---
title: "Improving Multi-Party Dialogue Discourse Parsing — Liu 2021"
description: "Discourse parsers for multi-party dialogue are trained on small SDRT treebanks that each cover a single domain."
authors: ["Zhengyuan Liu", "Nancy Chen"]
year: 2021
venue: "Proceedings of the 2nd Workshop on Computational Approaches to Discourse"
source: "https://aclanthology.org/2021.codi-main.11/"
doi: "10.18653/v1/2021.codi-main.11"
arxiv: "2110.04526"
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/liu-2021-improving-multi-party-dialogue-discourse/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/liu-2021-improving-multi-party-dialogue-discourse/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2021](https://md.research.elamur.ai/free/papers/2021/page/2/) / Improving Multi-Party Dialogue Discourse Parsing via Domain Integration

# Improving Multi-Party Dialogue Discourse Parsing via Domain Integration

**Authors:** [Zhengyuan Liu](https://md.research.elamur.ai/free/authors/zhengyuan-liu/), [Nancy Chen](https://md.research.elamur.ai/free/authors/nancy-chen/) · **Year:** 2021 · **Venue:** Proceedings of the 2nd Workshop on Computational Approaches to Discourse · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2021.codi-main.11/) · [PDF](https://aclanthology.org/2021.codi-main.11.pdf) · [DOI 10.18653/v1/2021.codi-main.11](https://doi.org/10.18653/v1/2021.codi-main.11) · [arXiv 2110.04526](https://arxiv.org/abs/2110.04526) · [OpenAlex](https://openalex.org/W3206379359)

**Citations:** 32 citations (openalex-snapshot · 2026-10-14) · [28](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
Discourse parsers for multi-party dialogue are trained on small SDRT treebanks that each cover a single domain. As a result, they degrade sharply on conversations from other domains. Liu and Chen first compare STAC (online strategy game chats), Molweni (Ubuntu technical forum) and, as a non-dialogue reference, RST-DT. STAC and Molweni have similar relation distributions but little shared vocabulary. The authors then build a dependency-style parser: a Transformer encodes tokens, a bidirectional GRU contextualizes EDUs across the dialogue, a pointer network chooses each EDU's head among earlier units, and a linear layer assigns one of 17 relations. To improve transfer, they add three steps: a RoBERTa-base backbone, masked-language-model pre-training on the pooled STAC and Molweni text, and removal of rare words that only one corpus uses. Together these steps substantially raise cross-domain micro-F1 without hurting in-domain scores. The work shows that SDRT parsers need explicit domain integration before they can be used reliably in practice.

## Key points
- **Data:** STAC has 1,091 training and 100 test dialogues from the Game domain. Molweni has 9,000 training and 500 test dialogues from the Ubuntu domain. Both average about 9–11 EDUs per dialogue and use the same 17-relation SDRT scheme.
- **Vocabulary refinement:** words seen fewer than 20 times that do not occur in both corpora are filtered out. This reduces overfitting to lexical cues specific to one corpus.
- **STAC → Molweni:** Link+Rel F1 rises from 26.4 to 33.1, a 25.3% relative gain. Link F1 rises from 57.8 to 63.2.
- **Molweni → STAC:** Link+Rel F1 rises from 18.0 to 28.9, a 60.6% relative gain. Link F1 rises from 42.3 to 50.5. The authors suggest the transfer drop is larger in this direction because STAC is more linguistically diverse.
- **Joint training:** training on STAC+Molweni with the RoBERTa backbone beats the Deep Sequential Parser of Shi and Huang (2019) on both test sets. Link+Rel F1 reaches 57.2 on STAC (vs. 54.8) and 56.9 on Molweni (vs. 54.3).

*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/)

## Cited by

Cited by

28 papers of our library cite it (of the 140673 whose bibliographies we read); 8 of them have a page here, 20 not yet.

