---
title: "A Topicality-Driven QUD Model for Discourse Processing (2025)"
description: "The authors offer an alternative QUD annotation scheme based on van Kuppevelt's (1995) topicality theory. 51 references."
authors: ["Yingxue Fu", "Mark-Jan Nederhof", "Anais Ollagnier"]
year: 2025
venue: "Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue"
source: "https://aclanthology.org/2025.sigdial-1.17/"
doi: "10.18653/v1/2025.sigdial-1.17"
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/en/papers/fu-2025-topicality-driven-qud-model-discourse/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/fu-2025-topicality-driven-qud-model-discourse/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/16/) / A Topicality-Driven QUD Model for Discourse Processing

# A Topicality-Driven QUD Model for Discourse Processing

**Authors:** [Yingxue Fu](https://md.research.elamur.ai/free/en/authors/yingxue-fu/), [Mark-Jan Nederhof](https://md.research.elamur.ai/free/en/authors/mark-jan-nederhof/) and [Anais Ollagnier](https://md.research.elamur.ai/free/en/authors/anais-ollagnier/) · **Year:** 2025 · **Venue:** [Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue](https://md.research.elamur.ai/free/en/venues/sigdial/) ([SIGDIAL 2025](https://md.research.elamur.ai/free/en/venues/sigdial/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.sigdial-1.17/) · [PDF](https://aclanthology.org/2025.sigdial-1.17.pdf) · [DOI 10.18653/v1/2025.sigdial-1.17](https://doi.org/10.18653/v1/2025.sigdial-1.17) · [OpenAlex](https://openalex.org/W4415348387)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
QUD-tree annotation, which models discourse as one tree of questions, has so far reached only moderate inter-annotator agreement. The authors offer an alternative QUD annotation scheme based on van Kuppevelt's (1995) topicality theory. In this theory, discourse topics are implicit questions, and each sentence serves as a comment that answers one of them. The scheme has three kinds of units. Feeders open a new topic, topic-constituting questions carry it, and subquestions arise when an answer is unsatisfactory. Two principles govern the structure: recency, and dynamic topic termination.

Using sentences as basic units, they annotated Wall Street Journal articles and reached high agreement on short and long files. They also:
- release an annotation interface, guidelines and samples;
- test GPT-4 as an automatic annotator and find it weak at hierarchy;
- compare the resulting trees with RST trees;
- outline how to add intra-sentential relations through QA templates.

The work matters because it shows that hierarchical question-based discourse annotation can be made reliable. It is explicitly a proof of concept and not a finished corpus.

## Key points
- Inter-annotator agreement was 81.45% on short WSJ files and 79.53% on long ones. The scheme, code, guidelines and sample annotations are on GitHub (topicality_driven_QUD_sigdial2025).
- GPT-4 was run deterministically (temperature 0, max tokens 3000). It had to output each sentence's parent plus the generated questions, and it still struggled to recover the hierarchy.
- RST trees for the same documents were generally taller than QUD trees. For example, wsj_0601 has RST height 12 against QUD height 8.
- In the long files, roughly half of the non-leaf spans carry both an RST relation and a QUD. The overlap is lower in the short files, where the ratios range from 0.375 to 0.5625.
- Question types do not map neatly onto RST relations. Why-questions, for instance, appeared over Background, Explanation and Elaboration spans.
- Intra-sentential relations are handled in two steps:
  - PDTB 3.0 criteria identify the argument pairs.
  - The question templates of Pyatkin et al. (2020) turn those pairs into QA pairs, with more than one question allowed per pair.

## Interesting ideas
- Treat each sentence as an answer to an implicit question, and let an unsatisfactory answer spawn a subquestion; this builds hierarchy from a simple, checkable local decision.
- Use "feeder" units that start a new topic, either with no prior context or branching from part of the previous topic; this gives explicit topic boundaries.
- Dynamic topic termination: once a question is satisfactorily answered, its topic stops being current, much like popping a stack.
- Pair a hierarchical model between sentences with template-based QA pairs inside sentences; together they turn all discourse relations into question–answer form.
- Compare the trees of two discourse formalisms on the same documents, using tree height and the share of spans annotated in both; this is a cheap cross-check of structure.

