Elamur Research⌕
☰
home / papers / 2022 / Infusing Knowledge from Wikipedia to Enhance Stance Detection

Infusing Knowledge from Wikipedia to Enhance Stance Detection

Summary

Stance detection means deciding whether a text supports, opposes, or is neutral toward a given target. It often fails when the text refers to the target only indirectly, because models lack the background knowledge that human readers have. The authors fix this by giving the model the summary of the target's Wikipedia page as extra input. Their model, WS-BERT, has two variants. For formally written documents, WS-BERT-Single packs the text, the target and the Wikipedia summary into one BERT input so all three can attend to each other. For tweets, WS-BERT-Dual encodes the text–target pair with a Twitter-pretrained model (BERTweet or COVID-Twitter-BERT) and encodes the Wikipedia summary separately with BERT-base. It then joins the two [CLS] vectors before a softmax classifier. Across P-Stance, COVID-19-Stance and VAST, the method set new state-of-the-art results in target-specific, cross-target and zero/few-shot settings. The largest gains came when test targets were unseen in training. This suggests that raw encyclopedia text is a cheap, easily updated knowledge source, including for newly emerging targets.

Key points

  • Datasets: P-Stance (tweets about Biden, Sanders, Trump), COVID-19-Stance (four targets, e.g. Anthony Fauci and mask wearing) and VAST (New York Times debate comments, ~6000 targets).
  • For VAST, Wikipedia pages were retrieved automatically with the wikipedia Python API. Roughly 200 targets had no page, so the target string itself served as the knowledge. Summaries were cut to 512 tokens.
  • On COVID-19-Stance, WS-BERT-Dual reached an average macro-F1 of 84.4, compared with 83.0 for the authors' re-implemented COVID-Twitter-BERT.
  • On VAST, WS-BERT-Single scored 75.3 zero-shot, 73.6 few-shot and 74.5 overall. The knowledge-graph model CKE-Net reached 70.1 overall, about the same as a well-tuned plain BERT (70.0).
  • In cross-target transfer on P-Stance, the biggest improvements came from training on Trump and testing on Biden or Sanders. Code and data are released on GitHub (zihaohe123/wiki-enhanced-stance-detection).

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

Cited by

30 papers of our library cite it (of the 140673 whose bibliographies we read); 4 of them have a page here, 26 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2022.wassa-1.7 · arXiv 2204.03839

@inproceedings{he2022infusing,
  title = {{Infusing Knowledge from Wikipedia to Enhance Stance Detection}},
  author = {He, Zihao and Mokhberian, Negar and Lerman, Kristina},
  booktitle = {Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment \& Social Media Analysis},
  year = {2022},
  doi = {10.18653/v1/2022.wassa-1.7},
  eprint = {2204.03839},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2022.wassa-1.7}
}

