A Dependency Perspective on RST Discourse Parsing and Evaluation

What it is about

RST parsing had been treated as constituency parsing and scored with a simplified PARSEVAL on RST-DT, which counts one attachment decision several times and says little about the semantic arguments of relations. The authors argue for dependencies between elementary discourse units: relations have a direction (cause vs effect, explained vs explanation), so trees should be headed, with heads found by following nuclei. They prove that head-ordered dependency trees (dependencies plus the order in which a head takes its dependents) are in one-to-one correspondence with headed RST constituent trees, so nothing is lost, and that span-plus-head accuracy equals unlabelled attachment score on such trees. Re-evaluating a wide panel of published parsers under one protocol, they find that many reported differences shrink, that simple dependency parsers are competitive, and that shift-reduce constituency parsers behave like dependency parsers; a dependency structure gives the minimal arguments of a relation, a constituent tree only an upper bound.

Ideas

• I1. Score Mova's frame links as discourse dependencies: convert GUM's RST trees on dev to EDU dependencies by the nucleus-head rule, map each EDU to the frame of its predicate head, and compute unlabelled and labelled attachment (does each frame attach to the right other frame, with the right link type and direction). Mova's links are already dependencies between frames, so this is the natural metric, simpler than span matching (see also costa-2023-mapping-explicit-implicit-discourse-relations I1).
• I2. Use headedness for the student: the frames that other frames attach to (the nuclei, the heads of many cause/next links) are the main events of a lesson. A centrality count over links gives a deterministic «main event» list that can weight remembered frames or answer «What is the story mainly about?». Check against GUM's central discourse units on dev before using it in courses.

For Mova

36. Discourse relations and coherence §3 (RST), §10 (discourse parsing), §11.1. Code: a dependency scorer next to prag/src/fbench.rs (GUM RST dev, evaluation only), world/src/knowledge.rs (main-event weights). Measures: link UAS/LAS against GUM dev; course questions about the main event.

Topics: Discourse analysis · Dependency parsing

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00314

@article{morey2018dependency,
  title = {{A Dependency Perspective on RST Discourse Parsing and Evaluation}},
  author = {Morey, Mathieu and Muller, Philippe and Asher, Nicholas},
  journal = {Computational Linguistics},
  year = {2018},
  doi = {10.1162/coli\_a\_00314},
  url = {https://doi.org/10.1162/coli_a_00314}
}

