Elamur Research⌕
☰
home / papers / 2025 / The DISRPT 2025 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation Classification

The DISRPT 2025 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation Classification

Paper · 2025 · Chloé Braud, Amir Zeldes, Chuyuan Li et al.

Summary

DISRPT 2025 is the fourth edition of a shared task on discourse analysis that spans several annotation frameworks. It has three subtasks: finding where elementary discourse units (EDUs) begin, spotting discourse connectives, and labeling the relation between two attached units. The benchmark grew to 39 datasets in 16 languages and six frameworks. These are RST, SDRT, DEP and PDTB, plus two newcomers, ISO and eRST. It also adds Czech, Polish and Nigerian Pidgin and more dialogue data.

Two design changes aim at joint, reproducible modeling:

  • The many framework-specific relation labels were collapsed into 17 coarse classes.
  • Each team had to submit one model per task, capped at 4B parameters, which the organizers then re-ran.

Five teams took part. The best reproduced scores were:

  • Relation classification: about 71% mean accuracy (DeDisCo), well above the 2023 best.
  • Segmentation: 91.57 / 87.38 F1.
  • Connective detection: 81.53 / 79.92 F1.

In each pair, the first number is the Treebanked track and the second the Plain track. The outcome suggests that one multilingual model can beat per-dataset systems. Small datasets, out-of-domain sets and low-resource languages still lag behind.

Key points

  • Data: 39 datasets, 16 languages and 6 frameworks, including 13 new datasets. Six datasets are surprise releases from the final phase, among them Polish, Nigerian Pidgin and ISO data. Six are out-of-domain sets with only dev/test splits. Dialogue datasets rose from two to six.
  • Labels: the relation inventory, earlier cut from 350 to 191 labels, is now mapped to 17 coarse labels shared across frameworks.
  • Rules: one set of parameters and hyper-parameters per task must cover all datasets, with a cap of 4B parameters. Ensembles and pipelines were allowed within that cap.
  • Winners:
    • DiscUT (MELODI) won Treebanked segmentation and Treebanked connectives, narrowly ahead of HITS on connectives.
    • SeCoRel (AU-KBC) won Plain segmentation.
    • MELODI won Plain connectives.
    • DeDisCo (Georgetown) won relation classification with 71.19 reproduced and 71.28 reported, versus 62.36 for the best 2023 system.
  • Weak spots: on six datasets relation accuracy hovers around or under 60%: the Turkish TEDm set, French ANNODIS, the English STS set, Nigerian Pidgin DiscoNaija, the Farsi PRSTC set and the Basque ERT set. Connective detection shows large Plain-track drops for Italian LUNA, Polish PDC and Turkish TEDm.

Interesting ideas

  • I1. Collapsing hundreds of framework-specific relation names into a small coarse shared inventory made it practical to pool corpora and train one joint model.
  • I2. Running every task in two tracks, with gold sentence boundaries and morpho-syntax versus raw tokens, shows how much a component leans on upstream annotation.
  • I3. Holding back surprise datasets until the final phase, and including out-of-domain sets with no training split, tests real generalization instead of fit to known corpora.
  • I4. The winning relation classifier feeds the relation's direction and the surrounding context into an instruction-style decoder prompt, and its ablation shows these two inputs give the biggest gains.
  • I5. Capping model size and having organizers re-run every submission keeps results comparable and reproducible across teams.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (frames): Mova could map speech-act and inter-clause relation labels from different sources onto one compact coarse set, so that heterogeneous silver data can feed a single prag model.
  • I2 (learn): Mova could score frames and answers both on gold UD trees and on its own parser output, so the gap attributes errors to the parser rather than to later stages.
  • I3 (learn): Mova could keep sealed, never-trained-on genres of tales and test sets as negative controls, checking that self-induced repair rules do not only fit familiar text.
  • I4 (world): when Mova orders events or links states between clauses, it could encode which unit points to which and keep neighboring context, instead of judging clause pairs in isolation.
  • I5 (learn): Mova could set a fixed compute budget for each pipeline stage and require that evaluation numbers be regenerated from saved models rather than taken from logs.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of PittsburghPittsburgh · United States59 works · 22,324 citations🎓University of British ColumbiaVancouver · Canada98 works · 34,805 citations🔬Centre National de la Recherche ScientifiqueParis · France168 works · 62,369 citations🎓Georgetown UniversityWashington · United States88 works · 4,732 citations🔬Institut de Recherche en Informatique de ToulouseToulouse · France35 works · 1,872 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksPhilosophy · 284 works

