---
title: "A Distance-Aware Multi-Task Framework for — Fan 2022"
description: "This paper addresses conversational discourse parsing in the SDRT tradition."
authors: ["Yaxin Fan", "Peifeng Li", "Fang Kong", "Qiaoming Zhu"]
year: 2022
venue: "Proceedings of the 29th International Conference on Computational Linguistics"
source: "https://aclanthology.org/2022.coling-1.76/"
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/fan-2022-distance-aware-multi-task-framework/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/fan-2022-distance-aware-multi-task-framework/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2022](https://md.research.elamur.ai/free/papers/2022/) / A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing

# A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing

**Authors:** [Yaxin Fan](https://md.research.elamur.ai/free/authors/yaxin-fan/), [Peifeng Li](https://md.research.elamur.ai/free/authors/peifeng-li/), [Fang Kong](https://md.research.elamur.ai/free/authors/fang-kong/), [Qiaoming Zhu](https://md.research.elamur.ai/free/authors/qiaoming-zhu/) · **Year:** 2022 · **Venue:** Proceedings of the 29th International Conference on Computational Linguistics · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2022.coling-1.76/) · [PDF](https://aclanthology.org/2022.coling-1.76.pdf) · [OpenAlex](https://openalex.org/W6910587050)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14) · [11](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## Summary
This paper addresses conversational discourse parsing in the SDRT tradition. The task is to connect each utterance (EDU) of a multi-party dialogue to an earlier one and label the relation, which yields a dependency tree. The authors note that the two main parser families are good at different things. Graph-based parsers score every EDU pair and decode globally, so they handle links between adjacent utterances better. Transition-based parsers build the tree incrementally and do better when a link spans several utterances.

To combine these strengths, they propose DAMT, a multi-task model that trains both paradigms on a hierarchical GRU encoder. It has two key parts:
- An Encoding Interactive Module (EIM) uses self-attention and cross-attention so the two paradigms can exchange information during encoding.
- A Distance-Aware Graph Convolutional Network (DAGCN) passes the links predicted by a pointer-network transition decoder, grouped by distance, to the graph-based decoder.

On STAC and Molweni, DAMT outperforms state-of-the-art baselines, with the largest gains on long-distance links. Better discourse structure can help downstream dialogue tasks such as reading comprehension and summarization.

## Key points
- Analysis on both corpora: the graph-based paradigm wins at distance 1, while the transition-based one wins at distances above 1.
- Datasets use 16 relation types. STAC (from *The Settlers of Catan* game chats) has 1,062 training and 111 test dialogues. Molweni (from Ubuntu Chat) has 9,000/500/500 train/validation/test instances.
- Compared baselines include the graph-based SSAM and the transition-based pointer network (PN).
- In the ablation, removing DAGCN hurts performance most, and removing EIM also lowers scores. Gains are largest for dialogues with 11 and 8 EDUs (about 9% and 4%), which also have the highest shares of long links (41% and 43%).
- Code is released at github.com/yxfanSuda/DAMT.

*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/) · [Dependency parsing](https://md.research.elamur.ai/free/topics/dependency-parsing/)

## Cited by

Cited by

11 papers of our library cite it (of the 140673 whose bibliographies we read); 4 of them have a page here, 7 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/)
- [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/)
- [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/)

## Cite

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

```bibtex
@inproceedings{fan2022distance,
  title = {{A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing}},
  author = {Fan, Yaxin and Li, Peifeng and Kong, Fang and Zhu, Qiaoming},
  booktitle = {Proceedings of the 29th International Conference on Computational Linguistics},
  year = {2022},
  doi = {10.48448/qp5b-0w87},
  url = {https://doi.org/10.48448/qp5b-0w87}
}
```

- [← previous A Dependency Treebank of Spoken Second Language English](https://md.research.elamur.ai/free/papers/kyle-2022-dependency-treebank-spoken-second-language/)
- [next → A Double-Graph Based Framework for Frame Semantic Parsing](https://md.research.elamur.ai/free/papers/zheng-2022-double-graph-based-framework-frame/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/papers/2022/)