References

47 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Afantenos, Stergos, Eric Kow, Nicholas Asher, and Jérémy Perret. 2015. Discourse parsing for multi-party chat dialogues. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 928–937, Lisbon. find
2. Asher, Nicholas. 1993. Reference to Abstract Objects in Discourse. Kluwer. find
3. Asher, Nicholas, Julie Hunter, Mathieu Morey, Farah Benamara, and Stergos Afantenos. 2016. Discourse structure and dialogue acts in multiparty dialogue: The STAC corpus. In Tenth International Conference on Language Resources and Evaluation (LREC 2016), pages 2721–2727, Paris. find our card
4. Asher, Nicholas and Alex Lascarides. 2003. Logics of Conversation. Studies in Natural Language Processing. Cambridge University Press, Cambridge, UK. find
5. Bhatia, Parminder, Yangfeng Ji, and Jacob Eisenstein. 2015. Better document-level sentiment analysis from RST discourse parsing. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 2212–2218, Lisbon. find
6. Black, E., S. Abney, D. Flickinger, C. Gdaniec, R. Grishman, P. Harrison, D. Hindle, R. Ingria, F. Jelinek, J. Klavans, M. Liberman, M. Marcus, S. Roukos, B. Santorini, and T. Strzalkowski. 1991. Procedure for quantitatively comparing the syntactic coverage of English grammars. In Proceedings of the Workshop on Speech and Natural Language, pages 306–311, Pacific Grove, CA. find
7. Braud, Chloé, Maximin Coavoux, and Anders Søgaard. 2017. Cross-lingual RST discourse parsing. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 292–304, Valencia. find
8. Braud, Chloé, Barbara Plank, and Anders Søgaard. 2016. Multi-view and multi-task training of RST discourse parsers. In 26th International Conference on Computational Linguistics (COLING), pages 1903–1913, Osaka. find
9. Carlson, Lynn, Daniel Marcu, and Mary Ellen Okurowski. 2003. Building a discourse-tagged corpus in the framework of rhetorical structure theory. In Jan van Kuppevelt and Ronnie Smith, editors, Current Directions in Discourse and Dialogue. Kluwer Academic Publishers, pages 85–112. find our card
10. Carroll, J., E. Briscoe, and A. Sanfilippo. 1998. Parser evaluation: A survey and a new proposal. In Proceedings of the 1st International Conference on Language Resources and Evaluation, pages 447–454, Granada. find
11. Carroll, John, Guido Minnen, and Ted Briscoe. 1999. Corpus annotation for parser evaluation. In Proceedings of the EACL-99 Workshop on Linguistically Interpreted Corpora, pages 35–41, Bergen. find our card
12. Danlos, Laurence. 2004. Discourse dependency structures as constrained dags. In Proceedings of the SIGDIAL 2004 Workshop, The 5th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 127–135, Cambridge, MA. duVerle, David and Helmut Prendinger. 2009. A novel discourse parser based on support vector machine classification. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, pages 665–673, Suntec. find
13. Eisner, Jason M. 1996. Three new probabilistic models for dependency parsing: An exploration. In Proceedings of the 16th Conference on Computational linguistics-Volume 1, pages 340–345, Copenhagen. find our card
14. Feng, Vanessa Wei and Graeme Hirst. 2014. A linear-time bottom-up discourse parser with constraints and post-editing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 511–521, Baltimore, MA. find
15. Fernández-González, Daniel and André F. T. Martins. 2015. Parsing as reduction. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1523–1533, Beijing. find
16. Gaifman, Haim. 1965. Dependency systems and phrase-structure systems. Information and Control, 8(3):304–337. find
17. Grosz, B. and C. Sidner. 1986. Attention, intentions and the structure of discourse. Computational Linguistics, 12:175–204. find
18. Hayashi, Katsuhiko, Tsutomu Hirao, and Masaaki Nagata. 2016. Empirical comparison of dependency conversions for RST discourse trees. In Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 128–136, Los Angeles, CA. find
19. Hernault, Hugo, Helmut Prendinger, David A. duVerle, and Mitsuru Ishizuka. 2010. HILDA: A discourse parser using support vector machine classification. Dialogue and Discourse, 1(3):1–33. find
20. Hirao, Tsutomu, 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, WA. find
21. Hobbs, J., W. Croft, T. Davies, D. Edwards, and K. Laws. 1987. Commonsense metaphysics and lexical semantics. Computational Linguistics, 13(3-4):241–250. find
22. Iruskieta, Mikel, Iria da Cunha, and Maite Taboada. 2015. A qualitative comparison method for rhetorical structures: Identifying different discourse structures in multilingual corpora. Language Resources and Evaluation, 49(2):263–309. find
23. Ji, Yangfeng and Jacob Eisenstein. 2014. Representation learning for text-level discourse parsing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13–24, Baltimore, MD. find