🧭 Topics 1Research subjects and languages the work is about.Discourse analysis · 466 works

Cite

Cite as Chloé Braud, Amir Zeldes, Chuyuan Li, Yang Janet Liu and Philippe Muller. 2025. The DISRPT 2025 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation Classification. Proceedings of the 4th Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2025).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.disrpt-1.1

@inproceedings{braud2025disrpt,
  title = {{The DISRPT 2025 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation Classification}},
  author = {Chloé Braud, Amir Zeldes, Chuyuan Li, Yang Janet Liu and Philippe Muller},
  booktitle = {Proceedings of the 4th Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2025)},
  year = {2025},
  doi = {10.18653/v1/2025.disrpt-1.1},
  url = {https://doi.org/10.18653/v1/2025.disrpt-1.1}
}

References

110 references, 32 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Stergos Afantenos, Nicholas Asher, Farah Benamara, Myriam Bras, Cécile Fabre, Mai Ho-dac, Anne Le Draoulec, Philippe Muller, Marie-Paule Péry-Woodley, Laurent Prévot, Josette Rebeyrolles, Ludovic Tanguy, Marianne Vergez-Couret, and Laure Vieu. 2012. An empirical resource for discovering cognitive principles of discourse organisation: the ANNODIS corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 2727–2734, Istanbul, Turkey. European Language Resources Association (ELRA). ↗
  2. Harry Bunt and Rashmi Prasad. 2016. Iso dr-core (iso 24617-8): Core concepts for the annotation of discourse relations. In Proceedings 12th joint ACL-ISO workshop on interoperable semantic annotation (ISA-12), pages 45–54. find
  3. Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue, editors. 2024. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). ELRA and ICCL, Torino, Italy. find
  4. Tatsuya Aoyama, Shabnam Behzad, Luke Gessler, Lauren Levine, Jessica Lin, Yang Janet Liu, Siyao Peng, Yilun Zhu, and Amir Zeldes. 2023. GENTLE: A genre-diverse multilayer challenge set for English NLP and linguistic evaluation. In Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII), pages 166–178, Toronto, Canada.
  5. Shuyuan Cao, Iria da Cunha, and Mikel Iruskieta. 2018. The RST Spanish-Chinese treebank. In Proceedings of the Joint Workshop on Linguistic Annotation, Multiword Expressions and Constructions (LAW-MWE-CxG-2018), pages 156–166, Santa Fe, New Mexico, USA. Association for Computational Linguistics. find
  6. Nicholas Asher, Julie Hunter, Mathieu Morey, Benamara Farah, and Stergos Afantenos. 2016. Discourse structure and dialogue acts in multiparty dialogue: the STAC corpus. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 2721–2727, Portorož, Slovenia. European Language Resources Association (ELRA). ↗
  7. Paula Christina Figueira Cardoso, Erick Galani Maziero, Maria Lucía del Rosario Castro Jorge, M. Eloize, R. Kibar Aji Seno, Ariani Di Felippo, Lucia Helena Machado Rino, Maria das Graças Volpe Nunes, and Thiago Alexandre Salgueiro Pardo. 2011. CST-News - a discourse-annotated corpus for single and multi-document summarization of news texts in Brazilian Portuguese. In Proceedings of the 3rd RST Brazilian Meeting, pages 88–105, Cuiabá, Brazil. find
  8. Farah Benamara and Maite Taboada. 2015. Mapping different rhetorical relation annotations: A proposal. In Proceedings of Starsem. find
  9. Lynn Carlson, Daniel Marcu, and Mary Ellen Okurovsky. 2001. Building a discourse-tagged corpus in the framework of Rhetorical Structure Theory. In Proceedings of the Second SIGdial Workshop on Discourse and Dialogue. ↗
  10. Tillmann Dönicke. 2021. Delexicalised multilingual discourse segmentation for DISRPT 2021 and tense, mood, voice and modality tagging for 11 languages. In Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021), pages 33–45, Punta Cana, Dominican Republic. Association for Computational Linguistics. find
