---
title: "Prompt-based Logical Semantics Enhancement for — Wang 2023"
description: "Recognizing implicit discourse relations (IDRR), where no connective such as \"because\" signals how two arguments relate, is still hard."
authors: ["Chenxu Wang", "Ping Jian", "Mu Huang"]
year: 2023
venue: "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/2023.emnlp-main.45/"
doi: "10.18653/v1/2023.emnlp-main.45"
arxiv: "2311.00367"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/wang-2023-prompt-based-logical-semantics-enhancement/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/wang-2023-prompt-based-logical-semantics-enhancement/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2023](https://md.research.elamur.ai/free/papers/2023/page/5/) / Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition

# Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition

**Authors:** Chenxu Wang, [Ping Jian](https://md.research.elamur.ai/free/authors/ping-jian/), Mu Huang · **Year:** 2023 · **Venue:** Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2023.emnlp-main.45/) · [PDF](https://aclanthology.org/2023.emnlp-main.45.pdf) · [DOI 10.18653/v1/2023.emnlp-main.45](https://doi.org/10.18653/v1/2023.emnlp-main.45) · [arXiv 2311.00367](https://arxiv.org/abs/2311.00367) · [OpenAlex](https://openalex.org/W4389518617)

**Citations:** 4 citations (openalex-snapshot · 2026-10-14) · 4 in our library, of the 140673 papers whose bibliographies we read

## Summary
Recognizing implicit discourse relations (IDRR), where no connective such as "because" signals how two arguments relate, is still hard. Recent systems rely heavily on annotated sense hierarchies, so they are limited by how much labeled data exists. The authors propose PLSE, which uses plentiful unlabeled text containing explicit connectives. First, they pre-train a language model with a manually designed Cloze-Prompt: the connective between two arguments is masked and must be recovered. The same template is then reused to fine-tune the model on implicit pairs by predicting an implied connective, so pre-training and the downstream task share one format. MLM is good at local context but weak at whole-text meaning, so the authors add a self-supervised objective. It maximizes mutual information between the connective-related representation and a global logical-semantic representation. On PDTB 2.0 and CoNLL16, the method reports state-of-the-art results without depending on hierarchical sense labels. This shows that cheap explicit data can partly replace costly annotation.

## Key points
- About 0.56 million explicit argument pairs were mined from Gigaword and split 9:1 into training and validation. Connectives were masked 90% of the time and left unchanged 10% of the time.
- Pre-training combines three tasks: Connectives Mask (CM), standard MLM, and Global Logical Semantics Learning (GLSL, the MI-based objective). Ablations show that removing any one of them hurts performance, and removing GLSL hurts most. GLSL also beat auxiliary tasks built on the [CLS] or mean representations.
- Gains slow down sharply beyond roughly 500,000 unannotated pairs, so that scale was chosen. The authors attribute this plateau to distribution differences between explicit and implicit data.
- In few-shot tests, PLSE trained on 50% of the data roughly matches a baseline without pre-training that uses all training data.
- Evaluation covered PDTB 2.0 and CoNLL16 (Test and Blind sets); PDTB 3.0 was excluded. A known limitation is that only single-token connectives are supported.