## For Mova

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

- **I1** (world): Each new sentence could be attached in the text world as answering an open question about some entity or event, giving an explainable discourse tree over the event order.
- **I2** (answer): Fable and tale QA could limit its search for an answer to the topic block opened by the relevant feeder, cutting distractors.
- **I3** (frames): Coreference could favour referents from still-open topics and down-weight those whose question has been closed.
- **I4** (frames): Intra-sentential connectives could be expressed as templated questions over the frames, keeping relation labels readable and explainable.
- **I5** (learn): The same span-overlap and height metrics could check silver discourse structures from different witnesses against each other before accepting them.

*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

- [Institut national de recherche en sciences et technologies du numérique](https://md.research.elamur.ai/free/en/labs/institut-national-de-recherche-en-sciences-et-technologies-du-numerique/) — Research institute, Le Chesnay-Rocquencourt, France · 84 works · 25,414 citations
- [Centre National de la Recherche Scientifique](https://md.research.elamur.ai/free/en/labs/centre-national-de-la-recherche-scientifique/) — Research institute, Paris, France · 168 works · 62,369 citations
- [University of St Andrews](https://md.research.elamur.ai/free/en/universities/university-of-st-andrews/) — University, St Andrews, United Kingdom · 5 works · 41 citations
- [Laboratoire d'Informatique, Signaux et Systèmes de Sophia Antipolis](https://md.research.elamur.ai/free/en/labs/laboratoire-d-informatique-signaux-et-systemes-de-sophia-antipolis/) — Research institute, Valbonne, France · 3 works · 1 citation
- [Université Côte d'Azur](https://md.research.elamur.ai/free/en/universities/universite-cote-d-azur/) — University, Nice, France · 3 works · 1 citation

Also on the byline: [MARIANNE: Modèles et données pour l'argumentation computationnelle en langage naturel](https://ror.org/00ynfac79).

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🤔 Philosophy](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/philosophy/) · 284 works

🧭 Topics (1): [🧵 Discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) · 466 works

## Cite

Cite as: Yingxue Fu, Mark-Jan Nederhof and Anais Ollagnier. 2025. A Topicality-Driven QUD Model for Discourse Processing. Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue.

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

```bibtex
@inproceedings{fu2025topicality,
  title = {{A Topicality-Driven QUD Model for Discourse Processing}},
  author = {Yingxue Fu, Mark-Jan Nederhof and Anais Ollagnier},
  booktitle = {Proceedings of the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue},
  year = {2025},
  doi = {10.18653/v1/2025.sigdial-1.17},
  url = {https://doi.org/10.18653/v1/2025.sigdial-1.17}
}
```

- [← previous A Thought Too Far: A Case for a Corpus Approach to Bad Knowledge in Old English Literature](https://md.research.elamur.ai/free/en/papers/boyle-2025-thought-too-far-case-corpus/)
- [next → A “White Spot” in History of Linguistic Thought: the Jewish Grammatical Tradition](https://md.research.elamur.ai/free/en/papers/khukhuni-2025-white-spot-history-linguistic-thought/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/16/)

