Elamur Research⌕
☰
home / papers / 2022 / Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognition

Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognition

Summary

Implicit discourse relation recognition (IDRR) requires labeling the semantic link between two text spans (Arg1, Arg2) when no connective word signals it. This makes it much harder than the explicit case. Earlier systems relied on multi-task learning or label-dependency constraints, but they handled fine-grained senses poorly and often never correctly predicted rare second-level classes. The authors recast IDRR as a cloze problem. Both arguments are placed into a hand-written natural-language template, RoBERTa-large fills a masked slot with a connective, and that connective is then translated into a sense label. Instead of handpicking answer words, the mapping assigns each relation its frequent, low-ambiguity connectives from the data. On PDTB 2.0 and the CoNLL-2016 Shared Task, PCP reports state-of-the-art results and, for the first time, nonzero scores on several few-shot fine-grained senses, though frequent classes lose a little. A variant also handles explicit relations. The work suggests that aligning fine-tuning with the masked-language-model objective lets PLM knowledge about connectives benefit discourse parsing.

Key points

  • Template search on RoBERTa-large used PDTB 2.0 top-level dev accuracy. Scores ranged from 69.23 for the plain "Arg1 <mask> Arg2." template to 72.27 for an instruction-style template asking for the "conjunction" between the arguments, with </s></s> separators.
  • Predicting connectives beats asking the model to name the relation directly (PIDRP). Top-level Macro-F1 was 67.79 vs 62.05, with the biggest gap on Temporal (56.41 vs 39.13).
  • A prior pipeline approach had to score roughly 100 candidate connectives in PDTB 2.0 per sample. PCP needs only a single masked-token prediction.
  • The explicit-relation variant PEDRR, which feeds the gold connective and predicts the sense word, reaches 94.78 accuracy and 93.59 F1 on PDTB 2.0 top-level senses, close to earlier strong systems.
  • The authors acknowledge two limitations: templates were designed manually with no ensembling, and class imbalance in second-level senses remains. Code is available on GitHub (zh-i9/PCP-for-IDRR).

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

Topics: Discourse analysis

Cited by

23 papers of our library cite it (of the 140673 whose bibliographies we read); 8 of them have a page here, 15 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2022.findings-emnlp.282 · arXiv 2210.07032

@inproceedings{zhou2022prompt,
  title = {{Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognition}},
  author = {Zhou, Hao and Lan, Man and Wu, Yuanbin and Chen, Yuefeng and Ma, Meirong},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2022},
  year = {2022},
  doi = {10.18653/v1/2022.findings-emnlp.282},
  eprint = {2210.07032},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2022.findings-emnlp.282}
}