*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](https://md.research.elamur.ai/free/shelves/linguistics/)

Topics: [Discourse analysis](https://md.research.elamur.ai/free/topics/discourse-analysis/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{wang2023prompt,
  title = {{Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition}},
  author = {Wang, Chenxu and Jian, Ping and Huang, Mu},
  booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
  year = {2023},
  doi = {10.18653/v1/2023.emnlp-main.45},
  eprint = {2311.00367},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2023.emnlp-main.45}
}
```

- [← previous Prompt Tuning with Contradictory Intentions for Sarcasm Recognition](https://md.research.elamur.ai/free/papers/liu-2023-prompt-tuning-contradictory-intentions-sarcasm/)
- [next → Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://md.research.elamur.ai/free/papers/fernando-2023-promptbreeder-self-referential-self-improvement/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/papers/2023/page/5/)

## References

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

1. Alexander A Alemi, Ian Fischer, Joshua V Dillon, and Kevin Murphy. 2016. Deep variational information bottleneck. arXiv preprint arXiv:1612.00410. — [arXiv:1612.00410](https://arxiv.org/abs/1612.00410) [find](https://scholar.google.com/scholar?q=Alexander+A+Alemi%2C+Ian+Fischer%2C+Joshua+V+Dillon%2C+and+Kevin+Murphy%2E+2016%2E+Deep+variational+information+bottleneck%2E+arXiv+preprint+arXiv%3A1612%2E00410%2E+%E2%80%94+%5BarXiv%3A1612%2E00410%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1612%2E00410)
2. Anthony J Bell and Terrence J Sejnowski. 1995. An information-maximization approach to blind separation and blind deconvolution. Neural computation, 7(6):1129–1159. maximization. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Anthony+J+Bell+and+Terrence+J+Sejnowski%2E+1995%2E+An+information%2Dmaximization+approach+to+blind+separation+and+blind+deconvolution%2E+Neural+computation%2C+7%286%29%3A1129%E2%80%931159%2E+maximization%2E+In+International+Conf)
3. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chri… [find](https://scholar.google.com/scholar?q=Tom+Brown%2C+Benjamin+Mann%2C+Nick+Ryder%2C+Melanie+Subbiah%2C+Jared+D+Kaplan%2C+Prafulla+Dhariwal%2C+Arvind+Neelakantan%2C+Pranav+Shyam%2C+Girish+Sastry%2C+Amanda+Askell%2C+Sandhini+Agarwal%2C+Ariel+Herbert%2DVoss%2C+Gretchen)
4. Aapo Hyvärinen and Petteri Pajunen. 1999. Nonlinear independent component analysis: Existence and uniqueness results. Neural networks, 12(3):429–439. [find](https://scholar.google.com/scholar?q=Aapo+Hyv%C3%A4rinen+and+Petteri+Pajunen%2E+1999%2E+Nonlinear+independent+component+analysis%3A+Existence+and+uniqueness+results%2E+Neural+networks%2C+12%283%29%3A429%E2%80%93439%2E)
5. Chunkit Chan, Jiayang Cheng, Weiqi Wang, Yuxin Jiang, Tianqing Fang, Xin Liu, and Yangqiu Song. 2023a. Chatgpt evaluation on sentence level relations: A focus on temporal, causal, and discourse relations. arXiv preprint arXiv:2304.14827. [find](https://scholar.google.com/scholar?q=Chunkit+Chan%2C+Jiayang+Cheng%2C+Weiqi+Wang%2C+Yuxin+Jiang%2C+Tianqing+Fang%2C+Xin+Liu%2C+and+Yangqiu+Song%2E+2023a%2E+Chatgpt+evaluation+on+sentence+level+relations%3A+A+focus+on+temporal%2C+causal%2C+and+discourse+relati) [our card](https://md.research.elamur.ai/free/papers/chan-2024-exploring-potential-chatgpt-sentence-level/)
