A Survey of QUD Models for Discourse Processing

What it is about

The survey sorts computational work on Questions Under Discussion into three approaches. The QUD-tree approach (Roberts 2012; annotation guidelines of Riester and De Kuthy) builds a hierarchy of explicit and implicit questions under constraints: question–answer congruence, givenness (implicit questions use only given material), maximal anaphoricity, and «back to the roots» (attach as low as anaphora requires, as high as possible); non-at-issue material is what can be deleted without changing the main proposition's truth. The expectation-driven approach (Westera et al.'s TED-Q) has annotators write the questions a passage evokes at probe points and later rate how far each is answered. The dependency-based approach (Ko et al.'s DCQA, 22,394 questions over 606 news articles) links each sentence to an anchor sentence by a free question it answers, and is now parsed and evaluated automatically (QUDeval). The survey also reviews comparisons with RST, PDTB and SDRT: QUD trees and RST trees overlap about 74% in one German study, why-questions correlate with PDTB causal relations, and SDRT and QUD do not map one to one.

Ideas

• I1. Add the «back to the roots» rule to world/src/qud.rs: an assertion currently attaches to the deepest open question that shares a lemma and has the right answer type; when it has no pronoun or other anaphoric link into the lower question's material but is congruent with a higher open question, attach it to the higher one and pop the lower ones. Test with a story where a digression ends and the narration returns to the main question.
• I2. Add expectation-driven questions to the reader of tales: a want, plan or problem frame evokes a question («Will the crow keep the cheese?», «Why is the hare sad?») that stays open until a later frame answers it; record which sentence answered it. These evoked questions are exactly the school questions about stories, so the record doubles as a test of the reader: for each evoked question, does the reader find the answering frame?
• I3. Mark non-at-issue material by the paper's deletion test, approximated by syntax (appositions, non-restrictive relative clauses, parentheticals, sentence adverbs like of course): it should not attach to the QUD stack or count as an answer. Check that qud.rs ignores it, with a negative-control test.

For Mova

36. Discourse relations and coherence §9 (questions under discussion) and §11.5 (the QUD stack), 29-ellipsis-word-order-information-structure.md. Code: world/src/qud.rs, prag/src/frames.rs (want/plan frames). Measures: hand-built QUD tests with negative controls; share of evoked questions answered by the reader's frames on a set of tales.

Topics: Discourse analysis

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.naacl-long.84

@inproceedings{fu2025survey,
  title = {{A Survey of QUD Models for Discourse Processing}},
  author = {Fu, Yingxue},
  booktitle = {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)},
  year = {2025},
  doi = {10.18653/v1/2025.naacl-long.84},
  url = {https://doi.org/10.18653/v1/2025.naacl-long.84}
}