- [The DISRPT 2023 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation Classification](https://md.research.elamur.ai/free/papers/braud-2023-disrpt-2023-shared-task-elementary/)
- [Structured Dialogue Discourse Parsing](https://md.research.elamur.ai/free/papers/chi-2022-structured-dialogue-discourse-parsing/)
- [Improving Dialogue Discourse Parsing via Reply-to Structures of Addressee Recognition](https://md.research.elamur.ai/free/papers/fan-2023-improving-dialogue-discourse-parsing-reply/)
- [Task-Aware Self-Supervised Framework for Dialogue Discourse Parsing](https://md.research.elamur.ai/free/papers/li-2023-task-aware-self-supervised-framework/)
- [Dialogue Discourse Parsing as Generation: A Sequence-to-Sequence LLM-based Approach](https://md.research.elamur.ai/free/papers/li-2024-dialogue-discourse-parsing-as-generation/)
- [Discourse Relation Prediction and Discourse Parsing in Dialogues with Minimal Supervision](https://md.research.elamur.ai/free/papers/li-2024-discourse-relation-prediction-discourse-parsing/)
- [Speaker-Aware Discourse Parsing on Multi-Party Dialogues](https://md.research.elamur.ai/free/papers/yu-2022-speaker-aware-discourse-parsing-multi/)
- [Multilingual Coreference Resolution in Multiparty Dialogue](https://md.research.elamur.ai/free/papers/zheng-2023-multilingual-coreference-resolution-multiparty-dialogue/)

## Cite

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

```bibtex
@inproceedings{liu2021improving,
  title = {{Improving Multi-Party Dialogue Discourse Parsing via Domain Integration}},
  author = {Liu, Zhengyuan and Chen, Nancy},
  booktitle = {Proceedings of the 2nd Workshop on Computational Approaches to Discourse},
  year = {2021},
  doi = {10.18653/v1/2021.codi-main.11},
  eprint = {2110.04526},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2021.codi-main.11}
}
```

- [← previous Improving Arabic Diacritization with Regularized Decoding and Adversarial Training](https://md.research.elamur.ai/free/papers/acl-2021-qin-improving-arabic-diacritization-regularized-decoding/)
- [next → Improving Stance Detection with Multi-Dataset Learning and Knowledge Distillation](https://md.research.elamur.ai/free/papers/li-2021-improving-stance-detection-multi-dataset/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/papers/2021/page/2/)

