Elamur Research⌕
☰
home / papers / 2018 / Discourse Coherence: Concurrent Explicit and Implicit Relations

Discourse Coherence: Concurrent Explicit and Implicit Relations

Summary

The paper asks why readers sometimes link the same pair of discourse segments with conjunctions that seem incompatible, such as SO and OR. Earlier work by the authors showed this happens around explicit discourse adverbials. Rohde et al. argue that these splits are not noise or annotator bias. Instead, several coherence relations hold at once: some are signalled explicitly by the adverbial, and others are inferred from the passage content.

To test this, they ran a controlled conjunction-insertion experiment. Native English speakers filled a gap before an adverbial (in other words, otherwise, instead, after all) with one or more conjunctions. Some passages were deliberately altered, for example by making them more parallel or more causal, or by removing the adverbial. The results show that conjunction choices follow from two sources:

  • the lexical semantics of the adverbial;
  • properties of the surrounding text.

This matters for annotation and parsing. Resources like the PDTB do not record an inferred relation alongside an explicit adverbial, and most parsers assume one relation per segment pair.

Key points

  • Participants and setup: 28 pre-screened monolingual English speakers (paid £50) saw passages in batches of 34 over three days. The choices were AND, BECAUSE, BUT, OR, SO and NONE, and 6 catch trials checked data quality.
  • Materials: 16 passages each with in other words, instead and after all, plus 48 with otherwise. The passages are released via the ACL Anthology "dataset" link.
  • Instead: parallel variants drew more BUT, while causal variants drew significantly more SO (β = −7.0008, p < 0.001).
  • After all: removing the adverbial barely changed responses (R² = .70, F(1,13) = 30.98, p < 0.001), with passage G as the single outlier.
  • Otherwise: participant paraphrases largely matched researcher-assigned senses (ARGUMENTATION 91.5%, ENUMERATION 81.4%, EXCEPTION 87.7%).

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

Topics: Discourse analysis

Cited by

18 papers of our library cite it (of the 140673 whose bibliographies we read); 5 of them have a page here, 13 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/p18-1210

@inproceedings{rohde2018discourse,
  title = {{Discourse Coherence: Concurrent Explicit and Implicit Relations}},
  author = {Rohde, Hannah and Johnson, Alexander and Schneider, Nathan and Webber, Bonnie},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2018},
  doi = {10.18653/v1/p18-1210},
  url = {https://doi.org/10.18653/v1/p18-1210}
}