References

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

  1. Hongxiao Bai and Hai Zhao. 2018. Deep enhanced representation for implicit discourse relation recognition. In Proceedings of the 27th International Conference on Computational Linguistics, pages 571–583, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find our card
  2. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901. find
  3. Xiang Chen, Ningyu Zhang, Lei Li, Xin Xie, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, and Huajun Chen. 2021. Lightner: A lightweight generative framework with prompt-guided attention for low-resource ner. arXiv preprint arXiv:2109.00720. — [arXiv:2109.00720](https://arxiv.org/abs/2109.00720) find
  4. Xiang Chen, Ningyu Zhang, Xin Xie, Shumin Deng, Yunzhi Yao, Chuanqi Tan, Fei Huang, Luo Si, and Huajun Chen. 2022a. Knowprompt: Knowledge-aware prompt-tuning with synergistic optimization for relation extraction. In Proceedings of the ACM Web Conference 2022, pages 2778–2788. find
  5. Yulong Chen, Yang Liu, Li Dong, Shuohang Wang, Chenguang Zhu, Michael Zeng, and Yue Zhang. 2022b. Adaprompt: Adaptive model training for prompt-based nlp. arXiv preprint arXiv:2202.04824. find
  6. Leyang Cui, Yu Wu, Jian Liu, Sen Yang, and Yue Zhang. 2021. Template-based named entity recognition using bart. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1835–1845. find
  7. Zeyu Dai and Ruihong Huang. 2018. Improving implicit discourse relation classification by modeling inter-dependencies of discourse units in a paragraph. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find our card
  8. Zeyu Dai and Ruihong Huang. 2019. A regularization approach for incorporating event knowledge and coreference relations into neural discourse parsing. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Langu… find our card
  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,… find
  10. Xu Han, Weilin Zhao, Ning Ding, Zhiyuan Liu, and Maosong Sun. 2021. Ptr: Prompt tuning with rules for text classification. ArXiv, abs/2105.11259. — [arXiv:2105.11259](https://arxiv.org/abs/2105.11259) find
  11. Shengding Hu, Ning Ding, Huadong Wang, Zhiyuan Liu, Juanzi Li, and Maosong Sun. 2021. Knowledgeable prompt-tuning: Incorporating knowledge into prompt verbalizer for text classification. arXiv preprint arXiv:2108.02035. find
  12. Yangfeng Ji and Jacob Eisenstein. 2015. One vector is not enough: Entity-augmented distributed semantics for discourse relations. Transactions of the Association for Computational Linguistics, 3:329–344. find our card
  13. Ting Jiang, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Liangjie Zhang, and Qi Zhang. 2022. Promptbert: Improving bert sentence embeddings with prompts. ArXiv preprint, abs/2201.04337. find
  14. Najoung Kim, Song Feng, Chulaka Gunasekara, and Luis Lastras. 2020. Implicit discourse relation classification: We need to talk about evaluation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5404– 5414, Online. Association for Computational Lingui… find our card
  15. Yudai Kishimoto, Yugo Murawaki, and Sadao Kurohashi. 2020. Adapting BERT to implicit discourse relation classification with a focus on discourse connectives. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 1152– 1158, Marseille, France. European Language Resources Asso… find our card
  16. Murathan Kurfalı and Robert Östling. 2021. Let’s be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction. In Proceedings of the 1st Workshop on Understanding Implicit and Underspecified Language, pages 1–10, Online. Association for Computa… find our card
  17. Man Lan, Jianxiang Wang, Yuanbin Wu, Zheng-Yu Niu, and Haifeng Wang. 2017. Multi-task attention-based neural networks for implicit discourse relationship representation and identification. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1299–1308. find our card
  18. Ziheng Lin, Min-Yen Kan, and Hwee Tou Ng. 2009. Recognizing implicit discourse relations in the Penn Discourse Treebank. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 343–351, Singapore. Association for Computational Linguistics. find our card
  19. 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. ArXiv preprint, abs/2107.13586. find our card
  20. Xin Liu, Jiefu Ou, Yangqiu Song, and Xin Jiang. 2020. On the importance of word and sentence representation learning in implicit discourse relation classification. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, pages 3830–3836. ijcai.org. find
  21. Yang Liu and Sujian Li. 2016. Recognizing implicit discourse relations via repeated reading: Neural networks with multi-level attention. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1224–1233. find our card
  22. Yang Liu, Sujian Li, Xiaodong Zhang, and Zhifang Sui. 2016. Implicit discourse relation classification via multi-task neural networks. In Thirtieth AAAI Conference on Artificial Intelligence. find
  23. 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, abs/1907.11692. find
  24. Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101. find
  25. Todor Mihaylov and Anette Frank. 2019. Discourse-aware semantic self-attention for narrative reading comprehension. 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), page… find
  26. Emily Pitler and Ani Nenkova. 2009. Using syntax to disambiguate explicit discourse connectives in text. In Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 13–16, Suntec, Singapore. Association for Computational Linguistics. find our card
  27. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Milt-sakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. 2008. The Penn Discourse TreeBank 2.0. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08), Marrakech, Morocco. European Language Resources Asso… find our card
  28. Timo Schick and Hinrich Schütze. 2021a. Exploiting cloze-questions for few-shot text classification and natural language inference. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 255–269, Online. Association for Comp… find our card
  29. Timo Schick and Hinrich Schütze. 2021b. It’s not just size that matters: Small language models are also few-shot learners. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2339–2352, Online. Assoc… find our card
  30. Linh Van Ngo, Khoat Than, Thien Huu Nguyen, et al. 2019. Employing the correspondence of relations and connectives to identify implicit discourse relations via label embeddings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4201–4207. find our card
  31. Siddharth Varia, Christopher Hidey, and Tuhin Chakrabarty. 2019. Discourse relation prediction: Revisiting word pairs with convolutional networks. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 442–452, Stockholm, Sweden. Association for Computational Linguistics. find our card
  32. Jianxiang Wang and Man Lan. 2016. Two end-to-end shallow discourse parsers for english and chinese in conll-2016 shared task. In Proceedings of the CoNLL-16 shared task, pages 33–40. find our card
  33. Changxing Wu, Liuwen Cao, Yubin Ge, Yang Liu, Min Zhang, and Jinsong Su. 2021. A label dependence-aware sequence generation model for multi-level implicit discourse relation recognition. ArXiv preprint, abs/2112.11740. — [arXiv:2112.11740](https://arxiv.org/abs/2112.11740) find
  34. Changxing Wu, Chaowen Hu, Ruochen Li, Hongyu Lin, and Jinsong Su. 2020. Hierarchical multi-task learning with crf for implicit discourse relation recognition. Knowledge-Based Systems, 195:105637. find
  35. Wei Xiang and Bang Wang. 2022. A survey of implicit discourse relation recognition. ArXiv preprint, abs/2203.02982. find
  36. Hao Xiong, Zhongjun He, Hua Wu, and Haifeng Wang. 2019. Modeling coherence for discourse neural machine translation. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Sy… find
  37. Jiacheng Xu, Zhe Gan, Yu Cheng, and Jingjing Liu. 2020. Discourse-aware neural extractive text summarization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5021–5031, Online. Association for Computational Linguistics. find our card
  38. Nianwen Xue, Hwee Tou Ng, Sameer Pradhan, Attapol Rutherford, Bonnie Webber, Chuan Wang, and Hongmin Wang. 2016. find
  39. CoNLL 2016 shared task on multilingual shallow discourse parsing. In Proceedings of the CoNLL-16 shared task, pages 1–19, Berlin, Germany. Association for Computational Linguistics. find our card
  40. Zhi Min Zhou, Man Lan, Zheng Yu Niu, Yu Xu, and Jian Su. 2010. The effects of discourse connectives prediction on implicit discourse relation recognition. In Proceedings of the SIGDIAL 2010 Conference, pages 139–146, Tokyo, Japan. Association for Computational Linguistics. find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhou-2022-prompt-based-connective-prediction-method/