6. Chunkit Chan, Xin Liu, Jiayang Cheng, Zihan Li, Yangqiu Song, Ginny Y Wong, and Simon See. 2023b. Discoprompt: Path prediction prompt tuning for implicit discourse relation recognition. arXiv preprint arXiv:2305.03973. [find](https://scholar.google.com/scholar?q=Chunkit+Chan%2C+Xin+Liu%2C+Jiayang+Cheng%2C+Zihan+Li%2C+Yangqiu+Song%2C+Ginny+Y+Wong%2C+and+Simon+See%2E+2023b%2E+Discoprompt%3A+Path+prediction+prompt+tuning+for+implicit+discourse+relation+recognition%2E+arXiv+preprint) [our card](https://md.research.elamur.ai/free/papers/chan-2023-discoprompt-path-prediction-prompt-tuning/)
7. Arman Cohan, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Seokhwan Kim, Walter Chang, and Nazli Goharian. 2018. A discourse-aware attention model for abstractive summarization of long documents. In Proceedings of NAACL-HLT, pages 615–621. [find](https://scholar.google.com/scholar?q=Arman+Cohan%2C+Franck+Dernoncourt%2C+Doo+Soon+Kim%2C+Trung+Bui%2C+Seokhwan+Kim%2C+Walter+Chang%2C+and+Nazli+Goharian%2E+2018%2E+A+discourse%2Daware+attention+model+for+abstractive+summarization+of+long+documents%2E+In+Pr) [our card](https://md.research.elamur.ai/free/papers/cohan-2018-discourse-aware-attention-model-abstractive/)
8. 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](https://scholar.google.com/scholar?q=Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2019%2E+BERT%3A+Pre%2Dtraining+of+deep+bidirectional+transformers+for+language+understanding%2E+In+Proceedings+of+the+2019+Conference+of+the+N)
9. Ning Ding, Shengding Hu, Weilin Zhao, Yulin Chen, Zhiyuan Liu, Haitao Zheng, and Maosong Sun. 2022. Openprompt: An open-source framework for prompt-learning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 105–113. [find](https://scholar.google.com/scholar?q=Ning+Ding%2C+Shengding+Hu%2C+Weilin+Zhao%2C+Yulin+Chen%2C+Zhiyuan+Liu%2C+Haitao+Zheng%2C+and+Maosong+Sun%2E+2022%2E+Openprompt%3A+An+open%2Dsource+framework+for+prompt%2Dlearning%2E+In+Proceedings+of+the+60th+Annual+Meeting+)
10. Zhiyi Fu, Wangchunshu Zhou, Jingjing Xu, Hao Zhou, and Lei Li. 2022. Contextual representation learning beyond masked language modeling. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2701–2714, Dublin, Ireland. Association f… [find](https://scholar.google.com/scholar?q=Zhiyi+Fu%2C+Wangchunshu+Zhou%2C+Jingjing+Xu%2C+Hao+Zhou%2C+and+Lei+Li%2E+2022%2E+Contextual+representation+learning+beyond+masked+language+modeling%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+fo)
11. R Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Phil Bachman, Adam Trischler, and Yoshua Bengio. 2019. Learning deep representations by mutual information estimation and Yangfeng Ji and Jacob Eisenstein. 2015. One Vector is Not Enough: Entity-Augmented Distributed Semantics for… [find](https://scholar.google.com/scholar?q=R+Devon+Hjelm%2C+Alex+Fedorov%2C+Samuel+Lavoie%2DMarchildon%2C+Karan+Grewal%2C+Phil+Bachman%2C+Adam+Trischler%2C+and+Yoshua+Bengio%2E+2019%2E+Learning+deep+representations+by+mutual+information+estimation+and+Yangfeng+)
12. Feng Jiang, Yaxin Fan, Xiaomin Chu, Peifeng Li, and Qiaoming Zhu. 2021. Not just classification: Recognizing implicit discourse relation on joint modeling of classification and generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2418–2431, Onl… [find](https://scholar.google.com/scholar?q=Feng+Jiang%2C+Yaxin+Fan%2C+Xiaomin+Chu%2C+Peifeng+Li%2C+and+Qiaoming+Zhu%2E+2021%2E+Not+just+classification%3A+Recognizing+implicit+discourse+relation+on+joint+modeling+of+classification+and+generation%2E+In+Proceedi) [our card](https://md.research.elamur.ai/free/papers/jiang-2021-not-just-classification-recognizing-implicit/)