## References

22 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Nicholas Asher, Julie Hunter, Mathieu Morey, Bena-To evaluate the effectiveness of the proposed mara Farah, and Stergos Afantenos. 2016. Dis-domain integration methods, we conduct single-course structure and dialogue acts in multiparty di-corpus training and cross-corpus evaluation (each alogue: the… [find](https://scholar.google.com/scholar?q=Nicholas+Asher%2C+Julie+Hunter%2C+Mathieu+Morey%2C+Bena%2DTo+evaluate+the+effectiveness+of+the+proposed+mara+Farah%2C+and+Stergos+Afantenos%2E+2016%2E+Dis%2Ddomain+integration+methods%2C+we+conduct+single%2Dcourse+struct)
2. Sonia Badene, Kate Thompson, Jean-Pierre Lorré, and Nicholas Asher. 2019. Weak supervision for learning discourse structure. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCN… [find](https://scholar.google.com/scholar?q=Sonia+Badene%2C+Kate+Thompson%2C+Jean%2DPierre+Lorr%C3%A9%2C+and+Nicholas+Asher%2E+2019%2E+Weak+supervision+for+learning+discourse+structure%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+Langu)
3. Lynn Carlson, Mary Ellen Okurowski, and Daniel Marcu. 2002. RST discourse treebank. Linguistic Data Consortium, University of Pennsylvania. [find](https://scholar.google.com/scholar?q=Lynn+Carlson%2C+Mary+Ellen+Okurowski%2C+and+Daniel+Marcu%2E+2002%2E+RST+discourse+treebank%2E+Linguistic+Data+Consortium%2C+University+of+Pennsylvania%2E)
4. Junyoung Chung, Caglar Gulcehre, Kyunghyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. In NIPS 2014 Workshop on Deep Learning, December 2014. [find](https://scholar.google.com/scholar?q=Junyoung+Chung%2C+Caglar+Gulcehre%2C+Kyunghyun+Cho%2C+and+Yoshua+Bengio%2E+2014%2E+Empirical+evaluation+of+gated+recurrent+neural+networks+on+sequence+modeling%2E+In+NIPS+2014+Workshop+on+Deep+Learning%2C+December+)
5. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL2019, pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics. [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+NAACL2019%2C+pages+4171%E2%80%934186%2C+)
6. Xiachong Feng, Xiaocheng Feng, Bing Qin, Xinwei Geng, and Ting Liu. 2020. Dialogue discourse-aware graph convolutional networks for abstractive meeting summarization. arXiv preprint arXiv:2012.03502. — [arXiv:2012.03502](https://arxiv.org/abs/2012.03502) [find](https://scholar.google.com/scholar?q=Xiachong+Feng%2C+Xiaocheng+Feng%2C+Bing+Qin%2C+Xinwei+Geng%2C+and+Ting+Liu%2E+2020%2E+Dialogue+discourse%2Daware+graph+convolutional+networks+for+abstractive+meeting+summarization%2E+arXiv+preprint+arXiv%3A2012%2E03502%2E+)
7. Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, and Noah A. Smith. 2020. Don’t stop pretraining: Adapt language models to domains and tasks. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=Suchin+Gururangan%2C+Ana+Marasovic%CC%81%2C+Swabha+Swayamdipta%2C+Kyle+Lo%2C+Iz+Beltagy%2C+Doug+Downey%2C+and+Noah+A%2E+Smith%2E+2020%2E+Don%E2%80%99t+stop+pretraining%3A+Adapt+language+models+to+domains+and+tasks%2E+In+Proceedings+of+)
8. Jiaqi Li, Ming Liu, Min-Yen Kan, Zihao Zheng, Zekun Wang, Wenqiang Lei, Ting Liu, and Bing Qin. 2020. Molweni: A challenge multiparty dialogues-based machine reading comprehension dataset with discourse structure. In Proceedings of the 28th International Conference on Computational Linguistics, page… [find](https://scholar.google.com/scholar?q=Jiaqi+Li%2C+Ming+Liu%2C+Min%2DYen+Kan%2C+Zihao+Zheng%2C+Zekun+Wang%2C+Wenqiang+Lei%2C+Ting+Liu%2C+and+Bing+Qin%2E+2020%2E+Molweni%3A+A+challenge+multiparty+dialogues%2Dbased+machine+reading+comprehension+dataset+with+discour)
9. Jiwei Li, Rumeng Li, and Eduard Hovy. 2014a. Recursive deep models for discourse parsing. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2061–2069. [find](https://scholar.google.com/scholar?q=Jiwei+Li%2C+Rumeng+Li%2C+and+Eduard+Hovy%2E+2014a%2E+Recursive+deep+models+for+discourse+parsing%2E+In+Proceedings+of+the+2014+Conference+on+Empirical+Methods+in+Natural+Language+Processing+%28EMNLP%29%2C+pages+2061%E2%80%93) [our card](https://md.research.elamur.ai/free/papers/li-2014-recursive-deep-models-discourse-parsing/)
10. Sujian Li, Liang Wang, Ziqiang Cao, and Wenjie Li. 2014b. Text-level discourse dependency parsing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 25–35. [find](https://scholar.google.com/scholar?q=Sujian+Li%2C+Liang+Wang%2C+Ziqiang+Cao%2C+and+Wenjie+Li%2E+2014b%2E+Text%2Dlevel+discourse+dependency+parsing%2E+In+Proceedings+of+the+52nd+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+25%E2%80%93)
11. 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)
