F1 stays below 50%. The authors propose a Cross-lingual Knowledge Fusion (CKF) framework. First, a large language model with a ten-shot prompt translates review texts and their labels into other languages (English, Chinese, Japanese, German) while keeping label alignment intact. Next, a multilingual model is pre-trained on bilingual tasks built from source and target sentences and labels:

  • translation in both directions
  • sentence-to-label and label-to-sentence mapping
  • cross-lingual variants of these mappings

These tasks are used individually (single-round) or combined as two-round fusions, for example Translation Fusion and Monolingual Reconstruction Fusion. The model is then fine-tuned for ABSA. CKF improves over monolingual training and over simpler ways of mixing languages in all four languages. This shows that structured cross-lingual pre-training can partly compensate for small annotated datasets in low-resource languages.

Key points

  • F1 rises over the monolingual baseline in every language: EN 43.34 → 46.51, CN 75.17 → 77.25, JP 69.48 → 72.18, DE 81.24 → 83.49.
  • CKF beats naive integration baselines that use the same bilingual data (MultiInput, MultiOutput, MultiInOut). The strongest of these, MultiInOut, reaches EN 44.21 and DE 82.49.
  • Translation quality was measured with BLEU on 500 manually annotated samples and compared against Qwen-Plus, LLaMA-3.1-8B and ChatGPT-4o-mini. The authors' setup scored best or near-best, and better translations tracked with better downstream F1.
  • Adding a second auxiliary language often helps further, e.g. EN + JP & CN reaches 46.25 F1.
  • Stated limitations:
    • Training cost grows as more languages are added, even with LoRA.
    • Translations require human verification.
    • The approach has been evaluated on only a limited range of domains and languages.

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

🎓Soochow UniversitySuzhou · China63 works · 4,507 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 3,320 worksSentiment & emotion · 972 worksMultilingual & cross-lingual NLP · 828 works

Cite

Cite as Ye Wang, Ruijun Jiang, Zhongqing Wang and Guodong Zhou. 2026. Exploring Multilingual Pre-trained Language Model for Aspect-based Sentiment Analysis. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.298

@inproceedings{wang2026exploring,
  title = {{Exploring Multilingual Pre-trained Language Model for Aspect-based Sentiment Analysis}},
  author = {Ye Wang, Ruijun Jiang, Zhongqing Wang and Guodong Zhou},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.298},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.298}
}