## References

26 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Stergos Afantenos, Éric Kow, Nicholas Asher, and Jérémy Perret. 2015. Discourse parsing for multi-party chat dialogues. In EMNLP, pages 928–937. [find](https://scholar.google.com/scholar?q=Stergos+Afantenos%2C+%C3%89ric+Kow%2C+Nicholas+Asher%2C+and+J%C3%A9r%C3%A9my+Perret%2E+2015%2E+Discourse+parsing+for+multi%2Dparty+chat+dialogues%2E+In+EMNLP%2C+pages+928%E2%80%93937%2E) [our card](https://md.research.elamur.ai/free/papers/afantenos-2015-discourse-parsing-multi-party-chat/)
2. Nicholas Asher, Nicholas Michael Asher, and Alex Lascarides. 2003. Logics of conversation. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Nicholas+Asher%2C+Nicholas+Michael+Asher%2C+and+Alex+Lascarides%2E+2003%2E+Logics+of+conversation%2E+Cambridge+University+Press%2E)
3. Nicholas Asher, Julie Hunter, Mathieu Morey, Farah Benamara, and Stergos Afantenos. 2016. Discourse structure and dialogue acts in multiparty dialogue: the stac corpus. In LREC, pages 2721–2727. [find](https://scholar.google.com/scholar?q=Nicholas+Asher%2C+Julie+Hunter%2C+Mathieu+Morey%2C+Farah+Benamara%2C+and+Stergos+Afantenos%2E+2016%2E+Discourse+structure+and+dialogue+acts+in+multiparty+dialogue%3A+the+stac+corpus%2E+In+LREC%2C+pages+2721%E2%80%932727%2E) [our card](https://md.research.elamur.ai/free/papers/asher-2016-discourse-structure-dialogue-acts-multiparty/)
4. Lynn Carlson, Daniel Marcu, and Mary Ellen Okurowski. 2003. Building a discourse-tagged corpus in the framework of rhetorical structure theory. In Current and new directions in discourse and dialogue, pages 85–112. Springer. [find](https://scholar.google.com/scholar?q=Lynn+Carlson%2C+Daniel+Marcu%2C+and+Mary+Ellen+Okurowski%2E+2003%2E+Building+a+discourse%2Dtagged+corpus+in+the+framework+of+rhetorical+structure+theory%2E+In+Current+and+new+directions+in+discourse+and+dialogue%2C) [our card](https://md.research.elamur.ai/free/papers/carlson-2001-building-discourse-tagged-corpus-framework/)
5. Jiaqi Li, Ming Liu, Zihao Zheng, Heng Zhang, Bing Qin, Min-Yen Kan, and Ting Liu. 2021b. Dadgraph: A discourse-aware dialogue graph neural network for multiparty dialogue machine reading comprehension. In IJCNN, pages 1–8. [find](https://scholar.google.com/scholar?q=Jiaqi+Li%2C+Ming+Liu%2C+Zihao+Zheng%2C+Heng+Zhang%2C+Bing+Qin%2C+Min%2DYen+Kan%2C+and+Ting+Liu%2E+2021b%2E+Dadgraph%3A+A+discourse%2Daware+dialogue+graph+neural+network+for+multiparty+dialogue+machine+reading+comprehension)
6. Yiyang Li and Hai Zhao. 2021. Self- and pseudo-self-supervised prediction of speaker and key-utterance for multi-party dialogue reading comprehension. In Findings of EMNLP, pages 2053–2063. [find](https://scholar.google.com/scholar?q=Yiyang+Li+and+Hai+Zhao%2E+2021%2E+Self%2D+and+pseudo%2Dself%2Dsupervised+prediction+of+speaker+and+key%2Dutterance+for+multi%2Dparty+dialogue+reading+comprehension%2E+In+Findings+of+EMNLP%2C+pages+2053%E2%80%932063%2E)