  11. Yapei Chang, Kyle Lo, Tanya Goyal, and Mohit Iyyer. 2024. Booookscore: A systematic exploration of book-length summarization in the era of LLMs. In The Twelfth International Conference on Learning Representations. ↗
  12. Florian Eichin, Yang Janet Liu, Barbara Plank, and Michael A. Hedderich. 2025. Probing LLMs for multilingual discourse generalization through a unified label set. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 18665–18684, Vienna, Austria. Association for Computational Linguistics. find
  13. Yi Cheng and Sujian Li. 2019. Zero-shot Chinese discourse dependency parsing via cross-lingual mapping. In Proceedings of the 1st Workshop on Discourse Structure in Neural NLG, pages 24–29, Tokyo, Japan. Association for Computational Linguistics. ↗
  14. Alexander Chernyavskiy, Dmitry Ilvovsky, and Preslav Nakov. 2024. Unleashing the power of discourse-enhanced transformers for propaganda detection. In Proc. EACL 2024, pages 1452–1462, St. Julian’s, Malta. find
  15. Shangbin Feng, Zhaoxuan Tan, Wenqian Zhang, Zhenyu Lei, and Yulia Tsvetkov. 2023. KALM: Knowledge-aware integration of local, document, and global contexts for long document understanding. In Proc. ACL 2023, pages 2116–2138, Toronto. find
  16. Christian Chiarcos. 2012. Towards the unsupervised acquisition of discourse relations. In Proceedings of ACL. find
  17. Patrick Fernandes, Kayo Yin, Emmy Liu, André Martins, and Graham Neubig. 2023. When does translation require context? a data-driven, multilingual exploration. In Proc. ACL 2023, pages 606–626, Toronto. find
  18. Christian Chiarcos. 2014. Towards interoperable discourse annotation. discourse features in the ontologies of linguistic annotation. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC‘14), pages 4569– 4577, Reykjavik, Iceland. European Language Resources Association (ELRA). find
  19. Igor Frohmann, Markus Sterner, Ivan Vulić, Benjamin Minixhofer, and Markus Schedl. 2024. Segment any text: A universal approach for robust, efficient and adaptable sentence segmentation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 11908–11941, Miami, Florida, USA. Association for Computational Linguistics. find
  20. Nelson Filipe Costa, Nadia Sheikh, and Leila Kosseim. 2023. Mapping explicit and implicit discourse relations between the RST-DT and the PDTB 3.0. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 344–352, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
  21. Michel Généreux, Iris Hendrickx, and Amália Mendes. 2012. Introducing the reference corpus of contemporary Portuguese online. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 2237–2244, Istanbul, Turkey. European Language Resources Association (ELRA). ↗
  22. Liam Cripwell, Joël Legrand, and Claire Gardent. 2023. Context-aware document simplification. In Findings of ACL 2023, pages 13190–13206, Toronto. find
  23. Iria da Cunha, Juan-Manuel Torres-Moreno, and Gerardo Sierra. 2011. On the development of the RST Spanish treebank. In Proceedings of the 5th Linguistic Annotation Workshop, pages 1–10, Portland, Oregon, USA. Association for Computational Linguistics. find
  24. Luke Gessler, Shabnam Behzad, Yang Janet Liu, Siyao Peng, Yilun Zhu, and Amir Zeldes. 2021. Dis-CoDisCo at the DISRPT2021 shared task: A system for discourse segmentation, classification, and connective detection. In Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021), pages 51–62, Punta Cana, Dominican Republic. Association for Computational Linguistics. ↗
  25. 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, Volume 1 (Long Papers), pages 141–151, New Orleans, Louisiana. Association for Computational Linguistics. ↗
  26. Luke Gessler, Yang Liu, and Amir Zeldes. 2019. A discourse signal annotation system for RST trees. In Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019, pages 56–61, Minneapolis, MN. Association for Computational Linguistics.