12. Zhengyuan Liu, Ke Shi, and Nancy Chen. 2020. Multilingual neural RST discourse parsing. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6730–6738, Barcelona, Spain (Online). International Committee on Computational Linguistics. [find](https://scholar.google.com/scholar?q=Zhengyuan+Liu%2C+Ke+Shi%2C+and+Nancy+Chen%2E+2020%2E+Multilingual+neural+RST+discourse+parsing%2E+In+Proceedings+of+the+28th+International+Conference+on+Computational+Linguistics%2C+pages+6730%E2%80%936738%2C+Barcelona%2C+Sp) [our card](https://md.research.elamur.ai/free/papers/liu-2020-multilingual-neural-rst-discourse-parsing/)
13. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. The International Conference on Learning Representations (ICLR2019). [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2019%2E+Decoupled+weight+decay+regularization%2E+The+International+Conference+on+Learning+Representations+%28ICLR2019%29%2E)
14. Ryan McDonald, Fernando Pereira, Kiril Ribarov, and Jan Hajic. 2005. Non-projective dependency parsing using spanning tree algorithms. In Proceedings of human language technology conference and conference on empirical methods in natural language processing, pages 523–530. [find](https://scholar.google.com/scholar?q=Ryan+McDonald%2C+Fernando+Pereira%2C+Kiril+Ribarov%2C+and+Jan+Hajic%2E+2005%2E+Non%2Dprojective+dependency+parsing+using+spanning+tree+algorithms%2E+In+Proceedings+of+human+language+technology+conference+and+confer) [our card](https://md.research.elamur.ai/free/papers/narrative-2005-mcdonald-non-projective-dependency-parsing-spanning/)
15. Karthik Narasimhan and Regina Barzilay. 2015. Machine comprehension with discourse relations. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages 1253–1262, Beijing, China. Associa… [find](https://scholar.google.com/scholar?q=Karthik+Narasimhan+and+Regina+Barzilay%2E+2015%2E+Machine+comprehension+with+discourse+relations%2E+In+Proceedings+of+the+53rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+the+7th+Int) [our card](https://md.research.elamur.ai/free/papers/narasimhan-2015-machine-comprehension-discourse-relations/)
16. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. In Proceedings of NeurIPS2019, pages 8026–8037. [find](https://scholar.google.com/scholar?q=Adam+Paszke%2C+Sam+Gross%2C+Francisco+Massa%2C+Adam+Lerer%2C+James+Bradbury%2C+Gregory+Chanan%2C+Trevor+Killeen%2C+Zeming+Lin%2C+Natalia+Gimelshein%2C+Luca+Antiga%2C+et+al%2E+2019%2E+Pytorch%3A+An+imperative+style%2C+high%2Dperfor) [our card](https://md.research.elamur.ai/free/papers/paszke-2019-pytorch-imperative-style-high-performance/)
17. 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. Citeseer. [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+Citeseer%2E) [our card](https://md.research.elamur.ai/free/papers/disc-2008-prasad-penn-discourse-treebank-2-0/)
18. Zhouxing Shi and Minlie Huang. 2019. A deep sequential model for discourse parsing on multi-party dialogues. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 7007–7014. [find](https://scholar.google.com/scholar?q=Zhouxing+Shi+and+Minlie+Huang%2E+2019%2E+A+deep+sequential+model+for+discourse+parsing+on+multi%2Dparty+dialogues%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+33%2C+pages+7007%E2%80%93701)
19. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of NeurIPS2017, pages 5998–6008. [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+In+Proceedings+of+NeurIPS2017%2C+pages+5998%E2%80%93)
20. Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer networks. In Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Oriol+Vinyals%2C+Meire+Fortunato%2C+and+Navdeep+Jaitly%2E+2015%2E+Pointer+networks%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+28%2E+Curran+Associates%2C+Inc%2E)
21. 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](https://scholar.google.com/scholar?q=Jiacheng+Xu%2C+Zhe+Gan%2C+Yu+Cheng%2C+and+Jingjing+Liu%2E+2020%2E+Discourse%2Daware+neural+extractive+text+summarization%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Computational+Linguistics) [our card](https://md.research.elamur.ai/free/papers/xu-2019-discourse-aware-neural-extractive-text/)
22. Chaohui Yu, Jindong Wang, Yiqiang Chen, and Meiyu Huang. 2019. Transfer learning with dynamic adversarial adaptation network. In 2019 IEEE International Conference on Data Mining (ICDM), pages 778–786. IEEE. [find](https://scholar.google.com/scholar?q=Chaohui+Yu%2C+Jindong+Wang%2C+Yiqiang+Chen%2C+and+Meiyu+Huang%2E+2019%2E+Transfer+learning+with+dynamic+adversarial+adaptation+network%2E+In+2019+IEEE+International+Conference+on+Data+Mining+%28ICDM%29%2C+pages+778%E2%80%93786)