## References

51 references, 25 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Nicholas Asher and Alex Lascarides. 2003. Logics of conversation. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Nicholas+Asher+and+Alex+Lascarides%2E+2003%2E+Logics+of+conversation%2E+Cambridge+University+Press%2E)
2. Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural language processing with Python: analyzing text with the natural language toolkit. " O’Reilly Media, Inc.". [find](https://scholar.google.com/scholar?q=Steven+Bird%2C+Ewan+Klein%2C+and+Edward+Loper%2E+2009%2E+Natural+language+processing+with+Python%3A+analyzing+text+with+the+natural+language+toolkit%2E+%22+O%E2%80%99Reilly+Media%2C+Inc%2E%22%2E)
3. Chloé Braud, Barbara Plank, and Anders Søgaard. 2016. [Multi-view and multi-task training of RST discourse parsers](https://md.research.elamur.ai/free/en/papers/braud-2016-multi-view-multi-task-training/). In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1903–1913, Osaka, Japan.
4. The COLING 2016 Organizing Committee. [find](https://scholar.google.com/scholar?q=The+COLING+2016+Organizing+Committee%2E)
5. Chloé Braud, Amir Zeldes, Laura Rivière, Yang Janet Liu, Philippe Muller, Damien Sileo, and Tatsuya Aoyama. 2024. DISRPT: A multilingual, multi-domain, cross-framework benchmark for discourse processing. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 4990–5005, Torino, Italia. ELRA and ICCL. [↗](https://doi.org/10.63317/2kmundhdbfae)
6. Lynn Carlson, Daniel Marcu, and Mary Ellen Okurovsky. 2001. [Building a discourse-tagged corpus in the framework of Rhetorical Structure Theory](https://md.research.elamur.ai/free/en/papers/carlson-2001-building-discourse-tagged-corpus-framework/). In Proceedings of the Second SIGdial Workshop on Discourse and Dialogue. [↗](https://doi.org/10.3115/1118078.1118083)
7. Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement, 20(1):37–46. [↗](https://doi.org/10.1177/001316446002000104)
8. Kordula De Kuthy, Nils Reiter, and Arndt Riester. 2018. [QUD-based annotation of discourse structure and information structure: Tool and evaluation](https://md.research.elamur.ai/free/en/papers/kuthy-2018-qud-based-annotation-discourse-structure/). In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA). [↗](https://doi.org/10.63317/368a5yfgwg9q)
9. Bosheng Ding, Chengwei Qin, Linlin Liu, Yew Ken Chia, Boyang Li, Shafiq Joty, and Lidong Bing. 2023. [Is GPT-3 a good data annotator?](https://md.research.elamur.ai/free/en/papers/ding-2022-gpt-3-good-data-annotator/) In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11173–11195, Toronto, Canada. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2212.10450)
10. Jacob Eisenstein and Regina Barzilay. 2008. [Bayesian unsupervised topic segmentation](https://md.research.elamur.ai/free/en/papers/eisenstein-2008-bayesian-unsupervised-topic-segmentation/). In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 334–343, Honolulu, Hawaii. Association for Computational Linguistics.
11. Yingxue Fu. 2022. Towards unification of discourse annotation frameworks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 132– 142, Dublin, Ireland. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2022.acl-srw.12)
12. Yingxue Fu. 2024. Automatic alignment of discourse relations of different discourse annotation frameworks. In Proceedings of the 20th Joint ACL - ISO Workshop on Interoperable Semantic Annotation @ LREC-COLING 2024, pages 27–38, Torino, Italia. ELRA and ICCL. [find](https://scholar.google.com/scholar?q=Yingxue+Fu%2E+2024%2E+Automatic+alignment+of+discourse+relations+of+different+discourse+annotation+frameworks%2E+In+Proceedings+of+the+20th+Joint+ACL+%2D+ISO+Workshop+on+Interoperable+Semantic+Annotation+%40+LR)
13. Yingxue Fu. 2025. [A survey of QUD models for discourse processing](https://md.research.elamur.ai/free/en/papers/fu-2025-survey-qud-models-discourse-processing/). In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1722–1732, Albuquerque, New Mexico. Association for Computational Linguistics. [↗](https://doi.org/10.13140/rg.2.2.10554.30404)