References

31 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Long Papers), pages 1596–1611, Online. Association for Computational Linguistics. find
  2. 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 Computational Linguistics. find our card
  3. Kazuaki Hanawa, Akira Sasaki, Naoaki Okazaki, and Kentaro Inui. 2019. Stance detection attending external knowledge from wikipedia. Journal of Information Processing, 27:499–506. find
  4. Momchil Hardalov, Arnav Arora, Preslav Nakov, and Isabelle Augenstein. 2021. Cross-domain label-adaptive stance detection. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9011–9028, Online and Punta Cana, Dominican Republic. Association for Computatio… find our card
  5. 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
  6. Binxuan Huang and Kathleen Carley. 2018. Parameterized convolutional neural networks for aspect level sentiment classification. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1091–1096, Brussels, Belgium. Association for Computational Linguistics. find
  7. 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
  8. Myungha Jang and James Allan. 2018. Explaining controversy on social media via stance summarization. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pages 1221–1224. find
  9. Ramy Baly, Georgi Karadzhov, Dimitar Alexandrov, James Glass, and Preslav Nakov. 2018. Predicting factuality of reporting and bias of news media sources. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3528–3539, Brussels, Belgium. Association for Com… find
  10. Yingjie Li, Tiberiu Sosea, Aditya Sawant, Ajith Ja-yaraman Nair, Diana Inkpen, and Cornelia Caragea. 2021a. 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 Comp… find our card
  11. Ramy Baly, Georgi Karadzhov, Jisun An, Haewoon Kwak, Yoan Dinkov, Ahmed Ali, James Glass, and Preslav Nakov. 2020. What was written vs. who read it: News media profiling using text analysis and social media context. In Proceedings of the 58th Annual Meeting of the Association for Computational Lingu… find
  12. Yingjie Li, Chenye Zhao, and Cornelia Caragea. 2021b. Improving stance detection with multi-dataset learning and knowledge distillation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6332–6345, Online and Punta Cana, Dominican Republic. Association… find our card
  13. 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,… find
  14. 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, pages 3453–3464. find
  15. Yuxiao Lin, Yuxian Meng, Xiaofei Sun, Qinghong Han, Kun Kuang, Jiwei Li, and Fei Wu. 2021. BertGCN: Transductive text classification by combining GNN and BERT. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1456–1462, Online. Association for Computational Lingui… find
  16. Jiachen Du, Ruifeng Xu, Yulan He, and Lin Gui. 2017. Stance classification with target-specific neural attention networks. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, pages 3988–3994. find
  17. 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: Ru… find our card
  18. 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 Ling… find
  19. Yichong Xu, Chenguang Zhu, Ruochen Xu, Yang Liu, Michael Zeng, and Xuedong Huang. 2021. Fusing context into knowledge graph for commonsense question answering. In Workshop on Commonsense Reasoning and Knowledge Bases. find
  20. Wei Xue and Tao Li. 2018. Aspect based sentiment analysis with gated convolutional networks. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2514–2523, Melbourne, Australia. Association for Computational Linguistics. find
  21. Saif M Mohammad, Parinaz Sobhani, and Svetlana Kiritchenko. 2017. Stance and sentiment in tweets. ACM Transactions on Internet Technology (TOIT), 17(3):1–23. find
  22. Martin Müller, Marcel Salathé, and Per E Kummervold. 2020. Covid-twitter-bert: A natural language processing model to analyse covid-19 content on twitter. arXiv preprint arXiv:2005.07503. — [arXiv:2005.07503](https://arxiv.org/abs/2005.07503) find
  23. Bowen Zhang, Min Yang, Xutao Li, Yunming Ye, Xiaofei Xu, and Kuai Dai. 2020. Enhancing cross-target stance detection with transferable semantic-emotion knowledge. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3188–3197, Online. Association for Comp… find our card
  24. 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
  25. Yiwei Zhou, Alexandra I Cristea, and Lei Shi. 2017. Connecting targets to tweets: Semantic attention-based model for target-specific stance detection. In International Conference on Web Information Systems Engineering, pages 18–32. Springer. find
  26. Umme Aymun Siddiqua, Abu Nowshed Chy, and Masaki Aono. 2019. Tweet stance detection using an attention based neural ensemble model. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Sh… find our card
  27. Swapna Somasundaran and Janyce Wiebe. 2010. Recognizing stances in ideological on-line debates. In Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text, pages 116–124, Los Angeles, CA. Association for Computational Linguistics. find
  28. Peter Stefanov, Kareem Darwish, Atanas Atanasov, and Preslav Nakov. 2020. Predicting the topical stance and political leaning of media using tweets. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 527–537, Online. Association for Computational Lingui… find
  29. Qingying Sun, Zhongqing Wang, Qiaoming Zhu, and Guodong Zhou. 2018. Stance detection with hierarchical attention network. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2399–2409, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find our card
  30. Qizhe Xie, Minh-Thang Luong, Eduard Hovy, and Quoc V Le. 2020. Self-training with noisy student improves imagenet classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10687–10698. find
  31. Chang Xu, Cécile Paris, Surya Nepal, Ross Sparks, Chong Long, and Yafang Wang. 2020. Dan: Dual-view representation learning for adapting stance classifiers to new domains. In ECAI 2020, pages 2260– 2267. IOS Press. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/he-2022-infusing-knowledge-wikipedia-enhance-stance/