Detection and Resolution of Verb Phrase Ellipsis

What it is about

The paper describes ViPER, a rule-based system that detects and resolves VP ellipsis. It uses syntactic parallelism, modality correlations and the split between core and peripheral sentence constituents. Its key claim is that some cases are easy enough to resolve with high confidence before full semantic understanding exists. It was run on Gigaword. Of 26,988 candidate sentences, 18,027 remained after pruning false positives such as homonyms, parentheticals and idioms. Annotators judged 393 treatable examples: 239 (61%) were fully correct, 75 (19%) partly correct and 80 (20%) incorrect. For 320 of the 393 (81%), all three annotators chose the same resolution. The best single strategy, a parallel-modal rule without trimming, was correct on 45 of 55 examples (82%).

Ideas

• I1. en/src/expert.rs: encode the three ViPER conditions as separate rules: parallel syntactic configuration, modal pairing and core-versus-peripheral constituents. Log the rule that fired in en/src/explain.rs, so every resolution gives its reason.
• I2. Coverage against precision: report, for each rule, how many cases it covers and how often it is correct on a held-out sample. Emit a resolution only from the rules with high precision, and state the coverage. The paper's split into correct, partial and incorrect outcomes is the right form for this table.
• I3. Gold by agreement: in annot, accept a sponsor as gold when all annotators agree (81% in the paper). Send the disagreements to review, and do not let them enter the gold set silently.

For Mova

The code is en/src/expert.rs, en/src/explain.rs and annot. The chapters are 29. Ellipsis, word order and information structure and 24. Coordination and subordination (parallelism). The Gigaword source is licensed data, so use only the test material that the licence allows. Measure first: the correct, partial and incorrect split for the parallel-modal rule on a sample we may test on.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.33011/lilt.v13i.1385

@inproceedings{mcshane2016detection,
  title = {{Detection and Resolution of Verb Phrase Ellipsis}},
  author = {McShane, Marjorie and Babkin, Petr},
  booktitle = {Linguistic Issues in Language Technology},
  year = {2016},
  doi = {10.33011/lilt.v13i.1385},
  url = {https://doi.org/10.33011/lilt.v13i.1385}
}

References

26 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Artstein, R. and M. Poesio. 2008. Inter-coder agreement for computational linguistics. Computational Linguistics 34(4):555–596. find
2. Baldwin, B. 1997. CogNIAC: High precision coreference with limited knowledge and linguistic resources. In Proceedings of a Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts. Association for Computational Linguistics. find our card
3. Bos, J. and J. Spenader. 2011. An annotated corpus for the analysis of VP ellipsis. Language Resources and Evaluation 45:463–494. find
4. Davies, M. 2008. The Corpus of Contemporary American English: 450 million words, 1990-present. Available online at http://corpus.byu.edu/coca/. ↗
5. Fiengo, R. and R. May. 1994. Indices and Identity. Cambridge, Mass.: The MIT Press. find
6. Gagnon, M. and L. Da Sylva. 2005. Text summarization by sentence extraction and syntactic pruning. In Proceedings of Computational Linguistics in the North East. find
7. Goodall, G. 2009. Parallel Structures in Syntax: Coordination, Causatives and Restructuring. Cambridge University Press. find
8. Graff, D. and C. Cieri. 2003. English Gigaword. Linguistic Data Consortium, Philadelphia. find
9. Grosz, B., A. K. Joshi, and S. Weinstein. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics 21(2):203–225. find our card
10. Hardt, D. 1997. An empirical approach to VP ellipsis. Computational Linguistics 23(4):525–541. find our card
11. Hirshman, L. and N. Chinchor. 1997. MUC-7 Coreference Task Definition. Version 3.0. In Proceedings of the Seventh Message Understanding Conference (MUC-7). Applications International Corporation. References / 33 find
12. Hobbs, J. R. and A. Kehler. 1998. A theory of parallelism and the case of VP ellipsis. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics (ACL-98), pages 394–401. find
13. Knight, K. and D. Marcu. 2002. Summarization beyond sentence extraction: A probabilistic approach to sentence compression. Artificial Intelligence 139(1):91–107. find
14. Krippendorff, K. 2010. Krippendorff’s alpha. In N. Salkind, ed., Encyclopedia of Research Design, pages 669–674. Thousand Oaks, CA: SAGE Publications, Inc. find
15. Lee, H., A. Chang, Y. Peirsman, N. Chambers, M. Surdeanu, and D. Jurafsky. 2013. Deterministic coreference resolution based on entity-centric, precision-ranked rules. Computational Linguistics 39(4):885–916. find our card
16. Manning, C. D., M. Surdeanu, J. Bauer, J. Finkel, S. J. Bethard, and D. McClosky. 2014. The Stanford CoreNLP Natural Language Processing Toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 55–60. find
17. McShane, M. 2000. Hierarchies of parallelism in elliptical Polish structures. Journal of Slavic Linguistics 8:83–117. find
18. McShane, M. and S. Nirenburg. 2012. A knowledge representation language for natural language processing, simulation and reasoning. International Journal of Semantic Computing 6:3–23. find
19. Mitkov, R. 2001. Outstanding issues in anaphora resolution. In Computational Linguistics and Intelligent Text Processing, pages 110–125. Springer. find
20. Nielsen, L. A. 2005. A corpus-based study of verb phrase ellipsis identification and resolution. Ph.D. thesis, King’s College London. find
21. Nirenburg, S. and V. Raskin. 2004. Ontological Semantics. Cambridge, Mass.: The MIT Press. find
22. Olsson, F. 2004. A survey of machine learning for reference resolution in textual discourse. Tech. Rep. T2004:02. ISSN 1100-3154. ISRN:SICS-T-2004/02-SE., SICS. find
23. Poesio, M., R. Stevenson, B. di Eugenio, and J. Hitzeman. 2004. Centering: A parametric theory and its instantiations. Computational Linguistics 30:309–363. find
24. Stoyanov, V., N. Gilbert, C. Cardie, and E. Riloff. 2009. Conundrums in noun phrase coreference resolution: Making sense of the state-of-the-art. In Proceedings of Joint Conference of the 47th Annual Meeting of the Association of Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing. find our card
25. Vanderwende, L., H. Suzuki, C. Brockett, and A. Nenkova. 2007. Beyond SumBasic: Task-focused summarization with sentence simplification and lexical expansion. Information Processing and Management 43(6):1606– 1618. find
26. Webber, B. L. 1988. Discourse deixis: reference to discourse segments. In Proceedings of the 26th Annual Meeting of the Association for Computational Linguistics (ACL ’88), pages 113–122. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2016-mcshane-detection-resolution-verb-phrase-ellipsis/