References

39 references, 12 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
2. Anton Benz and Katja Jasinskaja. 2017. Questions under discussion: From sentence to discourse. ↗
3. Kordula De Kuthy, Lisa Brunetti, and Marta Berardi. 2019. Annotating information structure in Italian: Characteristics and cross-linguistic applicability of a QUD-based approach. In Proceedings of the 13th Linguistic Annotation Workshop, pages 113–123, Florence, Italy. Association for Computational Linguistics. ↗
4. Kordula De Kuthy, Madeeswaran Kannan, Haemanth Santhi Ponnusamy, and Detmar Meurers. 2020. Towards automatically generating questions under discussion to link information and discourse structure. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5786–5798, Barcelona, Spain (Online). International Committee on Computational Linguistics. ↗
5. Kordula De Kuthy, Nils Reiter, and Arndt Riester. 2018. QUD-based annotation of discourse structure and information structure: Tool and evaluation. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA). ↗ our card
6. 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. ↗
7. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 643–653, Lisbon, Portugal. Association for Computational Linguistics. find
8. Tsutomu Hirao, Yasuhisa Yoshida, Masaaki Nishino, Norihito Yasuda, and Masaaki Nagata. 2013. Single-document summarization as a tree knapsack problem. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1515–1520, Seattle, Washington, USA. Association for Computational Linguistics. ↗
9. Julie Hunter and Marta Abrusán. 2015. Rhetorical structure and quds. In JSAI International Symposium on Artificial Intelligence, pages 41–57. Springer. find
10. Andrew Kehler and Hannah Rohde. 2017. Evaluating an expectation-driven question-under-discussion model of discourse interpretation. Discourse Processes, 54(3):219–238. ↗
11. Wei-Jen Ko, Te-yuan Chen, Yiyan Huang, Greg Durrett, and Junyi Jessy Li. 2020. Inquisitive question generation for high level text comprehension. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6544–6555, Online. Association for Computational Linguistics. ↗ our card
12. 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. ↗
13. 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. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11181–11195, Toronto, Canada. Association for Computational Linguistics. ↗ our card
14. EunHee Lee. 2024. Integrating relational and intentional theories of discourse coherence. Glossa: a journal of general linguistics, 9(1). ↗
15. William C Mann and Sandra A Thompson. 1988. Rhetorical structure theory: Toward a functional theory of text organization. Text, 8(3):243–281. ↗ our card
16. Paul Grice. 1991. Studies in the Way of Words. Harvard University Press. find
17. Shashi Narayan, Joshua Maynez, Reinald Kim Amplayo, Kuzman Ganchev, Annie Louis, Fantine Huot, Anders Sandholm, Dipanjan Das, and Mirella Lapata. 2023. Conditional generation with a question-answering blueprint. Transactions of the Association for Computational Linguistics, 11:974–996. ↗
18. Luheng He, Mike Lewis, and Luke Zettlemoyer. 2015. Question-answer driven semantic role labeling: Using natural language to annotate natural language. ↗ our card
19. Edgar Onea. 2016. Potential questions at the semantics-pragmatics interface. In Potential Questions at the Semantics-Pragmatics Interface. Brill. ↗
20. Valentina Pyatkin, Ayal Klein, Reut Tsarfaty, and Ido Dagan. 2020. QADiscourse - Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2804–2819, Online. Association for Computational Linguistics. ↗
21. Pranav Rajpurkar, Robin Jia, and Percy Liang. 2018. Know what you don’t know: Unanswerable questions for SQuAD. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 784–789, Melbourne, Australia. Association for Computational Linguistics. ↗
22. Arndt Riester. 2019. Constructing qud trees. In Questions in discourse, pages 164–193. Brill. ↗
23. Arndt Riester, Lisa Brunetti, and Kordula De Kuthy. 2018. Annotation guidelines for questions under discussion and information structure. Information structure in lesser-described languages: Studies in prosody and syntax, pages 403–443. ↗ our card
24. Arndt Riester, Amalia Canes Nápoles, and Jet Hoek. 2021. Combined discourse representations: Coherence relations and questions under discussion. In Proceedings of the First Workshop on Integrating Perspectives on Discourse Annotation, pages 26–30, Tübingen, Germany. Association for Computational Linguistics. find our card
25. Craige Roberts. 2012. Information structure: Towards an integrated formal theory of pragmatics. Semantics and pragmatics, 5:6–1. ↗ our card
26. Ted JM Sanders, Wilbert PM Spooren, and Leo GM Noordman. 1992. Toward a taxonomy of coherence relations. Discourse processes, 15(1):1–35. ↗
27. Ted JM Sanders, Wilbert PM Spooren, and Leo GM Noordman. 1993. Coherence relations in a cognitive theory of discourse representation. ↗
28. Sara Shahmohammadi, Hannah Seemann, Manfred Stede, and Tatjana Scheffler. 2023. Encoding discourse structure: Comparison of RST and QUD. In Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023), pages 89– 98, Toronto, Canada. Association for Computational Linguistics. ↗ our card
29. Ashima Suvarna, Xiao Liu, Tanmay Parekh, Kai-Wei Chang, and Nanyun Peng. 2024. QUDSELECT: Selective decoding for questions under discussion parsing. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 1288–1299, Miami, Florida, USA. Association for Computational Linguistics. ↗
30. 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. ↗
31. Bonnie Webber, Matthew Stone, Aravind Joshi, and Alistair Knott. 2003. Anaphora and discourse structure. Computational Linguistics, 29(4):545–587. ↗ our card
32. Matthijs Westera, Laia Mayol, and Hannah Rohde. 2020. TED-Q: TED talks and the questions they evoke. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 1118–1127, Marseille, France. European Language Resources Association. find
33. Yating Wu, Ritika Mangla, Greg Durrett, and Junyi Jessy Li. 2023a. QUDeval: The evaluation of 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. ↗ our card
34. 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. ↗
35. Yating Wu, William Sheffield, Kyle Mahowald, and Junyi Jessy Li. 2023b. Elaborative simplification as implicit questions under discussion. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5525–5537, Singapore. Association for Computational Linguistics. ↗ our card
36. Liyan Xu, Jiangnan Li, Mo Yu, and Jie Zhou. 2024. Fine-grained modeling of narrative context: A coherence perspective via retrospective questions. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5822–5838, Bangkok, Thailand. Association for Computational Linguistics. ↗
37. Frances Yung, Vera Demberg, and Merel Scholman. 2019. Crowdsourcing discourse relation annotations by a two-step connective insertion task. In Proceedings of the 13th Linguistic Annotation Workshop, pages 16–25, Florence, Italy. Association for Computational Linguistics. ↗
38. Deniz Zeyrek, Amália Mendes, Yulia Grishina, Murathan Kurfalı, Samuel Gibbon, and Maciej Ogrodniczuk. 2020. Ted multilingual discourse bank (ted-mdb): a parallel corpus annotated in the pdtb style. Language Resources and Evaluation, 54(2):587–613. ↗
39. Jan Van Kuppevelt. 1995. Discourse structure, topicality and questioning. Journal of linguistics, 31(1):109– 147. ↗

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/fu-2025-survey-qud-models-discourse-processing/