References

40 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Xiaoyi Bao, Wang Zhongqing, Xiaotong Jiang, Rong Xiao, and Shoushan Li. 2022. Aspect-based sentiment analysis with opinion tree generation. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 4044–4050. International Joint Conferences on Arti… find
  2. Tom B. Brown, Ben Mann, Nick Ryder, Amanda Subbiah, Jack Kaplan, Prafulla Dhariwal, A. Neelakantan, K. Zirnheld, and Dario Amodei. 2020. Language models are few-shot learners. Advances in Neural Information Processing Systems.
  3. Hongjie Cai, Rui Xia, and Jianfei Yu. 2021. Aspect-category-opinion-sentiment quadruple extraction with implicit aspects and opinions. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing…
  4. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chengg… — DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
  5. Rui Fan, Shu Li, Tingting He, and Yu Liu. 2025. Aspect-based sentiment analysis with syntax-opinion-sentiment reasoning chain. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3123–3137, Abu Dhabi, UAE. Association for Computational Linguistics. find
  6. Aleksandra Gabryszak and Philippe Thomas. 2022. MobASA: Corpus for aspect-based sentiment analysis and social inclusion in the mobility domain. find
  7. In Proceedings of the First Computing Social Responsibility Workshop within the 13th Language Resources and Evaluation Conference, pages 35–39, Marseille, France. European Language Resources Association. find
  8. Zhibin Gou, Qingyan Guo, and Yujiu Yang. 2023. MvP: Multi-view prompting improves aspect sentiment tuple prediction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4380–4397, Toronto, Canada. Association for Computational Lin… find
  9. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models.
  10. 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
  11. Diederik P. Kingma and Jimmy Ba. 2014. A method for stochastic optimization. abs/1412.6980.
  12. Adam: CoRR, 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
  13. Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2021. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing.
  14. Yue Mao, Yi Shen, Jingchao Yang, Xiaoying Zhu, and Longjun Cai. 2022. Seq2Path: Generating sentiment tuples as paths of a tree. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2215–2225, Dublin, Ireland. Association for Computational Linguistics. find
  15. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Annual Meeting of the Association for Computational Linguistics.
  16. Haiyun Peng, Lu Xu, Lidong Bing, Fei Huang, Wei Lu, and Luo Si. 2020. Knowing what, how and why: A near complete solution for aspect-based sentiment analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):8600–8607. find
  17. Matthew E. Peters, Waleed Ammar, Chandra Bhagavatula, and Russell Power. 2017. Semi-supervised sequence tagging with bidirectional language models. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1756–1765, Vancouver, Canada.…
  18. Guang Qiu, Bing Liu, Jiajun Bu, and Chun Chen. 2011. Opinion word expansion and target extraction through double propagation. Computational Linguistics, 37(1):9–27.
  19. Colin Raffel, Noam M. Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21:140:1– 140:67.
  20. Sebastian Ruder, Ivan Vulić, and Anders Søgaard. 2019. A survey of cross-lingual word embedding models. Journal of Artificial Intelligence Research, 65:569–631. find
  21. Jakub Šmíd, Pavel Priban, and Pavel Kral. 2025. LACA: Improving cross-lingual aspect-based sentiment analysis with LLM data augmentation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 839–853, Vienna, Austria. Association fo… find
  22. Fábio Souza, Rodrigo Nogueira, and Roberto de Alencar Lotufo. 2019. Portuguese named entity recognition using bert-crf. ArXiv, abs/1909.10649. find
  23. Guixin Su, Yongcheng Zhang, Tongguan Wang, Mingmin Wu, and Ying Sha. 2025. Unified grid tagging scheme for aspect sentiment quad prediction. In Proceedings of the 31st International Conference on Computational Linguistics, pages 3997–4010, Abu Dhabi, UAE. Association for Computational Linguistics. find
  24. Duyu Tang, Bing Qin, Xiaocheng Feng, and Ting Liu. 2016. Effective LSTMs for target-dependent sentiment classification. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3298– 3307, Osaka, Japan.
  25. The COLING 2016 Organizing Committee. find
  26. Erik F. Tjong Kim Sang and Fien De Meulder. 2003. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003, pages 142–147.
  27. Hugo Touvron, David Vial, François Yvon, David Grangier, Sergey Edunov, and et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
  28. Hai Wan, Yufei Yang, Jianfeng Du, Yanan Liu, Kunxun Qi, and Jeff Z. Pan. 2020. Target-aspect-sentiment joint detection for aspect-based sentiment analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05):9122–9129. find
  29. Ye Wang, Yuan Zhong, Xu Zhang, Conghui Niu, Dong Yu, and Pengyuan Liu. 2023. CCD-ASQP: A Chinese Cross-Domain Aspect Sentiment Quadruple Prediction Dataset, pages 233–245. find
  30. Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 504–510, Online. Association for Computational Linguistics. find
  31. Yequan Wang, Minlie Huang, Xiaoyan Zhu, and Li Zhao. 2016. Attention-based LSTM for aspect-level sentiment classification. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 606–615, Austin, Texas. Association for Computational Linguistics.
  32. Xinjie Zhou, Xiaojun Wan, and Jianguo Xiao. 2015a. Clopinionminer: opinion target extraction in a cross-language scenario. IEEE/ACM Trans. Audio, Speech and Lang. Proc., 23(4):619–630. find
  33. Chengyan Wu, Bolei Ma, Ningyuan Deng, Yanqing He, and Yun Xue. 2025. Multi-scale and multi-objective optimization for cross-lingual aspect-based sentiment analysis. find
  34. Hang Yan, Junqi Dai, Tuo Ji, Xipeng Qiu, and Zheng Zhang. 2021. A unified generative framework for 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 (V…
  35. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, Jianxin Yang, Jin Xu, Jingren Zhou, Jinze Bai, Jinzheng He, Juny… find
  36. Wenxuan Zhang, Yang Deng, Xin Li, Yifei Yuan, Lidong Bing, and Wai Lam. 2021a. Aspect sentiment quad prediction as paraphrase generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9209– 9219, Online and Punta Cana, Dominican Republic. Associatio…
  37. Wenxuan Zhang, Ruidan He, Haiyun Peng, Lidong Bing, and Wai Lam. 2021b. Cross-lingual aspect-based sentiment analysis with aspect term code-switching. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9220–9230, Online and Punta Cana, Dominican Republic… find
  38. Wenxuan Zhang, Xin Li, Yang Deng, Lidong Bing, and Wai Lam. 2021c. Towards generative aspect-based sentiment analysis. In Proceedings of the 59th Annual Meeting of the Association for Computational Xinjie Zhou, Xiaojun Wan, and Jianguo Xiao. 2015b. Representation learning for aspect category detecti… find
  39. Wenhao Zhu, Hao Zhou, Changjiang Gao, Sizhe Liu, and Shu-Hua Huang. 2023. Research development of machine translation and large language models. In China National Conference on Chinese Computational Linguistics. find
  40. Jakub Šmíd, Pavel Přibáň, and Pavel Král. 2025. Advancing cross-lingual aspect-based sentiment analysis with llms and constrained decoding for sequence-to-sequence models. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence, page 757–766. SCITEPRESS - Science… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-exploring-multilingual-pre-trained-language/