14. Barbara J. Grosz and Candace L. Sidner. 1986. [Attention, intentions, and the structure of discourse](https://md.research.elamur.ai/free/en/papers/grosz-1986-attention-intentions-structure-discourse/). Computational Linguistics, 12(3):175–204. [↗](https://doi.org/10.5555/12457.12458)
15. Patrick Huber, Linzi Xing, and Giuseppe Carenini. 2022. Predicting above-sentence discourse structure using distant supervision from topic segmentation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 10794–10802. [↗](https://doi.org/10.1609/aaai.v36i10.21325)
16. Feng Jiang, Yaxin Fan, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, and Fang Kong. 2021. Hierarchical macro discourse parsing based on topic segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14):13152–13160. [find](https://scholar.google.com/scholar?q=Feng+Jiang%2C+Yaxin+Fan%2C+Xiaomin+Chu%2C+Peifeng+Li%2C+Qiaoming+Zhu%2C+and+Fang+Kong%2E+2021%2E+Hierarchical+macro+discourse+parsing+based+on+topic+segmentation%2E+Proceedings+of+the+AAAI+Conference+on+Artificial+In)
17. Feng Jiang, Weihao Liu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, and Haizhou Li. 2024. Advancing topic segmentation and outline generation in Chinese texts: The paragraph-level topic representation, corpus, and benchmark. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 495–506, Torino, Italia. ELRA and ICCL. [find](https://scholar.google.com/scholar?q=Feng+Jiang%2C+Weihao+Liu%2C+Xiaomin+Chu%2C+Peifeng+Li%2C+Qiaoming+Zhu%2C+and+Haizhou+Li%2E+2024%2E+Advancing+topic+segmentation+and+outline+generation+in+Chinese+texts%3A+The+paragraph%2Dlevel+topic+representation%2C+cor)
18. Mitchell P. Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. [Building a large annotated corpus of English: The Penn Treebank](https://md.research.elamur.ai/free/en/papers/marcus-1993-building-large-annotated-corpus-english/). Computational Linguistics, 19(2):313–330. [↗](https://doi.org/10.21236/ada273556)
19. Shafiq Joty, Giuseppe Carenini, Raymond Ng, and Yashar Mehdad. 2013. [Combining intra- and multi-sentential rhetorical parsing for document-level discourse analysis](https://md.research.elamur.ai/free/en/papers/joty-2013-combining-intra-multi-sentential-rhetorical/). In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 486–496, Sofia, Bulgaria. Association for Computational Linguistics.
20. Johanna D. Moore and Martha E. Pollack. 1992. [A problem for RST: The need for multi-level discourse analysis](https://md.research.elamur.ai/free/en/papers/moore-1992-problem-rst-need-multi-level/). Computational Linguistics, 18(4):537–544.
21. Andrew Kehler and Hannah Rohde. 2017. Evaluating an expectation-driven question-under-discussion model of discourse interpretation. Discourse Processes, 54(3):219–238. [↗](https://doi.org/10.1080/0163853x.2016.1169069)
22. Alistair Knott, Jon Oberlander, Michael O’Donnell, and Chris Mellish. 2000. Beyond elaboration: The interaction of relations and focus in coherent text. In Text Representation: Linguistic and Psycholinguistic Aspects, chapter 7, pages 181–196. John Benjamins. [find](https://scholar.google.com/scholar?q=Alistair+Knott%2C+Jon+Oberlander%2C+Michael+O%E2%80%99Donnell%2C+and+Chris+Mellish%2E+2000%2E+Beyond+elaboration%3A+The+interaction+of+relations+and+focus+in+coherent+text%2E+In+Text+Representation%3A+Linguistic+and+Psycholi)
23. Wei-Jen Ko, Cutter Dalton, Mark Simmons, Eliza Fisher, Greg Durrett, and Junyi Jessy Li. 2022. Discourse comprehension: A question answering framework to represent sentence connections. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11752–11764, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2022.emnlp-main.806)
24. Wei-Jen Ko, Yating Wu, Cutter Dalton, Dananjay Srinivas, Greg Durrett, and Junyi Jessy Li. 2023. [Discourse analysis via questions and answers: Parsing dependency structures of questions under discussion](https://md.research.elamur.ai/free/en/papers/ko-2023-discourse-analysis-questions-answers-parsing/). In Findings of the Association for Computational Linguistics: ACL 2023, pages 11181–11195, Toronto, Canada. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2023.findings-acl.710)
