Elamur Research⌕
☰
home / papers / 2013 / What excludes an Alternative in Coherence Relations?

What excludes an Alternative in Coherence Relations?

Summary

The paper asks what linguistic signals mark one argument of a coherence relation as an alternative that the discourse sets aside. It focuses on the CHOSEN ALTERNATIVE sense of the Penn Discourse TreeBank 2.0 (PDTB 2.0). Recognizing discourse relations without an overt connective remains hard. Webber argues that better features will help more than new learning algorithms. She uses the connective instead as an almost unambiguous marker of this sense. Drawing on PDTB 2.0 and a separate hand-collected Instead Corpus, she catalogues the constructions that appear in Arg1, which supplies the rejected option. The most frequent are negation, downward-entailing (DE) predicates and event modals. Less common licensers include state-expecting verbs and non-factual if clauses. These cues show up even more often when the CHOSEN ALTERNATIVE relation is implicit than when it is explicitly signalled. When strong cues are present, the connective is often omitted. When the evidence is subtle, a connective tends to appear. This makes the features promising for identifying implicit relations and their arguments automatically.

Key points

  • PDTB 2.0 contains more than 40K manually annotated relations over the Wall Street Journal corpus. Of its 112 tokens of instead, 108 are labelled EXPANSION.ALTERNATIVE.CHOSEN ALTERNATIVE. The author argues the remaining four also belong to this sense.

  • A supplementary, singly-annotated Instead Corpus of more than 300 tokens provides additional evidence.

  • The frequency of each feature in implicit relations (171 tokens) versus explicit relations (118 tokens) is:

    FeatureImplicitExplicit
    Negation67.8%39.8%
    DE predicates14.0%15.3%
    Event modals5.3%11.0%
    Other12.9%33.9%

  • About 87% of implicit CHOSEN ALTERNATIVE relations contain at least one of the three main features.

  • These cues also occur in other relations, such as temporal and causal ones. They are therefore not sufficient on their own, but their absence counts as evidence against a candidate Arg1.

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

12 papers of our library cite it (of the 140673 whose bibliographies we read); 5 of them have a page here, 7 not yet.

Cite

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

@inproceedings{webber2013what,
  title = {{What excludes an Alternative in Coherence Relations?}},
  author = {Webber, Bonnie},
  booktitle = {Proceedings of the 10th International Conference on Computational Semantics (IWCS 2013) – Long Papers},
  year = {2013},
  url = {https://aclanthology.org/W13-0124/}
}

References

27 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Carlson, L. and D. Marcu (2001). Discourse tagging reference manual. Technical Report ISI-TR-545, Information Sciences Institute. find
  2. Carlson, L., D. Marcu, and M. E. Okurowski (2003). Building a discourse-tagged corpus in the framework of rhetorical structure theory. In J. van Kuppevelt & R. Smith (Ed.), Current Directions in Discourse and Dialogue. New York: Kluwer. find our card
  3. Danescu-Niculescu-Mizil, C., L. Lee, and R. Ducott (2009). Without a ’doubt’? unsupervised discovery of downward-entailing operators. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Boulder, Col… find
  4. Feng, V. W. and G. Hirst (2012). Text-level discourse parsing with rich linguistic features. In Proc. 50th Annual Meeting of the Association for Computational Linguistics, Jeju Island, Korea, pp. 60–68. find our card
  5. Ghosh, S., R. Johansson, G. Riccardi, and S. Tonelli (2011). Shallow discourse parsing with conditional random fields. In Proceedings, International Joint Conference on Natural Language Processing. find our card
  6. Halliday, M. and R. Hasan (1976). Cohesion in English. Longman. find
  7. Hernault, H., H. Prendinger, D. A. duVerle, and M. Ishizuka (2010). Hilda: A discourse parser using support vector machine classication. Dialogue and Discourse 1(3), 1–33. find
  8. Knott, A. (1996). A Data-driven Methodology for Motivating a Set of Coherence Relations. Ph. D. thesis, Department of Artificial Intelligence, University of Edinburgh. find
  9. Knott, A., J. Oberlander, M. O’Donnell, and C. Mellish (2001). Beyond elaboration: The interaction of relations and focus in coherent text. In T. Sanders, J. Schilperoord, and W. Spooren (Eds.), Text Representation:Linguistic and psycholinguistic aspects, pp. 181–196. John Benjamins Publishing. find
  10. Knott, A. and T. Sanders (1998). The classification of coherence relations and their linguistic markers. Journal of Pragmatics 30, 135–175. find
  11. Lin, Z. (2012). Discourse Parsing: Inferring Discourse Structure, Modelling Coherence, and its Applications. Ph. D. thesis, National University of Singapore. find
  12. Lin, Z., H. T. Ng, and M.-Y. Kan (2010, November). A PDTB-styled end-to-end discourse parser. Technical report, Department of Computing, National University of Singapore. http://arxiv.org/abs/1011.0835. ↗
  13. Mann, W. and S. Thompson (1988). Rhetorical Structure Theory: Toward a functional theory of text organization. Text 8(3), 243–281. find our card
  14. Marcu, D. (2000). The theory and practice of discourse parsing and summarization. MIT Press. find
  15. Marcu, D. and A. Echihabi (2002). An unsupervised approach to recognizing discourse relations. In Proceedings of ACL’02. find our card
  16. Martin, J. (1992). English Text: System and Structure. Philadelphia: John Benjamins. find
  17. Mauri, C. (2008). Towards a typology of disjunction. Studies in Language 32, 22–55. find
  18. Moore, J. and M. Pollack (1992). A problem for RST: The need for multi-level discouse analysis. Computational Linguistics 18(4), 537–544. find
  19. Palmer, F. (2001). Mood and Modality (2 ed.). Cambridge: Cambridge University Press. find
  20. Prasad, R., N. Dinesh, A. Lee, E. Miltsakaki, L. Robaldo, A. Joshi, and B. Webber (2008). The Penn Discourse TreeBank 2.0. In Proceedings, 6th International Conference on Language Resources and Evaluation, Marrakech, Morocco, pp. 2961–2968. find our card
  21. Prasad, R., S. McRoy, N. Frid, A. Joshi, and H. Yu (2011). The Biomedical Discourse Relation Bank. BMC Bioinformatics 12(188), 18 pages. http://www.biomedcentral.com/1471-2015/12/188. ↗
  22. Sagae, K. (2009). Analysis of discourse structure with syntactic dependencies and data-driven shift-reduce parsing. In In Proceedings of IWPT 2009. find
  23. Sporleder, C. and A. Lascarides (2008). Using automatically labelled examples to classify rhetorical relations: an assessment. Natural Language Engineering 14(3), 369–416. find
  24. Stede, M. (2012). Discourse Processing. Morgan & Claypool Publishers. find
  25. Subba, R., B. D. Eugenio, and S. N. Kim (2006). Discourse parsing: Learning fol rules based on rich verb semantic representations to automatically label rhetorical relations. In Proc. EACL Workshop on Learning Structured Information in Natural Language Applications. find
  26. The PDTB Research Group (2008). The Penn Discourse TreeBank 2.0 Annotation Manual. http://www.seas.upenn.edu/˜pdtb/, or as part of the download of LDC2008T05. ↗
  27. Webber, B., M. Egg, and V. Kordoni (2012). Discourse structure and language technology. Natural Language Engineering 18(4), 437–490. find

↑ back to top

This page in Markdown →