Elamur Research⌕
☰
home / papers / 2026 / Multilingual Target-Stance Extraction

Multilingual Target-Stance Extraction

Summary

Target-Stance Extraction (TSE) asks a system to determine both what a document is about and the author's stance toward it, without being given the target. Earlier TSE work covered only English. This paper builds the first multilingual TSE benchmark by combining existing stance corpora in Catalan, Spanish, Estonian, French, Italian and Mandarin. It also adapts the TSE pipeline so that one shared set of models handles every language. In the first stage, an mT5 model fine-tuned on a machine-translated keyphrase-generation corpus generates a free-form target. In the second, a BERTweet classifier predicts stance from the original text and that generated target. For automatic evaluation, FastText similarity maps each generated target onto a fixed pool of targets, using English verbalizations only. The pipeline reaches an F1 of 12.78, well below English-only results. Target prediction is the main weak point. The authors also show that scores depend on how targets are phrased. The work gives future multilingual opinion-mining research a reference dataset, method and evaluation protocol.

Key points

  • The benchmark has ten targets drawn from existing corpora:
    • Catalan/Spanish Catalonian independence (Zotova et al., 2020)
    • Estonian immigration (Mets et al., 2024)
    • French election candidates Macron and LePen (Lai et al., 2020)
    • Italian Sardinian independence (SardiStance)
    • Five Mandarin topics from NLPCC 2016, such as second births, firecrackers and iPhone SE
  • The authors used Target Generation rather than Target Classification. Because each corpus has its own distinct targets, a classifier head could simply memorize which targets belong to which corpus.
  • Predicted targets must be in the same language as the input document. Duplicate keyphrases in the mT5 output are removed during postprocessing.
  • The best end-to-end F1 is 12.78, and the target-prediction stage is the identified bottleneck.
  • This is the first study to show that TSE F1 changes with the wording of target verbalizations. The comparison covered original, GPT-OSS-shortened (2–3 words) and manually shortened versions. Code and data scripts are available at github.com/elmines/multiling_tse.

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

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/3q975uotc5m6

@inproceedings{mines2026multilingual,
  title = {{Multilingual Target-Stance Extraction}},
  author = {Mines, Ethan Leigh and Dorr, Bonnie J.},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/3q975uotc5m6},
  url = {https://doi.org/10.63317/3q975uotc5m6}
}