  27. Vera Demberg, Merel Scholman, and Fatemeh Torabi Asr. 2019. How compatible are our discourse annotation frameworks? Insights from mapping RST-DT and PDTB annotations. Dialogue & Discourse, 10:87–135. ↗
  28. Sindhuja Gopalan and Sobha Lalitha Devi. 2016. BioDCA identifier: A system for automatic identification of discourse connective and arguments from biomedical text. In Proceedings of the Fifth Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM2016), pages 89– 98, Osaka, Japan. find
  29. The COLING 2016 Organizing Committee. find
  30. Morteza Kamaladdini Ezzabady, Philippe Muller, and Chloé Braud. 2021. Multi-lingual discourse segmentation and connective identification: MELODI at disrpt2021. In Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DIS-RPT 2021), pages 22–32, Punta Cana, Dominican Republic. Association for Computational Linguistics. ↗
  31. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. Lora: Low-rank adaptation of large language models. In ICLR. OpenReview.net.
  32. Zae Myung Kim, Kwang Hee Lee, Preston Zhu, Vipul Raheja, and Dongyeop Kang. 2024. Threads of subtlety: Detecting machine-generated texts through discourse motifs. arXiv preprint arXiv:2402.10586. ↗
  33. Kung-Hsiang Huang, Philippe Laban, Alexander Richard Fabbri, Prafulla Kumar Choubey, Shafiq Joty, Caiming Xiong, and Chien-Sheng Wu. 2024. Embrace divergence for richer insights: A multi-document summarization benchmark and a case study on summarizing diverse information from news articles. In Proc. NAACL 2024, pages 570–593. ↗
  34. Chuyuan Li, Austin Xu, Shafiq Joty, and Giuseppe Carenini. 2025. Topic-guided reinforcement learning with llms for enhancing multi-document summarization. arXiv preprint arXiv:2509.09852. ↗
  35. Junyi Jessy Li, Marine Carpuat, and Ani Nenkova. 2014. Cross-lingual discourse relation analysis: A corpus study and a semi-supervised classification system. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pages 577–587, Dublin, Ireland. Dublin City University and Association for Computational Linguistics.
  36. Shyh-Shiun Hung, Hen-Hsen Huang, and Hsin-Hsi Chen. 2020. A complete shift-reduce Chinese discourse parser with robust dynamic oracle. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 133–138, Online. Association for Computational Linguistics. find
  37. Julie Hunter, Hiroyoshi Yamasaki, Océane Granier, Jérôme Louradour, Roxane Bertrand, Kate Thompson, and Laurent Prévot. 2024. MEETING: A corpus of French meeting-style conversations. In Actes de la 31ème Conférence sur le Traitement Automatique des Langues Naturelles, volume 1 : articles longs et prises de position, pages 508–529, Toulouse, France. ATALA and AFPC. find
  38. Xianming Li, Zongxi Li, Xiaotian Luo, Haoran Xie, Xing Lee, Yingbin Zhao, Fu Lee Wang, and Qing Li. 2023. Recurrent attention networks for long-text modeling. In Findings of ACL 2023, pages 3006– 3019, Toronto. find
  39. Xiaobo Liang, Zecheng Tang, Juntao Li, and Min Zhang. 2023. Open-ended long text generation via masked language modeling. In Proc. ACL 2023, pages 223– 241, Toronto. find
  40. Mikel Iruskieta, María Jesús Aranzabe, Arantza Diaz de Ilarraza, Itziar Gonzalez-Dios, Mikel Lersundi, and Oier Lopez de Lacalle. 2013. The RST Basque TreeBank: An online search interface to check rhetorical relations. In 4th Workshop on RST and Discourse Studies, pages 40–49, Fortaleza, Brasil. find
  41. Wei Liu, Yi Fan, and Michael Strube. 2023. HITS at DISRPT 2023: Discourse segmentation, connective detection, and relation classification. In Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023), pages 43–49, Toronto, Canada. The Association for Computational Linguistics. ↗
  42. Maor Ivgi, Uri Shaham, and Jonathan Berant. 2023. Efficient long-text understanding with short-text models. Transactions of the Association for Computational Linguistics, 11:284–299. ↗