13. Yuxin Jiang, Linhan Zhang, and Wei Wang. 2022. Global and local hierarchy-aware contrastive framework for implicit discourse relation recognition. arXiv preprint arXiv:2211.13873. [find](https://scholar.google.com/scholar?q=Yuxin+Jiang%2C+Linhan+Zhang%2C+and+Wei+Wang%2E+2022%2E+Global+and+local+hierarchy%2Daware+contrastive+framework+for+implicit+discourse+relation+recognition%2E+arXiv+preprint+arXiv%3A2211%2E13873%2E) [our card](https://md.research.elamur.ai/free/papers/jiang-2023-global-local-hierarchy-aware-contrastive/)
14. 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 Twelfth Language Resources and Evaluation Conference, pages 1152– 1158, Marseille, France. European Language Resources A… [find](https://scholar.google.com/scholar?q=Yudai+Kishimoto%2C+Yugo+Murawaki%2C+and+Sadao+Kurohashi%2E+2020%2E+Adapting+BERT+to+implicit+discourse+relation+classification+with+a+focus+on+discourse+connectives%2E+In+Proceedings+of+the+Twelfth+Language+Res) [our card](https://md.research.elamur.ai/free/papers/kishimoto-2020-adapting-bert-implicit-discourse-relation/)
15. Lingpeng Kong, Cyprien de Masson d’Autume, Wang Ling, Lei Yu, Zihang Dai, and Dani Yogatama. 2019. A mutual information maximization perspective of language representation learning. arXiv preprint arXiv:1910.08350. — [arXiv:1910.08350](https://arxiv.org/abs/1910.08350) [find](https://scholar.google.com/scholar?q=Lingpeng+Kong%2C+Cyprien+de+Masson+d%E2%80%99Autume%2C+Wang+Ling%2C+Lei+Yu%2C+Zihang+Dai%2C+and+Dani+Yogatama%2E+2019%2E+A+mutual+information+maximization+perspective+of+language+representation+learning%2E+arXiv+preprint+arX)
16. 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](https://scholar.google.com/scholar?q=Man+Lan%2C+Jianxiang+Wang%2C+Yuanbin+Wu%2C+Zheng%2DYu+Niu%2C+and+Haifeng+Wang%2E+2017%2E+Multi%2Dtask+attention%2Dbased+neural+networks+for+implicit+discourse+relationship+representation+and+identification%2E+In+Proceedi) [our card](https://md.research.elamur.ai/free/papers/lan-2017-multi-task-attention-based-neural/)
17. Li Liang, Zheng Zhao, and Bonnie Webber. 2020. Extending implicit discourse relation recognition to the PDTB-3. In Proceedings of the First Workshop on Computational Approaches to Discourse, pages 135– 147, Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Li+Liang%2C+Zheng+Zhao%2C+and+Bonnie+Webber%2E+2020%2E+Extending+implicit+discourse+relation+recognition+to+the+PDTB%2D3%2E+In+Proceedings+of+the+First+Workshop+on+Computational+Approaches+to+Discourse%2C+pages+135) [our card](https://md.research.elamur.ai/free/papers/liang-2020-extending-implicit-discourse-relation-recognition/)
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. [find](https://scholar.google.com/scholar?q=Ziheng+Lin%2C+Min%2DYen+Kan%2C+and+Hwee+Tou+Ng%2E+2009%2E+Recognizing+implicit+discourse+relations+in+the+penn+discourse+treebank%2E+In+Proceedings+of+the+2009+conference+on+empirical+methods+in+natural+language+) [our card](https://md.research.elamur.ai/free/papers/lin-2009-recognizing-implicit-discourse-relations-penn/)
19. Ralph Linsker. 1988. Self-organization in a perceptual network. Computer, 21(03):105–117. [find](https://scholar.google.com/scholar?q=Ralph+Linsker%2E+1988%2E+Self%2Dorganization+in+a+perceptual+network%2E+Computer%2C+21%2803%29%3A105%E2%80%93117%2E)