7. Xiang Lin, Shafiq Joty, Prathyusha Jwalapuram, and M Saiful Bari. 2019. A unified linear-time framework for sentence-level discourse parsing. In ACL, pages 4190–4200. [find](https://scholar.google.com/scholar?q=Xiang+Lin%2C+Shafiq+Joty%2C+Prathyusha+Jwalapuram%2C+and+M+Saiful+Bari%2E+2019%2E+A+unified+linear%2Dtime+framework+for+sentence%2Dlevel+discourse+parsing%2E+In+ACL%2C+pages+4190%E2%80%934200%2E) [our card](https://md.research.elamur.ai/free/papers/lin-2019-unified-linear-time-framework-sentence/)
8. Yang Liu and Mirella Lapata. 2017. Learning contextually informed representations for linear-time discourse parsing. In EMNLP, pages 1289–1298. [find](https://scholar.google.com/scholar?q=Yang+Liu+and+Mirella+Lapata%2E+2017%2E+Learning+contextually+informed+representations+for+linear%2Dtime+discourse+parsing%2E+In+EMNLP%2C+pages+1289%E2%80%931298%2E) [our card](https://md.research.elamur.ai/free/papers/liu-2017-learning-contextually-informed-representations-linear/)
9. Haihong E, Peiqing Niu, Zhongfu Chen, and Meina Song. 2019. A novel bi-directional interrelated model for joint intent detection and slot filling. In ACL, pages 5467–5471. [find](https://scholar.google.com/scholar?q=Haihong+E%2C+Peiqing+Niu%2C+Zhongfu+Chen%2C+and+Meina+Song%2E+2019%2E+A+novel+bi%2Ddirectional+interrelated+model+for+joint+intent+detection+and+slot+filling%2E+In+ACL%2C+pages+5467%E2%80%935471%2E)
10. Ryan Lowe, Nissan Pow, Iulian Vlad Serban, and Joelle Pineau. 2015. The ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems. In SIGDIAL, pages 285–294. [find](https://scholar.google.com/scholar?q=Ryan+Lowe%2C+Nissan+Pow%2C+Iulian+Vlad+Serban%2C+and+Joelle+Pineau%2E+2015%2E+The+ubuntu+dialogue+corpus%3A+A+large+dataset+for+research+in+unstructured+multi%2Dturn+dialogue+systems%2E+In+SIGDIAL%2C+pages+285%E2%80%93294%2E) [our card](https://md.research.elamur.ai/free/papers/lowe-2015-ubuntu-dialogue-corpus-large-dataset/)
11. Agnieszka Falenska, Anders Björkelund, and Jonas Kuhn. 2020. Integrating graph-based and transition-based dependency parsers in the deep contextualized era. In IWPT, pages 25–39. [find](https://scholar.google.com/scholar?q=Agnieszka+Falenska%2C+Anders+Bj%C3%B6rkelund%2C+and+Jonas+Kuhn%2E+2020%2E+Integrating+graph%2Dbased+and+transition%2Dbased+dependency+parsers+in+the+deep+contextualized+era%2E+In+IWPT%2C+pages+25%E2%80%9339%2E) [our card](https://md.research.elamur.ai/free/papers/ud-2020-falenska-integrating-graph-based-transition-based/)
12. William C Mann and Sandra A Thompson. 1987. Rhetorical structure theory: A theory of text organization. Information Sciences Institute, Los Angeles: University of Southern California. [find](https://scholar.google.com/scholar?q=William+C+Mann+and+Sandra+A+Thompson%2E+1987%2E+Rhetorical+structure+theory%3A+A+theory+of+text+organization%2E+Information+Sciences+Institute%2C+Los+Angeles%3A+University+of+Southern+California%2E)