  43. Wei Liu and Michael Strube. 2023. Annotation-inspired implicit discourse relation classification with auxiliary discourse connective generation. In Proc. ACL 2023, pages 15696–15712, Toronto. ↗
  44. 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. ↗
  45. Yang Janet Liu and Amir Zeldes. 2023. Why can’t discourse parsing generalize? a thorough investigation of the impact of data diversity. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3112– 3130, Dubrovnik, Croatia. Association for Computational Linguistics. ↗
  46. Yuchen Eleanor Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang, Mrinmaya Sachan, and Ryan Cotterell. 2023. Discourse-centric evaluation of document-level machine translation with a new densely annotated parallel corpus of novels. In Proc. ACL 2023, pages 7853–7872, Toronto. find
  47. Zhengyuan Liu and Nancy Chen. 2021. Improving multi-party dialogue discourse parsing via domain integration. In Proceedings of the 2nd Workshop on Computational Approaches to Discourse, pages 122– 127, Punta Cana, Dominican Republic and Online. Association for Computational Linguistics. ↗
  48. Swanie Juhng, Matthew Matero, Vasudha Varadarajan, Johannes Eichstaedt, Adithya V Ganesan, and H. Andrew Schwartz. 2023. Discourse-level representations can improve prediction of degree of anxiety. In Proc. ACL 2023, pages 1500–1511, Toronto. find
  49. Aru Maekawa, Tsutomu Hirao, Hidetaka Kamigaito, and Manabu Okumura. 2024. Can we obtain significant success in RST discourse parsing by using large language models? In Proc EACL 2024, pages 2803–2815, St. Julian’s, Malta. limitation. Transactions of the Association for Computational Linguistics, 10:127–144. ↗
  50. Maciej Ogrodniczuk, Aleksandra Tomaszewska, Daniel Ziembicki, Sebastian Żurowski, Ryszard Tuora, and Aleksandra Zwierzchowska. 2024. Polish Discourse Corpus (PDC): Corpus design, ISO-compliant annotation, data highlights, and parser development. In (Calzolari et al., 2024), pages 12829–12835. find
  51. Daniel Marcu. 2000. The Theory and Practice of Discourse Parsing and Summarization. MIT Press, Cambridge, MA. ↗
  52. Proyag Pal, Alexandra Birch, and Kenneth Heafield. 2024. Document-level machine translation with large-scale public parallel corpora. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13185–13197, Bangkok, Thailand. Association for Computational Linguistics. find
  53. Sameen Maruf, Fahimeh Saleh, and Gholamreza Haffari. 2021. A survey on document-level neural machine translation: Methods and evaluation. ACM Comput. Surv., 54(2). ↗
  54. Xin Men, Mingyu Xu, Qingyu Zhang, Bingning Wang, Hongyu Lin, Yaojie Lu, Xianpei Han, and Weipeng Chen. 2024. Shortgpt: Layers in large language models are more redundant than you expect. Preprint, arXiv:2403.03853. ↗
  55. Siyao Peng, Yang Janet Liu, and Amir Zeldes. 2022a. Chinese Discourse Annotation Reference Manual. Research Report, Georgetown University (Washington, D.C.). ↗
  56. Amália Mendes and Pierre Lejeune. 2022. Crpc-db a discourse bank for portuguese. In Computational Processing of the Portuguese Language: 15th International Conference, PROPOR 2022, Fortaleza, Brazil, March 21–23, 2022, Proceedings, page 79–89, Berlin, Heidelberg. Springer-Verlag. ↗
  57. Siyao Peng, Yang Janet Liu, and Amir Zeldes. 2022b. GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse Parsing. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing, pages 382–391, Online only. Association for Computational Linguistics. ↗
  58. Eleni Metheniti, Chloé Braud, Philippe Muller, and Laura Rivière. 2023. DisCut and DiscReT: MELODI at DISRPT 2023. In Proceedings of the 3rd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2023), pages 29–42, Toronto, Canada. The Association for Computational Linguistics. find