25. Yang Janet Liu, Tatsuya Aoyama, Wesley Scivetti, Yilun Zhu, Shabnam Behzad, Lauren Elizabeth Levine, Jessica Lin, Devika Tiwari, and Amir Zeldes. 2024. [GDTB: Genre diverse data for English shallow discourse parsing across modalities, text types, and domains](https://md.research.elamur.ai/free/en/papers/liu-2024-gdtb-genre-diverse-data-english/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 12287–12303, Miami, Florida, USA. Association for Computational Linguistics. [↗](https://doi.org/10.48550/arxiv.2411.00491)
26. Yang Janet Liu, Tatsuya Aoyama, and Amir Zeldes. 2023. [What’s hard in English RST parsing?](https://md.research.elamur.ai/free/en/papers/liu-2023-what-s-hard-english-rst/) Predictive models for error analysis. In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 31–42, Prague, Czechia. Association for Computational Linguistics.
27. William C Mann and Sandra A Thompson. 1988. [Rhetorical structure theory: Toward a functional theory of text organization](https://md.research.elamur.ai/free/en/papers/mann-1988-rhetorical-structure-theory-functional/). Text, 8(3):243–281. [↗](https://doi.org/10.1515/text.1.1988.8.3.243)
28. Daniel Marcu, Estibaliz Amorrortu, and Magdalena Romera. 1999. Experiments in constructing a corpus of discourse trees. In Towards Standards and Tools for Discourse Tagging. [find](https://scholar.google.com/scholar?q=Daniel+Marcu%2C+Estibaliz+Amorrortu%2C+and+Magdalena+Romera%2E+1999%2E+Experiments+in+constructing+a+corpus+of+discourse+trees%2E+In+Towards+Standards+and+Tools+for+Discourse+Tagging%2E)
29. Edgar Onea. 2016. Potential questions at the semantics-pragmatics interface. In Potential Questions at the Semantics-Pragmatics Interface. Brill. [↗](https://doi.org/10.1163/9789004217935)
30. OpenAI. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). abs/2303.08774. [↗](https://arxiv.org/abs/2303.08774)
31. ArXiv, Siyao Peng. 2023. Cross-Paragraph Discourse Structure in Rhetorical Structure Theory Parsing and Treebanking for Chinese and English. Georgetown University. [find](https://scholar.google.com/scholar?q=ArXiv%2C+Siyao+Peng%2E+2023%2E+Cross%2DParagraph+Discourse+Structure+in+Rhetorical+Structure+Theory+Parsing+and+Treebanking+for+Chinese+and+English%2E+Georgetown+University%2E)
32. Valentina Pyatkin, Ayal Klein, Reut Tsarfaty, and Ido Dagan. 2020. [QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines](https://md.research.elamur.ai/free/en/papers/pyatkin-2020-qadiscourse-discourse-relations-as-qa/). In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2804–2819, Online. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2020.emnlp-main.224)
33. 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](https://md.research.elamur.ai/free/en/papers/raffel-2019-exploring-limits-transfer-learning-unified/). Journal of machine learning research, 21(140):1–67. [↗](https://doi.org/10.48550/arxiv.1910.10683)
34. Nils Reimers and Iryna Gurevych. 2019. [Sentence-BERT: Sentence embeddings using Siamese BERT-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992, Hong Kong, China. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/d19-1410)
35. Arndt Riester. 2019. Constructing QUD trees. In Questions in discourse, pages 164–193. Brill. [↗](https://doi.org/10.1163/9789004378322_007)
36. Arndt Riester, Amalia Canes Nápoles, and Jet Hoek. 2021. [Combined discourse representations: Coherence relations and questions under discussion](https://md.research.elamur.ai/free/en/papers/riester-2021-combined-discourse-representations-coherence-relations/). In Proceedings of the First Workshop on Integrating Perspectives on Discourse Annotation, pages 26–30, Tübingen, Germany. Association for Computational Linguistics.
37. Craige Roberts. 2012. [Information structure: Towards an integrated formal theory of pragmatics](https://md.research.elamur.ai/free/en/papers/roberts-2012-information-structure-discourse-towards-integrated/). Semantics and pragmatics, 5:6–1. [↗](https://doi.org/10.3765/sp.5.6)
38. Sara Shahmohammadi, Hannah Seemann, Manfred Stede, and Tatjana Scheffler. 2023. [Encoding discourse structure: Comparison of RST and QUD](https://md.research.elamur.ai/free/en/papers/shahmohammadi-2023-encoding-discourse-structure-comparison-rst/). In Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023), pages 89– 98, Toronto, Canada. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2023.codi-1.11)