13. Fanyu Meng, Junlan Feng, Danping Yin, Si Chen, and Min Hu. 2020. A structure-enhanced graph convolutional network for sentiment analysis. In Findings of EMNLP, pages 586–595, Online. [find](https://scholar.google.com/scholar?q=Fanyu+Meng%2C+Junlan+Feng%2C+Danping+Yin%2C+Si+Chen%2C+and+Min+Hu%2E+2020%2E+A+structure%2Denhanced+graph+convolutional+network+for+sentiment+analysis%2E+In+Findings+of+EMNLP%2C+pages+586%E2%80%93595%2C+Online%2E)
14. Philippe Muller, Stergos Afantenos, Pascal Denis, and Nicholas Asher. 2012. Constrained decoding for text-level discourse parsing. In COLING, pages 1883– 1900. [find](https://scholar.google.com/scholar?q=Philippe+Muller%2C+Stergos+Afantenos%2C+Pascal+Denis%2C+and+Nicholas+Asher%2E+2012%2E+Constrained+decoding+for+text%2Dlevel+discourse+parsing%2E+In+COLING%2C+pages+1883%E2%80%93+1900%2E) [our card](https://md.research.elamur.ai/free/papers/muller-2012-constrained-decoding-text-level-discourse/)
15. Jeffrey Pennington, Richard Socher, and Christopher D Manning. 2014. Glove: Global vectors for word representation. In EMNLP, pages 1532–1543. [find](https://scholar.google.com/scholar?q=Jeffrey+Pennington%2C+Richard+Socher%2C+and+Christopher+D+Manning%2E+2014%2E+Glove%3A+Global+vectors+for+word+representation%2E+In+EMNLP%2C+pages+1532%E2%80%931543%2E)
16. Jérémy Perret, Stergos Afantenos, Nicholas Asher, and Mathieu Morey. 2016. Integer linear programming for discourse parsing. In NAACL, pages 99–109. [find](https://scholar.google.com/scholar?q=J%C3%A9r%C3%A9my+Perret%2C+Stergos+Afantenos%2C+Nicholas+Asher%2C+and+Mathieu+Morey%2E+2016%2E+Integer+linear+programming+for+discourse+parsing%2E+In+NAACL%2C+pages+99%E2%80%93109%2E) [our card](https://md.research.elamur.ai/free/papers/perret-2016-integer-linear-programming-discourse-parsing/)
17. Libo Qin, Tailu Liu, Wanxiang Che, Bingbing Kang, Sendong Zhao, and Ting Liu. 2021. A co-interactive transformer for joint slot filling and intent detection. In ICASSP, pages 8193–8197. [find](https://scholar.google.com/scholar?q=Libo+Qin%2C+Tailu+Liu%2C+Wanxiang+Che%2C+Bingbing+Kang%2C+Sendong+Zhao%2C+and+Ting+Liu%2E+2021%2E+A+co%2Dinteractive+transformer+for+joint+slot+filling+and+intent+detection%2E+In+ICASSP%2C+pages+8193%E2%80%938197%2E)
18. Zhouxing Shi and Minlie Huang. 2019. A deep sequential model for discourse parsing on multi-party dialogues. In AAAI, 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+AAAI%2C+pages+7007%E2%80%937014%2E)
19. Yang Sun, Nan Yu, and Guohong Fu. 2021. A discourse-aware graph neural network for emotion recognition in multi-party conversation. In Findings of ACL, pages 2949–2958. [find](https://scholar.google.com/scholar?q=Yang+Sun%2C+Nan+Yu%2C+and+Guohong+Fu%2E+2021%2E+A+discourse%2Daware+graph+neural+network+for+emotion+recognition+in+multi%2Dparty+conversation%2E+In+Findings+of+ACL%2C+pages+2949%E2%80%932958%2E)
20. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In NIPS, page 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%81+ukasz+Kaiser%2C+and+Illia+Polosukhin%2E+2017%2E+Attention+is+all+you+need%2E+In+NIPS%2C+page+5998%E2%80%936008%2E)