References

49 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abu Ubaida Akash, Ahmed Fahmy, and Amine Trabelsi. 2025. Can large language models address open-target stance detection? In Findings of the Association for Computational Linguistics: ACL 2025, pages 971–985, Vienna, Austria. Association for Computational Linguistics. find our card
  2. Emily Allaway, Malavika Srikanth, and Kathleen McKeown. 2021. Adversarial learning for zero-shot stance detection on social media. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4756–4767, Onlin… find our card
  3. Isabelle Augenstein, Tim Rocktäschel, Andreas Vlachos, and Kalina Bontcheva. 2016. Stance detection with bidirectional conditional encoding. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 876–885, Austin, Texas. Association for Computational Linguist… find our card
  4. Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5:135–146. find
  5. Hongzhou Chen, Ke Yan, Mustafa Raad Kadhim, Kui Wu, and Ling Tian. 2024. find
  6. SentKB-BERT: Sentiment-filtered Knowledge-based Stance Detection. In 2024 International Joint Conference on Neural Networks (IJCNN), pages 1–7. ISSN: 2161-4407. find
  7. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. find
  8. Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, and Armand Joulin. 2020. Beyond english-centric multiling… find
  9. Ygor Gallina, Florian Boudin, and Beatrice Daille. 2019. KPTimes: A large-scale dataset for keyphrase generation on news documents. In Proceedings of the 12th International Conference on Natural Language Generation, pages 130–135, Tokyo, Japan. Association for Computational Linguistics. find
  10. Momchil Hardalov, Arnav Arora, Preslav Nakov, and Isabelle Augenstein. 2022. Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-training. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10):10729– 10737. Number: 10. find
  11. Zihao He, Negar Mokhberian, and Kristina Lerman. 2022. Infusing knowledge from Wikipedia to enhance stance detection. In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, pages 71–77, Dublin, Ireland. Association for Computational Lingui… find our card
  12. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the… find our card
  13. Ang Li, Bin Liang, Jingqian Zhao, Bowen Zhang, Min Yang, and Ruifeng Xu. 2023a. Stance detection on social media with background knowledge. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15703–15717, Singapore. Association for Computational Linguisti… find our card
  14. Yingjie Li, Krishna Garg, and Cornelia Caragea. 2023b. A new direction in stance detection: Target-stance extraction in the wild. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10071–10085, Toronto, Canada. Association for Co… find our card
  15. Bin Liang, Yonghao Fu, Lin Gui, Min Yang, Jiachen Du, Yulan He, and Ruifeng Xu. 2021. Target-adaptive Graph for Cross-target Stance Detection. In Proceedings of the Web Conference 2021, WWW ’21, pages 3453–3464, New York, NY, USA. Association for Computing Machinery. find
  16. Bin Liang, Qinglin Zhu, Xiang Li, Min Yang, Lin Gui, Yulan He, and Ruifeng Xu. 2022. JointCL: A joint contrastive learning framework for zero-shot stance detection. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 81–91, Dublin… find our card
  17. Rui Liu, Zheng Lin, Yutong Tan, and Weiping Wang. 2021. Enhancing zero-shot and few-shot stance detection with commonsense knowledge graph. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 3152– 3157, Online. Association for Computational Linguistics. find our card
  18. Yun Luo, Zihan Liu, Yuefeng Shi, Stan Z. Li, and Yue Zhang. 2022. Exploiting sentiment and common sense for zero-shot stance detection. In Proceedings of the 29th International Conference on Computational Linguistics, pages 7112–7123, Gyeongju, Republic of Korea. International Committee on Computati… find our card
  19. Brodie Mather, Bonnie J Dorr, Owen Rambow, and Tomek Strzalkowski. 2021. A general framework for domain-specialization of stance detection: A covid-19 response use case. The International FLAIRS Conference Proceedings, 34. find
  20. Dat Quoc Nguyen, Thanh Vu, and Anh Tuan Nguyen. 2020. BERTweet: A pre-trained language model for English tweets. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 9–14, Online. Association for Computational Linguistics. find our card
  21. OpenAI. 2025. gpt-oss-120b & gpt-oss-20b model card. find our card
  22. Peter F. M. Staab. 2025. lingua. Computer software. Version 2.1.1. find
  23. Penghui Wei and Wenji Mao. 2019. Modeling Transferable Topics for Cross-Target Stance Detection. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR’19, pages 1173–1176, New York, NY, USA. Association for Computing Machinery. find
  24. Wan Wei, Xiao Zhang, Xuqin Liu, Wei Chen, and Tengjiao Wang. 2016. pkudblab at SemEval-2016 task 6 : A specific convolutional neural network system for effective stance detection. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 384–388, San Diego, Calif… find our card
  25. Chang Xu, Cécile Paris, Surya Nepal, and Ross Sparks. 2018. Cross-target stance classification with self-attention networks. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 778–783, Melbourne, Australia. Association for Compu… find
  26. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual pre-trained text-to-text transformer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Ling… find
  27. Naiyu Yan, Shaobin Huang, and Rongsheng Li. 2025. BCLTC: Bi-directional curriculum learning based tasks collaboration for target-stance extraction. Information Processing & Management, 62(4):104137. find