39. Manfred Stede. 2008. Disentangling nuclearity. ‘Subordination’ versus ‘Coordination’ in Sentence and Text: A cross-linguistic perspective, 98:33. questions under discussion discourse parsing. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5344– 5363, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Manfred+Stede%2E+2008%2E+Disentangling+nuclearity%2E+%E2%80%98Subordination%E2%80%99+versus+%E2%80%98Coordination%E2%80%99+in+Sentence+and+Text%3A+A+cross%2Dlinguistic+perspective%2C+98%3A33%2E+questions+under+discussion+discourse+parsing%2E+In+Proce)
40. Manfred Stede. 2012. Discourse processing, volume 15. Morgan & Claypool Publishers. [find](https://scholar.google.com/scholar?q=Manfred+Stede%2E+2012%2E+Discourse+processing%2C+volume+15%2E+Morgan+%26+Claypool+Publishers%2E)
41. Maite Taboada and William C Mann. 2006. Rhetorical structure theory: Looking back and moving ahead. Discourse studies, 8(3):423–459. [↗](https://doi.org/10.1177/1461445606061881)
42. Jan van Kuppevelt. 1993. Intentionality in a topical approach of discourse structure. In Intentionality and Structure in Discourse Relations. [find](https://scholar.google.com/scholar?q=Jan+van+Kuppevelt%2E+1993%2E+Intentionality+in+a+topical+approach+of+discourse+structure%2E+In+Intentionality+and+Structure+in+Discourse+Relations%2E)
43. Jan van Kuppevelt. 1995. Discourse structure, topicality and questioning. Journal of linguistics, 31(1):109– 147. [↗](https://doi.org/10.1017/s002222670000058x)
44. Christiane von Stutterheim and Wolfgang Klein. 1989. Referential movement in descriptive and narrative discourse. In North-Holland Linguistic Series: Linguistic Variations, volume 54, pages 39–76. Elsevier. [↗](https://doi.org/10.1016/b978-0-444-87144-2.50005-7)
45. Bonnie Webber, Rashmi Prasad, Alan Lee, and Aravind Joshi. 2019. The Penn Discourse Treebank 3.0 Annotation Manual. Philadelphia, University of Pennsylvania. [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%2E)
46. Bonnie Webber, Matthew Stone, Aravind Joshi, and Alistair Knott. 2003. [Anaphora and discourse structure](https://md.research.elamur.ai/free/en/papers/webber-2003-anaphora-discourse-structure/). Computational Linguistics, 29(4):545–587. [↗](https://doi.org/10.1162/089120103322753347)
47. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. 2022a. [Emergent abilities of large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-emergent-abilities-large-language-models/). Transactions on Machine Learning Research. Survey Certification. [↗](https://doi.org/10.48550/arxiv.2206.07682)
48. Yating Wu, Ritika Rajesh Mangla, Alex Dimakis, Greg Durrett, and Junyi Jessy Li. 2024. Which questions should I answer? Salience prediction of inquisitive questions. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19969–19987, Miami, Florida, USA. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/2024.emnlp-main.1114)
49. Weizhe Yuan, Graham Neubig, and Pengfei Liu. 2021. [BARTscore: Evaluating generated text as text generation](https://md.research.elamur.ai/free/en/papers/yuan-2021-bartscore-evaluating-generated-text-text/). In Advances in Neural Information Processing Systems, volume 34, pages 27263–27277. Curran Associates, Inc.
50. 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](https://md.research.elamur.ai/free/en/papers/zeldes-2025-erst-signaled-graph-theory-discourse/). Computational Linguistics, 51(1):23– 72. [↗](https://doi.org/10.1162/coli_a_00538)
51. Qinglin Zhang, Chong Deng, Jiaqing Liu, Hai Yu, Qian Chen, Wen Wang, Zhijie Yan, Jinglin Liu, Yi Ren, and Zhou Zhao. 2023. Mug: A general meeting understanding and generation benchmark. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. IEEE. [find](https://scholar.google.com/scholar?q=Qinglin+Zhang%2C+Chong+Deng%2C+Jiaqing+Liu%2C+Hai+Yu%2C+Qian+Chen%2C+Wen+Wang%2C+Zhijie+Yan%2C+Jinglin+Liu%2C+Yi+Ren%2C+and+Zhou+Zhao%2E+2023%2E+Mug%3A+A+general+meeting+understanding+and+generation+benchmark%2E+In+ICASSP+2023)

*Updated 1 November 2026*