  59. Lucie Poláková, Šárka Zikánová, Jiří Mírovský, and Eva Hajičová. 2023. Czech RST discourse treebank 1.0. LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL). find
  60. Eleni Metheniti, Philippe Muller, Chloé Braud, and Margarita Hernández Casas. 2024. Zero-shot learning for multilingual discourse relation classification. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 17858– 17876, Torino, Italia. ELRA and ICCL. find
  61. Andrew Potter. 2008. Interactional coherence in asynchronous learning networks: A rhetorical approach. Internet and Higher Education, 11(2):87–97. ↗
  62. Archiki Prasad, Trung Bui, Seunghyun Yoon, Hanieh Deilamsalehy, Franck Dernoncourt, and Mohit Bansal. 2023. MeetingQA: Extractive question-answering on meeting transcripts. In Proc. ACL 2023, pages 15000–15025, Toronto. find
  63. Philippe Muller, Chloé Braud, and Mathieu Morey. 2019a. ToNy: Contextual embeddings for accurate multilingual discourse segmentation of full documents. In Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019, pages 115– 124, Minneapolis, MN. Association for Computational Linguistics. find
  64. Rashmi Prasad, Bonnie Webber, and Aravind Joshi. 2014. Reflections on the Penn Discourse TreeBank, comparable corpora, and complementary annotation. Computational Linguistics, 40(4):921–950. ↗
  65. Philippe Muller, Chloé Braud, and Mathieu Morey. 2019b. Tony: Contextual embeddings for accurate multilingual discourse segmentation of full documents. In Proceedings of the Workshop on Discourse Relation Parsing and Treebanking (NAACL). find
  66. Rashmi Prasad, Bonnie Webber, Alan Lee, and Aravind Joshi. 2019. Penn Discourse Treebank Version 3.0. LDC2019T05. ↗
  67. Ponrawee Prasertsom, Apiwat Jaroonpol, and Attapol T. Rutherford. 2024. The thai discourse treebank: Annotating and classifying thai discourse connectives. Transactions of the Association for Computational Linguistics, 12:613–629. ↗
  68. Benjamin Newman, Luca Soldaini, Raymond Fok, Arman Cohan, and Kyle Lo. 2023. A question answering framework for decontextualizing user-facing snippets from scientific documents. In Proc. EMNLP 2023, pages 3194–3212. find
  69. Laurent Prévot, Roxane Bertrand, and Julie Hunter. 2025. Segmenting a large french meeting corpus into elementary discourse units. In Proceedings of SIGDIAL. find
  70. Noriki Nishida and Yuji Matsumoto. 2022. Out-of-domain discourse dependency parsing via bootstrapping: An empirical analysis on its effectiveness and Dongqi Pu, Yifan Wang, and Vera Demberg. 2023. Incorporating distributions of discourse structure for long document abstractive summarization. In Proc. ACL 2023, pages 5574–5590, Toronto. find
  71. Kate Thompson, Julie Hunter, and Nicholas Asher. 2024b. Discourse structure for the Minecraft corpus. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4957–4967, Torino, Italia. ELRA and ICCL.
  72. Gisela Redeker, Ildikó Berzlánovich, Nynke van der Vliet, Gosse Bouma, and Markus Egg. 2012. Multi-layer discourse annotation of a Dutch text corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 2820–2825, Istanbul, Turkey. European Language Resources Association (ELRA). ↗
  73. Svetlana Toldova, Dina Pisarevskaya, Margarita Ananyeva, Maria Kobozeva, Alexander Nasedkin, Sofia Nikiforova, Irina Pavlova, and Alexey Shelepov. 2017. Rhetorical relations markers in Russian RST treebank. In Proceedings of the 6th Workshop on Recent Advances in RST and Related Formalisms, pages 29–33, Santiago de Compostela, Spain. Association for Computational Linguistics. ↗
  74. Ines Rehbein, Merel Scholman, and Vera Demberg. 2016. Annotating discourse relations in spoken language: A comparison of the pdtb and ccr frameworks. In Proceedings of LREC.