References

26 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. M.J. Cuenca and M.J. Marin. 2009. Co-occurrence of discourse markers in Catalan and Spanish oral narrative. Journal of Pragmatics, 41(5):899–914. find
  2. Jesse Dunietz, Lori Levin, and Jaime Carbonell. 2017. The BECauSE Corpus 2.0: Annotating causality and overlapping relations. In Proceedings of the 11th Linguistic Annotation Workshop, pages 95–104, Valencia, Spain. find
  3. Vanessa Wei Feng and Graeme Hirst. 2012. Text-level discourse parsing with rich linguistic features. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, pages 60–68, Jeju Island, Korea. find our card
  4. Bruce Fraser. 2013. Combinations of contrastive discourse markers in English. International Review of Pragmatics, 5:318–340. find
  5. Barbara Grosz and Candace Sidner. 1986. Attention, intention and the structure of discourse. Computational Linguistics, 12(3):175–204. find
  6. Michael Halliday and Ruqaiya Hasan. 1976. Cohesion in English. Longman. find
  7. Yangfeng Ji 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, pages 13–24, Baltimore, Maryland. find our card
  8. Alistair Knott. 1996. A Data-driven Methodology for Motivating a Set of Coherence Relations. Ph.D. dissertation, Department of Artificial Intelligence, University of Edinburgh. find
  9. Ziheng Lin, Hwee Tou Ng, and Min-Yen Kan. 2014. A PDTB-styled end-to-end discourse parser. Natural Language Engineering, pages 151–184. find
  10. William C. Mann, Christian M. I. M. Matthiessen, and Sandra A. Thompson. 1989. Rhetorical structure theory and text analysis. Technical Report ISI/RR-89-242, USC-ISI, Marina del Rey CA. find
  11. William C. Mann and Sandra A. Thompson. 1988. Rhetorical Structure Theory: Toward a functional theory of text organization. Text, 8(3):243–281. find our card
  12. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Milt-sakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. 2008. The Penn Discourse TreeBank 2.0. In Proceedings of the 6th International Conference on Language Resources and Evaluation, pages 2961–2968, Marrakech, Morocco. find our card
  13. 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. find our card
  14. Hannah Rohde, Anna Dickinson, Chris Clark, Annie Louis, and Bonnie Webber. 2015. Recovering discourse relations: Varying influence of discourse adverbials. In Proceedings of the First Workshop on Linking Computational Models of Lexical, Sentential and Discourse-level Semantics, pages 22–31, Lisbon,… find our card
  15. Hannah Rohde, Anna Dickinson, Nathan Schneider, Christopher Clark, Annie Louis, and Bonnie Webber. 2016. Filling in the blanks in understanding discourse adverbials: Consistency, conflict, and context-dependence in a crowdsourced elicitation task. In Proceedings of the Tenth Linguistic Annotation Wo… find
  16. Hannah Rohde, Anna Dickinson, Nathan Schneider, Annie Louis, and Bonnie Webber. 2017. Exploring substitutability through discourse adverbials and multiple judgments. In Proceedings of the 12th International Conference on Computational Semantics (IWCS), Montpellier, France. find
  17. Merel Scholman and Vera Demberg. 2017. Crowdsourcing discourse interpretations: On the influence of context and the reliability of a connective insertion task. In Proceedings of the 11th Linguistic Annotation Workshop, pages 24–33, Valencia, Spain. find
  18. Manfred Stede. 2012. Discourse Processing. Morgan & Claypool Publishers. find
  19. Bonnie Webber. 2013. What excludes an alternative in coherence relations? In Proceedings of the 10th International Conference on Computational Semantics, Potsdam, Germany. find our card
  20. Daniel Marcu. 2000. The theory and practice of discourse parsing and summarization. MIT Press. find
  21. Bonnie Webber, Aravind Joshi, and Alistair Knott. 2000. The anaphoric nature of certain discourse connectives. In Making Sense: From Lexeme to Discourse, Groningen, The Netherlands. find
  22. Eleni Miltsakaki, Nikhil Dinesh, Rashmi Prasad, Aravind Joshi, and Bonnie Webber. 2005. Experiments on sense annotation and sense disambiguation of discourse connectives. In Proceedings of the Fourth Workshop on Treebanks and Linguistic Theories (TLT’05), Barcelona, Spain. find
  23. Nianwen Xue, Hwee Tou Ng, Sameer Pradhan, Rashmi Prasad, Christopher Bryant, and Attapol T. Rutherford. 2015. The CoNLL-2015 Shared Task on Shallow Discourse Parsing. In Proceedings of the Nineteenth Conference on Computational Language Learning: Shared Task, pages 1–16, Beijing, China. find our card
  24. Johanna Moore and Martha Pollack. 1992. A problem for RST: The need for multi-level discouse analysis. Computational Linguistics, 18(4):537–544. find
  25. Nianwen Xue, Hwee Tou Ng, Sameer Pradhan, Attapol Rutherford, Bonnie Webber, Chuan Wang, and Hongmin Wang. 2016. find
  26. CoNLL 2016 Shared Task on Multilingual Shallow Discourse Parsing. In Proceedings of the 20th Conference on Computational Natural Language Learning – Shared Task, pages 1– 19, Berlin, Germany. find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/rohde-2018-discourse-coherence-concurrent-explicit-implicit/