21. Ante Wang, Linfeng Song, Hui Jiang, Shaopeng Lai, Junfeng Yao, Min Zhang, and Jinsong Su. 2021a. A structure self-aware model for discourse parsing on multi-party dialogues. In IJCAI, pages 3943–3949. [find](https://scholar.google.com/scholar?q=Ante+Wang%2C+Linfeng+Song%2C+Hui+Jiang%2C+Shaopeng+Lai%2C+Junfeng+Yao%2C+Min+Zhang%2C+and+Jinsong+Su%2E+2021a%2E+A+structure+self%2Daware+model+for+discourse+parsing+on+multi%2Dparty+dialogues%2E+In+IJCAI%2C+pages+3943%E2%80%933949%2E)
22. Jinfeng Wang, Longyin Zhang, and Fang Kong. 2021b. Multi-level cohesion information modeling for better written and dialogue discourse parsing. In NLPCC, pages 40–52. [find](https://scholar.google.com/scholar?q=Jinfeng+Wang%2C+Longyin+Zhang%2C+and+Fang+Kong%2E+2021b%2E+Multi%2Dlevel+cohesion+information+modeling+for+better+written+and+dialogue+discourse+parsing%2E+In+NLPCC%2C+pages+40%E2%80%9352%2E)
23. Yizhong Wang, Sujian Li, and Houfeng Wang. 2017. A two-stage parsing method for text-level discourse analysis. In ACL, pages 184–188. [find](https://scholar.google.com/scholar?q=Yizhong+Wang%2C+Sujian+Li%2C+and+Houfeng+Wang%2E+2017%2E+A+two%2Dstage+parsing+method+for+text%2Dlevel+discourse+analysis%2E+In+ACL%2C+pages+184%E2%80%93188%2E) [our card](https://md.research.elamur.ai/free/papers/wang-2017-two-stage-parsing-method-text/)
24. Jingxuan Yang, Kerui Xu, Jun Xu, Si Li, Sheng Gao, Jun Guo, Nianwen Xue, and Ji-Rong Wen. 2021. A joint model for dropped pronoun recovery and conversational discourse parsing in Chinese conversational speech. In ACL, pages 1752–1763. [find](https://scholar.google.com/scholar?q=Jingxuan+Yang%2C+Kerui+Xu%2C+Jun+Xu%2C+Si+Li%2C+Sheng+Gao%2C+Jun+Guo%2C+Nianwen+Xue%2C+and+Ji%2DRong+Wen%2E+2021%2E+A+joint+model+for+dropped+pronoun+recovery+and+conversational+discourse+parsing+in+Chinese+conversationa) [our card](https://md.research.elamur.ai/free/papers/yang-2021-joint-model-dropped-pronoun-recovery/)
25. Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. In NIPS, volume 32. [find](https://scholar.google.com/scholar?q=Zhilin+Yang%2C+Zihang+Dai%2C+Yiming+Yang%2C+Jaime+Carbonell%2C+Russ+R+Salakhutdinov%2C+and+Quoc+V+Le%2E+2019%2E+Xlnet%3A+Generalized+autoregressive+pretraining+for+language+understanding%2E+In+NIPS%2C+volume+32%2E) [our card](https://md.research.elamur.ai/free/papers/yang-2019-xlnet-generalized-autoregressive-pretraining-language/)
26. Longyin Zhang, Fang Kong, and Guodong Zhou. 2021. Adversarial learning for discourse rhetorical structure parsing. In ACL-IJCNLP, pages 3946–3957. [find](https://scholar.google.com/scholar?q=Longyin+Zhang%2C+Fang+Kong%2C+and+Guodong+Zhou%2E+2021%2E+Adversarial+learning+for+discourse+rhetorical+structure+parsing%2E+In+ACL%2DIJCNLP%2C+pages+3946%E2%80%933957%2E) [our card](https://md.research.elamur.ai/free/papers/zhang-2021-adversarial-learning-discourse-rhetorical-structure/)