  75. Aleksandra Tomaszewska, Purificação Silvano, António Leal, and Evelin Amorim. 2024. ISO 24617-8 applied: Insights from multilingual discourse relations annotation in English, Polish, and Portuguese. In Proceedings of the 20th Joint ACL - ISO Workshop on Interoperable Semantic Annotation @ LREC-COLING 2024, pages 99–110, Torino, Italia. ELRA and ICCL. find
  76. Giuseppe Riccardi, Evgeny A. Stepanov, and Shammur Absar Chowdhury. 2016. Discourse connective detection in spoken conversations. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 6095–6099. ↗
  77. Ted J.M. Sanders, Vera Demberg, Jet Hoek, Merel C.J. Scholman, Fatemeh Torabi Asr, Sandrine Zufferey, and Jacqueline Evers-Vermeul. 2018. Unifying dimensions in coherence relations: How various annotation frameworks are related. Corpus Linguistics and Linguistic Theory. ↗
  78. Sara Tonelli, Giuseppe Riccardi, Rashmi Prasad, and Aravind Joshi. 2010. Annotation of discourse relations for conversational spoken dialogs. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10), Valletta, Malta. European Language Resources Association (ELRA). ↗
  79. Ted J.M. Sanders, Vera Demberg, Jet Hoek, Merel C.J. Scholman, Fatemeh Torabi Asr, Sandrine Zufferey, and Jacqueline Evers-Vermeul. 2021. Unifying dimensions in coherence relations: How various annotation frameworks are related. Corpus Linguistics and Linguistic Theory, 17(1):1–71. find
  80. Hanna Varachkina and Franziska Pannach. 2021. A unified approach to discourse relation classification in nine languages. In Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021), pages 46–50, Punta Cana, Dominican Republic. Association for Computational Linguistics.
  81. Merel CJ Scholman, Marian Marchal, AriaRay Brown, and Vera Demberg. 2025. Disconaija: a discourse-annotated parallel nigerian pidgin-english corpus. Language Resources and Evaluation, pages 1–37. ↗
  82. Sara Shahmohammadi, Hadi Veisi, and Ali Darzi. 2021. Persian Rhetorical Structure Theory. arXiv preprint arXiv:2106.13833. ↗
  83. Bonnie Webber, Rashmi Prasad, Alan Lee, and Aravind Joshi. 2019. The Penn Discourse TreeBank 3.0 annotation manual. Technical report, University of Edinburgh, Interactions, LLC, University of Pennsylvania. find
  84. Zayne Rea Sprague, Xi Ye, Kaj Bostrom, Swarat Chaudhuri, and Greg Durrett. 2023. Musr: Testing the limits of chain-of-thought with multistep soft reasoning. In The Twelfth International Conference on Learning Representations. find
  85. Yuhao Wu, Ming Shan Hee, Zhiqing Hu, and Roy Ka-Wei Lee. 2024a. Spinning the golden thread: Benchmarking long-form generation in language models. arXiv preprint arXiv:2409.02076. ↗
  86. Yunshu Wu, Hayate Iso, Pouya Pezeshkpour, Nikita Bhutani, and Estevam Hruschka. 2024b. Less is more for long document summary evaluation by LLMs. In Proc. EACL 2024, pages 330–343, St. Julian’s, Malta. ↗
  87. Manfred Stede and Arne Neumann. 2014. Potsdam commentary corpus 2.0: Annotation for discourse research. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14), pages 925–929, Reykjavik, Iceland. European Language Resources Association (ELRA). ↗
  88. Wei Xiang and Bang Wang. 2023. A survey of implicit discourse relation recognition. ACM Comput. Surv., 55(12). ↗
  89. Kate Thompson, Akshay Chaturvedi, Julie Hunter, and Nicholas Asher. 2024a. Llamipa: An incremental discourse parser. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 6418–6430, Miami, Florida, USA. Association for Computational Linguistics. find
  90. Fangyuan Xu, Yixiao Song, Mohit Iyyer, and Eunsol Choi. 2023. A critical evaluation of evaluations for long-form question answering. In Proc. ACL 2023, pages 3225–3245, Toronto.
  91. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. Qwen3 technical report. Preprint, arXiv:2505.09388. ↗
  92. Deniz Zeyrek, Amália Mendes, Yulia Grishina, Murathan Kurfalı, Samuel Gibbon, and Maciej Ogrodniczuk. 2019. TED Multilingual Discourse Bank (TED-MDB): A parallel corpus annotated in the PDTB style. Language Resources and Evaluation, pages 1–27. ↗