20. 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 e-prints, pages arXiv–2107. [find](https://scholar.google.com/scholar?q=Pengfei+Liu%2C+Weizhe+Yuan%2C+Jinlan+Fu%2C+Zhengbao+Jiang%2C+Hiroaki+Hayashi%2C+and+Graham+Neubig%2E+2021%2E+Pre%2Dtrain%2C+prompt%2C+and+predict%3A+A+systematic+survey+of+prompting+methods+in+natural+language+processing%2E+) [our card](https://md.research.elamur.ai/free/papers/liu-2021-pre-train-prompt-predict-systematic/)
21. 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. [find](https://scholar.google.com/scholar?q=Xin+Liu%2C+Jiefu+Ou%2C+Yangqiu+Song%2C+and+Xin+Jiang%2E+2020%2E+On+the+importance+of+word+and+sentence+representation+learning+in+implicit+discourse+relation+classification%2E+In+Proceedings+of+the+Twenty%2DNinth+I)
22. 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, Austin, Texas. Association for Computational Linguistic… [find](https://scholar.google.com/scholar?q=Yang+Liu+and+Sujian+Li%2E+2016%2E+Recognizing+implicit+discourse+relations+via+repeated+reading%3A+Neural+networks+with+multi%2Dlevel+attention%2E+In+Proceedings+of+the+2016+Conference+on+Empirical+Methods+in+N) [our card](https://md.research.elamur.ai/free/papers/liu-2016-recognizing-implicit-discourse-relations-repeated/)
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 arXiv:1907.11692. [find](https://scholar.google.com/scholar?q=Yinhan+Liu%2C+Myle+Ott%2C+Naman+Goyal%2C+Jingfei+Du%2C+Mandar+Joshi%2C+Danqi+Chen%2C+Omer+Levy%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Veselin+Stoyanov%2E+2019%2E+Roberta%3A+A+robustly+optimized+bert+pretraining+approach%2E+a)
24. Wanqiu Long and Bonnie Webber. 2022. Facilitating contrastive learning of discourse relational senses by exploiting the hierarchy of sense relations. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10704– 10716, Abu Dhabi, United Arab Emirates. Associ… [find](https://scholar.google.com/scholar?q=Wanqiu+Long+and+Bonnie+Webber%2E+2022%2E+Facilitating+contrastive+learning+of+discourse+relational+senses+by+exploiting+the+hierarchy+of+sense+relations%2E+In+Proceedings+of+the+2022+Conference+on+Empirical) [our card](https://md.research.elamur.ai/free/papers/long-2022-facilitating-contrastive-learning-discourse-relational/)
25. Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101. [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2017%2E+Decoupled+weight+decay+regularization%2E+arXiv+preprint+arXiv%3A1711%2E05101%2E)
26. Courtney Napoles, Matthew R Gormley, and Benjamin Van Durme. 2012. Annotated gigaword. In Proceedings of the joint workshop on automatic knowledge base construction and web-scale knowledge extraction (AKBC-WEKEX), pages 95–100. [find](https://scholar.google.com/scholar?q=Courtney+Napoles%2C+Matthew+R+Gormley%2C+and+Benjamin+Van+Durme%2E+2012%2E+Annotated+gigaword%2E+In+Proceedings+of+the+joint+workshop+on+automatic+knowledge+base+construction+and+web%2Dscale+knowledge+extraction+)
27. Joonsuk Park and Claire Cardie. 2012. Improving implicit discourse relation recognition through feature set optimization. In Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 108–112. [find](https://scholar.google.com/scholar?q=Joonsuk+Park+and+Claire+Cardie%2E+2012%2E+Improving+implicit+discourse+relation+recognition+through+feature+set+optimization%2E+In+Proceedings+of+the+13th+Annual+Meeting+of+the+Special+Interest+Group+on+Dis) [our card](https://md.research.elamur.ai/free/papers/park-2012-improving-implicit-discourse-relation-recognition/)
28. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Milt-sakaki, Livio Robaldo, Aravind K Joshi, and Bonnie L Webber. 2008. The penn discourse treebank 2.0. In LREC. [find](https://scholar.google.com/scholar?q=Rashmi+Prasad%2C+Nikhil+Dinesh%2C+Alan+Lee%2C+Eleni+Milt%2Dsakaki%2C+Livio+Robaldo%2C+Aravind+K+Joshi%2C+and+Bonnie+L+Webber%2E+2008%2E+The+penn+discourse+treebank+2%2E0%2E+In+LREC%2E) [our card](https://md.research.elamur.ai/free/papers/disc-2008-prasad-penn-discourse-treebank-2-0/)
29. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 21(1):5485–5551. [find](https://scholar.google.com/scholar?q=Colin+Raffel%2C+Noam+Shazeer%2C+Adam+Roberts%2C+Katherine+Lee%2C+Sharan+Narang%2C+Michael+Matena%2C+Yanqi+Zhou%2C+Wei+Li%2C+and+Peter+J+Liu%2E+2020%2E+Exploring+the+limits+of+transfer+learning+with+a+unified+text%2Dto%2Dtext)
30. Attapol Rutherford and Nianwen Xue. 2015. Improving the inference of implicit discourse relations via classifying explicit discourse connectives. In HLT-NAACL, pages 799–808. [find](https://scholar.google.com/scholar?q=Attapol+Rutherford+and+Nianwen+Xue%2E+2015%2E+Improving+the+inference+of+implicit+discourse+relations+via+classifying+explicit+discourse+connectives%2E+In+HLT%2DNAACL%2C+pages+799%E2%80%93808%2E) [our card](https://md.research.elamur.ai/free/papers/rutherford-2015-improving-inference-implicit-discourse-relations/)
31. Timo Schick and Hinrich Schütze. 2021. 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 Compu… [find](https://scholar.google.com/scholar?q=Timo+Schick+and+Hinrich+Sch%C3%BCtze%2E+2021%2E+Exploiting+cloze%2Dquestions+for+few%2Dshot+text+classification+and+natural+language+inference%2E+In+Proceedings+of+the+16th+Conference+of+the+European+Chapter+of+the+) [our card](https://md.research.elamur.ai/free/papers/schick-2021-exploiting-cloze-questions-few-shot/)
32. Wei Shi and Vera Demberg. 2019. Learning to explici-tate connectives with Seq2Seq network for implicit discourse relation classification. In Proceedings of the 13th International Conference on Computational Semantics - Long Papers, pages 188–199, Gothenburg, Sweden. Association for Computational Lin… [find](https://scholar.google.com/scholar?q=Wei+Shi+and+Vera+Demberg%2E+2019%2E+Learning+to+explici%2Dtate+connectives+with+Seq2Seq+network+for+implicit+discourse+relation+classification%2E+In+Proceedings+of+the+13th+International+Conference+on+Computa)
33. Jialong Tang, Hongyu Lin, Meng Liao, Yaojie Lu, Xi-anpei Han, Le Sun, Weijian Xie, and Jin Xu. 2021. From discourse to narrative: Knowledge projection for event relation extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International… [find](https://scholar.google.com/scholar?q=Jialong+Tang%2C+Hongyu+Lin%2C+Meng+Liao%2C+Yaojie+Lu%2C+Xi%2Danpei+Han%2C+Le+Sun%2C+Weijian+Xie%2C+and+Jin+Xu%2E+2021%2E+From+discourse+to+narrative%3A+Knowledge+projection+for+event+relation+extraction%2E+In+Proceedings+of+)
34. Siddharth Varia, Christopher Hidey, and Tuhin Chakrabarty. 2019a. Discourse relation prediction: Revisiting word pairs with convolutional networks. In Proceedings of the 20th annual SIGdial meeting on discourse and dialogue, pages 442–452. [find](https://scholar.google.com/scholar?q=Siddharth+Varia%2C+Christopher+Hidey%2C+and+Tuhin+Chakrabarty%2E+2019a%2E+Discourse+relation+prediction%3A+Revisiting+word+pairs+with+convolutional+networks%2E+In+Proceedings+of+the+20th+annual+SIGdial+meeting+on) [our card](https://md.research.elamur.ai/free/papers/varia-2019-discourse-relation-prediction-revisiting-word/)
