Elamur Research⌕
☰
home / papers / 2010 / Realization of Discourse Relations by Other Means: Alternative Lexicalizations

Realization of Discourse Relations by Other Means: Alternative Lexicalizations

Summary

Discourse relations such as cause, contrast or instantiation have traditionally been tied to a closed inventory of connectives drawn from a few syntactic classes: conjunctions, adverbs and prepositional phrases. Prasad, Joshi and Webber argue that this view is too narrow. They show how annotation of the Penn Discourse Treebank (PDTB) uncovered many other signals. When annotators tried to insert an implicit connective between adjacent sentences, some insertions sounded redundant because another expression in the text already conveyed the relation (e.g., "One reason is"). These cases were labelled AltLex in PDTB 2.0. Using the PDTB–Penn Treebank alignment, the authors analyse the syntax and lexical flexibility of these expressions. Most AltLex items are neither fixed phrases nor members of the accepted connective classes. They conclude that discourse relation markers (DRMs) form an open-ended class. This challenges both list-based annotation and token-classification approaches to automatic DRM detection. As a first step toward finding unlisted markers, they run a pilot using Callison-Burch's back-translation paraphrasing, including its syntactically constrained variant.

Key points

  • AltLex emerged from implicit-relation cases marked "NONE". These were split into EntRel, NoRel and AltLex, the last covering cases where an inserted connective would be redundant. PDTB 2.0 contains 624 AltLex tokens.
  • The AltLex tokens fall into three groups:
    • 92 (14.7%) are syntactically admitted and lexically frozen, i.e., connectives missing from the original list.
    • 54 (8.7%) are frozen but come from other syntactic classes (e.g., "What's more").
    • 478 (76.6%) are free both syntactically and lexically (e.g., "That is why", "The plunge followed").
  • In the pilot, Callison-Burch supplied EuroParl back-translations for 147 DRMs. These surfaced markers absent from the WSJ corpus (e.g., "as a consequence", "by the same token"). They also surfaced unannotated in-corpus markers (e.g., "above all", "after all"), often in paragraph-initial sentences, which were excluded from implicit annotation.
  • The authors identify two limitations of the back-translation approach:
    • Translations may differ in how explicitly they express relations, which adds alignment noise.
    • Morphologically marked DRMs, as in Turkish, would require extra handling.

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

38 papers of our library cite it (of the 140673 whose bibliographies we read); 14 of them have a page here, 24 not yet.

Cite

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

@inproceedings{prasad2010realization,
  title = {{Realization of Discourse Relations by Other Means: Alternative Lexicalizations}},
  author = {Prasad, Rashmi and Joshi, Aravind and Webber, Bonnie},
  booktitle = {Coling 2010: Posters},
  year = {2010},
  url = {https://aclanthology.org/C10-2118/}
}

References

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

  1. Callison-Birch, Chris. 2007. Paraphrasing and Translation. Ph.D. thesis, School of Informatics, University of Edinburgh. find
  2. Callison-Birch, Chris. 2008. Syntactic constraints on paraphrases extracted from parallel corpora. In Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  3. Danlos, Laurence. 2006. Discourse verbs. In Proceedings of the 2nd Workshop on Constraints in Discourse, pages 59–65, Maynooth, Ireland. find
  4. Forbes-Riley, Katherine, Bonnie Webber, and Aravind Joshi. 2006. Computing discourse semantics: The predicate-argument semantics of discourse connectives in D-LTAG. Journal of Semantics, 23:55–106. find
  5. Halliday, M. A. K. and Ruqaiya Hasan. 1976. Cohesion in English. London: Longman. find
  6. Huong, LeThanh, Geetha Abeysinghe, and Christian Huyck. 2003. Using cohesive devices to recognize rhetorical relations in text. In Proceedings of 4th Computational Linguistics UK Research Colloquium (CLUK 4), University of Edinburgh, UK. find
  7. Kibble, Rodger. 1999. Nominalisation and rhetorical structure. In Proceedings of ESSLLI Formal Grammar conference, Utrecht. find
  8. Knott, Alistair. 1996. A Data-Driven Methodology for Motivating a Set of Coherence Relations. Ph.D. thesis, University of Edinburgh, Edinburgh. find
  9. Lin, Ziheng, Min-Yen Kan, and Hwee Tou Ng. 2009. Recognizing implicit discourse relations in the penn discourse treebank. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Singapore. find our card
  10. Maat, Henk Pander and Ted Sanders. 2000. Domains of use or subjectivity? the distribution of three dutch causal connectives explained. TOPICS IN ENGLISH LINGUISTICS, pages 57–82. find
  11. Marcu, Daniel and Abdessamad Echihabi. 2002. An unsupervised approach to recognizing discourse relations. In Proceedings of the Association for Computational Linguistics. find our card
  12. Marcus, Mitchell P., Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. Building a large annotated corpus of english: The Penn Treebank. Computational Linguistics, 19(2):313–330. find our card
  13. Martin, James R. 1992. English text: System and structure. Benjamins, Amsterdam. find
  14. Oza, Umangi, Rashmi Prasad, Sudheer Kolachina, Dipti Mishra Sharma, and Aravind Joshi. 2009. The hindi discourse relation bank. In Proceedings of the ACL 2009 Linguistic Annotation Workshop III (LAW-III), Singapore. find our card
  15. Pitler, Emily and Ani Nenkova. 2009. Using syntax to disambiguate explicit discourse connectives in text. In Proceedings of the Joint Conference of the 47th Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing, Singapore. find our card
  16. Pitler, Emily, Annie Louis, and Ani Nenkova. 2009. Automatic sense prediction for implicit discourse relations in text. In Proceedings of the Joint Conference of the 47th Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processin… find our card
  17. Power, Richard. 2007. Abstract verbs. In ENLG ’07: Proceedings of the Eleventh European Workshop on Natural Language Generation, pages 93–96, Morristown, NJ, USA. Association for Computational Linguistics. find
  18. Prasad, Rashmi, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. 2008. The Penn Discourse TreeBank 2.0. In Proceedings of 6th International Conference on Language Resources and Evaluation (LREC 2008). find our card
  19. PDTB-Group. 2008. The Penn Discourse TreeBank 2.0 Annotation Manual. Technical Report IRCS-08-01, Institute for Research in Cognitive Science, University of Pennsylvania. find
  20. Sporleder, Caroline and Alex Lascarides. 2008. Using automatically labelled examples to classify rhetorical relations: an assessment. Natural Language Engineering, 14(3):369–416. find
  21. Steedman, Mark. 2000. The Syntactic Process. MIT Press, Cambridge MA. find
  22. Taboada, Maite. 2006. Discourse markers as signals (or not) of rhetorical relations. Journal of Pragmatics, 38(4):567–592. find
  23. Yu, Hong, Nadya Frid, Susan McRoy, P Simpson, Rashmi Prasad, Alan Lee, and Aravind Joshi. 2008. Exploring discourse connectivity in biomedical text for text mining. In Proceedings of the 16th Annual International Conference on Intelligent Systems for Molecular Biology BioLINK SIG Meeting, Toronto, C… find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/prasad-2010-realization-discourse-relations-other-means/