  93. Deniz Zeyrek, Amália Mendes, and Murathan Kurfalı. 2018. Multilingual extension of PDTB-style annotation: The case of TED multilingual discourse bank. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA). ↗
  94. An Yang and Sujian Li. 2018. SciDTB: Discourse dependency TreeBank for scientific abstracts. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 444–449, Melbourne, Australia. Association for Computational Linguistics. ↗
  95. Dingyi Yang and Qin Jin. 2023. Attractive storyteller: Stylized visual storytelling with unpaired text. In Proc. ACL 2023, pages 11053–11066, Toronto. ↗
  96. Duzhen Zhang, Feilong Chen, and Xiuyi Chen. 2023a. DualGATs: Dual graph attention networks for emotion recognition in conversations. In Proc. ACL 2023, pages 7395–7408, Toronto. find
  97. Yue Yu, Yilun Zhu, Yang Liu, Yan Liu, Siyao Peng, Mackenzie Gong, and Amir Zeldes. 2019. GumDrop at the DISRPT2019 shared task: A model stacking approach to discourse unit segmentation and connective detection. In Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019, pages 133–143, Minneapolis, MN. Association for Computational Linguistics.
  98. Longyin Zhang, Bowei Zou, and Ai Ti Aw. 2024. Empowering tree-structured entailment reasoning: Rhetorical perception and LLM-driven interpretability. In Proc. LREC-COLING 2024, pages 5783– 5793, Torino. find
  99. Shiyue Zhang, David Wan, and Mohit Bansal. 2023b. Extractive is not faithful: An investigation of broad unfaithfulness problems in extractive summarization. In Proc. ACL 2023, pages 2153–2174, Toronto. find
  100. Karolina Zaczynska and Manfred Stede. 2024. Rhetorical strategies in the UN security council: Rhetorical Structure Theory and conflicts. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 15–28, Kyoto, Japan. Association for Computational Linguistics. find
  101. Haodong Zhao, Ruifang He, Mengnan Xiao, and Jing Xu. 2023. Infusing hierarchical guidance into prompt tuning: A parameter-efficient framework for multi-level implicit discourse relation recognition. In Proc. ACL 2023, pages 6477–6492, Toronto.
  102. Amir Zeldes. 2017. The GUM Corpus: Creating Multilayer Resources in the Classroom. Language Resources and Evaluation, 51(3):581–612. ↗
  103. Yuping Zhou, Jill Lu, Jennifer Zhang, and Nianwen Xue. 2014. Chinese Discourse Treebank 0.5 LDC2014T21. find
  104. Amir Zeldes, Tatsuya Aoyama, Yang Janet Liu, Siyao Peng, Debopam Das, and Luke Gessler. 2025. eRST: A signaled graph theory of discourse relations and organization. Computational Linguistics, 51(1):23– 72. ↗
  105. Xuekai Zhu, Jian Guan, Minlie Huang, and Juan Liu. 2023. StoryTrans: Non-parallel story author-style transfer with discourse representations and content enhancing. In Proc. ACL 2023, pages 14803–14819, Toronto. find
  106. Amir Zeldes, Debopam Das, Erick Galani Maziero, Juliano Antonio, and Mikel Iruskieta. 2019. find
  107. The DIS-RPT 2019 shared task on elementary discourse unit segmentation and connective detection. In Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019, pages 97–104, Minneapolis, MN. Association for Computational Linguistics. find
  108. Amir Zeldes, Yang Janet Liu, Mikel Iruskieta, Philippe Muller, Chloé Braud, and Sonia Badene. 2021. find
  109. The DISRPT 2021 shared task on elementary discourse unit segmentation, connective detection, and relation classification. In Proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021), pages 1–12, Punta Cana, Dominican Republic. Association for Computational Linguistics.
  110. Deniz Zeyrek and Murathan Kurfalı. 2017. TDB 1.1: Extensions on Turkish discourse bank. In Proceedings of the 11th Linguistic Annotation Workshop, pages 76–81, Valencia, Spain. Association for Computational Linguistics. ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/braud-2025-disrpt-2025-shared-task-elementary/