35. Siddharth Varia, Christopher Hidey, and Tuhin Chakrabarty. 2019b. 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](https://scholar.google.com/scholar?q=Siddharth+Varia%2C+Christopher+Hidey%2C+and+Tuhin+Chakrabarty%2E+2019b%2E+Discourse+relation+prediction%3A+Revisiting+word+pairs+with+convolutional+networks%2E+In+Proceedings+of+the+20th+Annual+SIGdial+Meeting+on) [our card](https://md.research.elamur.ai/free/papers/varia-2019-discourse-relation-prediction-revisiting-word/)
36. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, 30. [find](https://scholar.google.com/scholar?q=Ashish+Vaswani%2C+Noam+Shazeer%2C+Niki+Parmar%2C+Jakob+Uszkoreit%2C+Llion+Jones%2C+Aidan+N+Gomez%2C+%C5%81ukasz+Kaiser%2C+and+Illia+Polosukhin%2E+2017%2E+Attention+is+all+you+need%2E+Advances+in+neural+information+processing+)
37. Bonnie Webber, Rashmi Prasad, Alan Lee, and Aravind Joshi. 2019. The penn discourse treebank 3.0 annotation manual. Philadelphia, University of Pennsylvania, 35:108. [find](https://scholar.google.com/scholar?q=Bonnie+Webber%2C+Rashmi+Prasad%2C+Alan+Lee%2C+and+Aravind+Joshi%2E+2019%2E+The+penn+discourse+treebank+3%2E0+annotation+manual%2E+Philadelphia%2C+University+of+Pennsylvania%2C+35%3A108%2E)
38. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtow-icz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lh… [find](https://scholar.google.com/scholar?q=Thomas+Wolf%2C+Lysandre+Debut%2C+Victor+Sanh%2C+Julien+Chaumond%2C+Clement+Delangue%2C+Anthony+Moi%2C+Pier%2Dric+Cistac%2C+Tim+Rault%2C+Remi+Louf%2C+Morgan+Funtow%2Dicz%2C+Joe+Davison%2C+Sam+Shleifer%2C+Patrick+von+Platen%2C+Clara) [our card](https://md.research.elamur.ai/free/papers/wolf-2020-transformers-state-art-natural-language/)
39. Changxing Wu, Liuwen Cao, Yubin Ge, Yang Liu, Min Zhang, and Jinsong Su. 2022. A label dependence-aware sequence generation model for multi-level implicit discourse relation recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 11486–11494. [find](https://scholar.google.com/scholar?q=Changxing+Wu%2C+Liuwen+Cao%2C+Yubin+Ge%2C+Yang+Liu%2C+Min+Zhang%2C+and+Jinsong+Su%2E+2022%2E+A+label+dependence%2Daware+sequence+generation+model+for+multi%2Dlevel+implicit+discourse+relation+recognition%2E+In+Proceeding)
40. Nianwen Xue, Hwee Tou Ng, Sameer Pradhan, Attapol Rutherford, Bonnie Webber, Chuan Wang, and Hongmin Wang. 2016. [find](https://scholar.google.com/scholar?q=Nianwen+Xue%2C+Hwee+Tou+Ng%2C+Sameer+Pradhan%2C+Attapol+Rutherford%2C+Bonnie+Webber%2C+Chuan+Wang%2C+and+Hongmin+Wang%2E+2016%2E)
41. 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](https://scholar.google.com/scholar?q=CoNLL+2016+shared+task+on+multilingual+shallow+discourse+parsing%2E+In+Proceedings+of+the+CoNLL%2D16+shared+task%2C+pages+1%E2%80%9319%2C+Berlin%2C+Germany%2E+Association+for+Computational+Linguistics%2E) [our card](https://md.research.elamur.ai/free/papers/xue-2016-conll-2016-shared-task-multilingual/)
42. Biao Zhang, Jinsong Su, Deyi Xiong, Yaojie Lu, Hong Duan, and Junfeng Yao. 2015. Shallow convolutional neural network for implicit discourse relation recognition. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 2230–2235. [find](https://scholar.google.com/scholar?q=Biao+Zhang%2C+Jinsong+Su%2C+Deyi+Xiong%2C+Yaojie+Lu%2C+Hong+Duan%2C+and+Junfeng+Yao%2E+2015%2E+Shallow+convolutional+neural+network+for+implicit+discourse+relation+recognition%2E+In+Proceedings+of+the+2015+Conference) [our card](https://md.research.elamur.ai/free/papers/zhang-2015-shallow-convolutional-neural-network-implicit/)