  28. Guido Zarrella and Amy Marsh. 2016. MITRE at SemEval-2016 task 6: Transfer learning for stance detection. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 458–463, San Diego, California. Association for Computational Linguistics. find our card
  29. Chenye Zhao and Cornelia Caragea. 2025. Bilingual zero-shot stance detection. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 29900–29919, Vienna, Austria. Association for Computational Linguistics. find
  30. Qinglin Zhu, Bin Liang, Jingyi Sun, Jiachen Du, Lanjun Zhou, and Ruifeng Xu. 2022. Enhancing Zero-Shot Stance Detection via Targeted Background Knowledge. In Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’22, pages 2070–2075, N… find
  31. Language Resource References Emily Allaway and Kathleen McKeown. 2020. Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8913–8931, Online. Association for… find our card
  32. Alessandra Teresa Cignarella, Mirko Lai, Cristina Bosco, Viviana Patti, and Paolo Rosso. 2020. SardiStance @ EVALITA2020: Overview of the Task on Stance Detection in Italian Tweets. In Valerio Basile, Danilo Croce, Maria Maro, and Lucia C. Passaro, editors, EVALITA Evaluation of NLP and Speech Tools… find
  33. Costanza Conforti, Jakob Berndt, Mohammad Taher Pilehvar, Chryssi Giannitsarou, Flavio Toxvaerd, and Nigel Collier. 2020. Will-they-won’t-they: A very large dataset for stance detection on Twitter. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1715… find our card
  34. Kyle Glandt, Sarthak Khanal, Yingjie Li, Doina Caragea, and Cornelia Caragea. 2021. Stance detection in COVID-19 tweets. 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: Lo… find our card
  35. Mirko Lai, Alessandra Teresa Cignarella, Delia Irazú Hernández Farías, Cristina Bosco, Viviana Patti, and Paolo Rosso. 2020. Multilingual stance detection in social media political debates. Computer Speech & Language, 63:101075. find
  36. Yingjie Li, Tiberiu Sosea, Aditya Sawant, Ajith Jayaraman Nair, Diana Inkpen, and Cornelia Caragea. 2021. P-stance: A large dataset for stance detection in political domain. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2355–2365, Online. Association for Comput… find our card
  37. Bin Liang, Ang Li, Jingqian Zhao, Lin Gui, Min Yang, Yue Yu, Kam-Fai Wong, and Ruifeng Xu. 2024. Multi-modal stance detection: New datasets and model. In Findings of the Association for Computational Linguistics: ACL 2024, pages 12373– 12387, Bangkok, Thailand. Association for Computational Linguist… find our card
  38. Mark Mets, Andres Karjus, Indrek Ibrus, and Maximilian Schich. 2024. Automated stance detection in complex topics and small languages: The challenging case of immigration in polarizing news media. PLOS ONE, 19(4):e0302380. Publisher: Public Library of Science. find
  39. Saif Mohammad, Svetlana Kiritchenko, Parinaz Sobhani, Xiaodan Zhu, and Colin Cherry. 2016. SemEval-2016 task 6: Detecting stance in tweets. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pages 31–41, San Diego, California. Association for Computational Lingu… find
  40. Fuqiang Niu, Zebang Cheng, Xianghua Fu, Xiaojiang Peng, Genan Dai, Yin Chen, Hu Huang, and Bowen Zhang. 2024. Multimodal multi-turn conversation stance detection: A challenge dataset and effective model. In Proceedings of the 32nd ACM International Conference on Multimedia, MM ’24, page 3867–3876, N… find
  41. Frédéric Piedboeuf and Philippe Langlais. 2022. A new dataset for multilingual keyphrase generation. In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track. find
  42. Olivier Salaün, Frédéric Piedboeuf, Guillaume Le Berre, David Alfonso-Hermelo, and Philippe Langlais. 2024. EUROPA: A legal multilingual keyphrase generation dataset. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12718–12736… find
  43. Jörg Tiedemann. 2012. Parallel data, tools and interfaces in OPUS. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 2214–2218, Istanbul, Turkey. European Language Resources Association (ELRA). find
  44. Jannis Vamvas and Rico Sennrich. 2020. X-stance: A multilingual multi-target dataset for stance detection. CoRR, abs/2003.08385. — [arXiv:2003.08385](https://arxiv.org/abs/2003.08385) find
  45. Ruifeng Xu, Yu Zhou, Dongyin Wu, Lin Gui, Jiachen Du, and Yun Xue. 2016. Overview of NLPCC Shared Task 4: Stance Detection in Chinese Microblogs. In Natural Language Understanding and Intelligent Applications, pages 907–916, Cham. Springer International Publishing. find
  46. Chenye Zhao and Cornelia Caragea. 2024. EZ-STANCE: A large dataset for English zero-shot stance detection. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15697–15714, Bangkok, Thailand. Association for Computational Linguisti… find
  47. Chenye Zhao, Yingjie Li, and Cornelia Caragea. 2023. C-STANCE: A large dataset for Chinese zero-shot stance detection. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13369–13385, Toronto, Canada. Association for Computational… find our card
  48. Jonathan Zheng, Ashutosh Baheti, Tarek Naous, Wei Xu, and Alan Ritter. 2022. Stanceosaurus: Classifying stance towards multicultural misinformation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2132–2151, Abu Dhabi, United Arab Emirates. Associatio… find
  49. Elena Zotova, Rodrigo Agerri, Manuel Nuñez, and German Rigau. 2020. Multilingual stance detection in tweets: The Catalonia independence corpus. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 1368–1375, Marseille, France. European Language Resources Association. find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/mines-2026-multilingual-target-stance-extraction/