Elamur Research⌕
☰
home / papers / 2021 / Target-Aware Data Augmentation for Stance Detection

Target-Aware Data Augmentation for Stance Detection

Summary

Stance detection classifies whether a text's author supports, opposes, or is neutral toward a given target. Annotated data for this task are scarce. Standard augmentation techniques such as synonym substitution, EDA, back-translation and CBERT tend to produce samples that lack variety or ignore the target and stance label. The authors frame augmentation as conditional masked language modeling and introduce ASDA (Auxiliary Sentence based Data Augmentation). They fine-tune BERTweet so that masked words are predicted using the tweet's context and a prepended auxiliary text. That text names the stance and target and includes a second training tweet with the same target and label. They also propose Target Replacement (TR), a simple, training-free method for multi-target data that swaps the mentions of the two targets. Experiments cover three datasets with 11 targets. Both methods beat earlier augmentation approaches across several base classifiers. ASDA is architecture-independent, so it also strengthens other methods like CBERT. This makes it useful for low-resource stance tasks.

Key points

  • Evaluation uses SemEval-2016 (single-target), the Multi-Target stance dataset (pairs of US presidential candidates) and WT-WT (company mergers, e.g., Cigna and Express Scripts), covering 11 targets in total.
  • ASDA builds on BERTweet, which was pre-trained on 850M English tweets. Unlike CBERT, it does not depend on segmentation embeddings, so it also handles multi-target detection.
  • Base classifiers are PGCNN, TAN and BERT. Compared with EDA's Random Swap, TR performs better on 6, 5 and 4 targets for these models, respectively.
  • TR does not apply to SemEval-2016, which has only one target per sample. It struggles on the Clinton–Sanders pair because target-related words (e.g., "Benghazi") remain unswapped.
  • Ablations show the reference tweet in the auxiliary sentence drives part of the gain. ASDA also works with other auxiliary-sentence formats and improves CBERT when combined with it.

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

22 papers of our library cite it (of the 140673 whose bibliographies we read); 10 of them have a page here, 12 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.naacl-main.148

@inproceedings{li2021target,
  title = {{Target-Aware Data Augmentation for Stance Detection}},
  author = {Li, Yingjie and Caragea, Cornelia},
  booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2021},
  doi = {10.18653/v1/2021.naacl-main.148},
  url = {https://doi.org/10.18653/v1/2021.naacl-main.148}
}

References

39 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abeer AlDayel and Walid Magdy. 2020. Stance detection on social media: State of the art and trends. arXiv preprint arXiv:2006.03644. find
  2. Ateret Anaby-Tavor, Boaz Carmeli, Esther Goldbraich, Amir Kantor, George Kour, Segev Shlomov, Naama Tepper, and Naama Zwerdling. 2020. Do not have enough data? deep learning to the rescue! In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, pages 7383–7390. find
  3. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations. 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. 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
  6. Yann N. Dauphin, Angela Fan, Michael Auli, and David Grangier. 2017. Language modeling with gated convolutional networks. In Proceedings of the 34th International Conference on Machine Learning - Volume 70, page 933–941. find our card
  7. 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
  8. 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
  9. Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, page 2672–2680. find
  10. 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. find
  11. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations. find
  12. Diederik P. Kingma and Max Welling. 2014. Auto-Encoding Variational Bayes. In 2nd International Conference on Learning Representations, ICLR 2014. find our card
  13. Sosuke Kobayashi. 2018. Contextual augmentation: Data augmentation by words with paradigmatic relations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 452–457. find our card
  14. Dilek Küçük and Fazli Can. 2020. Stance detection: A survey. ACM Comput. Surv., 53(1):1–37. find
  15. Varun Kumar, Ashutosh Choudhary, and Eunah Cho. 2020. Data augmentation using pre-trained transformer models. In Proceedings of the 2nd Workshop on Life-long Learning for Spoken Language Systems, pages 18–26. find our card
  16. Kun Li, Chengbo Chen, Xiaojun Quan, Qing Ling, and Yan Song. 2020. Conditional augmentation for aspect term extraction via masked sequence-to-sequence generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7056–7066. find
  17. Yingjie Li and Cornelia Caragea. 2019. Multi-task stance detection with sentiment and stance lexicons. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6298– 6304. find our card
  18. Junjie Lin, Qingchao Kong, Wenji Mao, and Lei Wang. 2019. A topic enhanced approach to detecting multiple standpoints in web texts. Information Sciences, 501:483–494. find
  19. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. find
  20. Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Distributed representations of words and phrases and their compositionality. In Proceedings of the 26th International Conference on Neural Information Processing Systems -Volume 2, page 3111–3119. find
  21. George A. Miller. 1995. Wordnet: A lexical database for english. Commun. ACM, 38(11):39–41. find our card
  22. Saif Mohammad, Svetlana Kiritchenko, Parinaz Sobhani, Xiao-Dan Zhu, and Colin Cherry. 2016. A dataset for detecting stance in tweets. In LREC. find
  23. 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. find our card
  24. Timo Schick and Hinrich Schütze. 2020. Exploiting cloze questions for few-shot text classification and natural language inference. Computing Research Repository, arXiv:2001.07676. find our card
  25. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Improving neural machine translation models with monolingual data. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 86–96. 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. Parinaz Sobhani, Diana Inkpen, and Xiaodan Zhu. 2017. A dataset for multi-target stance detection. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 551–557. find our card
  28. Parinaz Sobhani, Diana Inkpen, and Xiaodan Zhu. 2019. Exploring deep neural networks for multi-target stance detection. Computational Intelligence, 35(1):82–97. find
  29. Chi Sun, Luyao Huang, and Xipeng Qiu. 2019. Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence. 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
  30. Penghui Wei, Junjie Lin, and Wenji Mao. 2018a. Multi-target stance detection via a dynamic memory-augmented network. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR 2018, Ann Arbor, MI, USA, July 08-12, 2018, pages 1229–1232. find
  31. Penghui Wei, Wenji Mao, and Daniel Zeng. 2018b. A target-guided neural memory model for stance detection in twitter. In 2018 International Joint Conference on Neural Networks, IJCNN 2018, Rio de Janeiro, Brazil, July 8-13, 2018, pages 1–8. find
  32. Xing Wu, Shangwen Lv, Liangjun Zang, Jizhong Han, and Songlin Hu. 2019. Conditional bert contextual augmentation. In International Conference on Computational Science, pages 84–95. find
  33. Chang Xu, Cecile Paris, Surya Nepal, and Ross Sparks. 2019. Recognising agreement and disagreement between stances with reason comparing networks. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4665– 4671. find
  34. 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. find
  35. Adams Wei Yu, David Dohan, Quoc Le, Thang Luong, Rui Zhao, and Kai Chen. 2018. Fast and accurate reading comprehension by combining self-attention and convolution. In International Conference on Learning Representations. find
  36. Xiang Zhang, Junbo Zhao, and Yann LeCun. 2015. Character-level convolutional networks for text classification. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1, page 649–657. find our card
  37. 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. find our card
  38. William Yang Wang and Diyi Yang. 2015. That’s so annoying!!!: A lexical and frame-semantic embedding based data augmentation approach to automatic categorization of annoying behaviors using \#petpeeve tweets. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, p… find our card
  39. Jason Wei and Kai Zou. 2019. EDA: Easy data augmentation techniques for boosting performance on text classification tasks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP… find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/li-2021-target-aware-data-augmentation-stance/