24. Ji, Yangfeng and Noah A. Smith. 2017. Neural discourse structure for text categorization. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 996–1005, Vancouver. find
25. Joty, Shafiq, Giuseppe Carenini, and Raymond T. Ng. 2015. Codra: A novel discriminative framework for rhetorical analysis. Computational Linguistics, 41(3):385–435. find
26. Li, Jiwei, Rumeng Li, and Eduard Hovy. 2014. Recursive deep models for discourse parsing. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2061–2069, Doha. find
27. Li, Qi, Tianshi Li, and Baobao Chang. 2016. Discourse parsing with attention-based hierarchical neural networks. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 362–371, Austin, TX. find
28. Li, Sujian, Liang Wang, Ziqiang Cao, and Wenjie Li. 2014. Text-level discourse dependency parsing. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 25–35, Baltimore, MD. find
29. Louis, Annie, Aravind Joshi, and Ani Nenkova. 2010. Discourse indicators for content selection in summarization. In Proceedings of the SIGDIAL 2010 Conference, pages 147–156, Tokyo. find
30. Mann, William C. and Sandra A. Thompson. 1988. Rhetorical structure theory: Towards a functional theory of text organization. Text, 8(3):243–281. find
31. Marcu, Daniel. 1996. Building up rhetorical structure trees. In Proceedings of the Thirteenth National Conference on Artificial Intelligence and Eighth Innovative Applications of Artificial Intelligence Conference, AAAI 96, IAAI 96, Volume 2, pages 1069–1074, Portland, OR. find
32. Marcu, Daniel. 2000. The Theory and Practice of Discourse Parsing and Summarization. MIT Press. find
33. McDonald, Ryan, Koby Crammer, and Fernando Pereira. 2005. Online large-margin training of dependency parsers. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, pages 91–98, Ann Arbor, MI. find our card
34. Morey, Mathieu, Philippe Muller, and Nicholas Asher. 2017. How much progress have we made on RST discourse parsing? A replication study of recent results on the RST-DT. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1330–1335, Copenhagen. find our card
35. Muller, Philippe, Stergos Afantenos, Pascal Denis, and Nicholas Asher. 2012. Constrained decoding for text-level discourse parsing. In Proceedings of COLING 2012, pages 1883–1900, Mumbai. find
36. Nigam, Kamal, John Lafferty, and Andrew McCallum. 1999. Using maximum entropy for text classification. In IJCAI-99 Workshop on Machine Learning for Information Filtering, volume 1, pages 61–67, Stockholm. find
37. Perret, Jérémy, Stergos Afantenos, Nicholas Asher, and Mathieu Morey. 2016. Integer linear programming for discourse parsing. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 99–109, San Diego, CA. find
38. Prasad, Rashmi, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind Joshi, and Bonnie L. Webber. 2008. The Penn Discourse TreeBank 2.0. In Proceedings of LREC 2008, pages 2961–2968, Marrakech. find our card
39. Reitter, David. 2003. Simple signals for complex rhetorics: On rhetorical analysis with rich-feature support vector models. In LDV Forum, volume 18, pages 38–52. find
40. Sagae, Kenji. 2009. Analysis of discourse structure with syntactic dependencies and data-driven shift-reduce parsing. In Proceedings of the 11th International Conference on Parsing Technologies, pages 81–84, Stroudsburg, PA. find
41. Sagae, Kenji and Alon Lavie. 2005. A classifier-based parser with linear run-time complexity. In Proceedings of the Ninth International Workshop on Parsing Technology, pages 125–132, Vancouver. find
42. Soricut, Radu and Daniel Marcu. 2003. Sentence level discourse parsing using syntactic and lexical information. In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology-Volume 1, pages 149–156, Edmonton. find our card
43. Surdeanu, Mihai, Thomas Hicks, and Marco A. Valenzuela-Escárcega. 2015. Two practical rhetorical structure theory parsers. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, pages 1–5, Denver, CO. find
44. van der Vliet, Nynke and Gisela Redeker. 2011. Complex sentences as leaky units in discourse parsing. In Proceedings of Constraints in Discourse, pages 1–9, Agay-Saint Raphaël. find
45. Venant, Antoine, Nicholas Asher, Philippe Muller, Pascal Denis, and Stergos Afantenos. 2013. Expressivity and comparison of models of discourse structure. In Proceedings of the SIGDIAL 2013 Conference, pages 2–11, Metz. find
46. Wolf, Florian and Edward Gibson. 2006. Coherence in Natural Language: Data Structures and Applications. The MIT Press. find
47. Yoshida, Yasuhisa, Jun Suzuki, Tsutomu Hirao, and Masaaki Nagata. 2014. Dependency-based discourse parser for single-document summarization. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1834–1839, Doha. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/morey-2018-dependency-perspective-rst-discourse-parsing/