An Empirical Approach to VP Ellipsis

What it is about

Hardt builds the first corpus-based system for resolving VP ellipsis (VPE). The data are 644 VPE examples found in the parsed Penn Treebank, 260 of them from the Wall Street Journal. A syntactic filter first removes candidate antecedents in impossible configurations. The remaining candidates are ranked by four preference factors: recency, clausal relations, parallelism and quotation structure. On a blind test of 96 WSJ examples, the system gets 94.8% head-overlap success, against 75.0% for a recency baseline. Its exact-match accuracy is 76.0%, against 14.6% for the baseline. Human coders agree on the exact match in 93% of cases. Removing the clausal-relation factor drops the score from 75.9% to 72.8%.

Ideas

• I1. en/src/expert.rs: write the syntactic filter as rules over UD trees. Each rule rejects a candidate verb head in a configuration where VPE cannot take it as antecedent, and the rule name is logged in en/src/explain.rs, so every rejection can say why.
• I2. Recency baseline first: report the recency-only score next to the ranked score on the same test set, with the head-overlap and exact-match measures from the paper. A ranker that does not beat recency by a wide margin is not worth its rules.
• I3. Factor ablation on training data only: drop each preference factor in turn, as the paper does for Clause-Rel, and report the drop with en folds. The test set stays held out until the release check.

For Mova

The code is en/src/expert.rs and en/src/explain.rs. The chapter is 29. Ellipsis, word order and information structure. The Penn Treebank data is licensed, so the paper's numbers are not Mova numbers and no Penn data goes into what is built. Measure first on a VPE set whose licence allows testing: check the licence before any run.

Topics: Coreference resolution

Cite

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

@article{hardt1997empirical,
  title = {{An Empirical Approach to VP Ellipsis}},
  author = {Hardt, Daniel},
  journal = {Computational Linguistics},
  year = {1997},
  url = {https://aclanthology.org/J97-4002/}
}

References

32 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Asher, Nicholas. 1993. Reference to Abstract Objects in English. Dordrecht. find
2. Brennan, Susan E., Marilyn Walker Friedman, and Carl J. Pollard. 1987. A centering approach to pronouns. In Proceedings of the 25th Annual Meeting. Association for Computational Linguistics. find
3. Chao, Wynn. 1987. On Ellipsis. Ph.D. thesis, University of Massachusetts-Amherst. find
4. Chomsky, Noam. 1981. Lectures on Government and Binding. Foris. find
5. Dalrymple, Mary, Stuart Shieber, and Fernando Pereira. 1991. Ellipsis and higher-order unification. Linguistics and Philosophy, 14(4). find
6. Fiengo, Robert and Robert May. 1994. Indices and Identity. MIT Press, Cambridge, MA. find
7. Hankamer, Jorge and Ivan Sag. 1976. Deep and surface anaphora. Linguistic Inquiry, 7(3). find
8. Hardt, Daniel. 1992. An Algorithm for VP Ellipsis. In Proceedings of the 30th Annual Meeting, Newark, DE. Association for Computational Linguisitics. find
9. Hardt, Daniel. 1993. Verb Phrase Ellipsis: Form, Meaning, and Processing. Ph.D. thesis, University of Pennsylvania. find
10. Hardt, Daniel. 1995. An empirical approach to VP ellipsis. In Proceedings, AAAI Symposium on Empirical Approaches in Discourse and Generation, Palo Alto, CA. find our card
11. Harper, Mary Patricia. 1990. The Representation of Noun Phrases in Logical Form. Ph.D. thesis, Brown University. find
12. Hobbs, Jerry. 1978. Resolving pronoun references. Lingua, 44:311-338. find our card
13. Hobbs, Jerry. 1979. Coherence and coreference. Cognitive Science, 3:67-90. find
14. Hobbs, Jerry and Andrew Kehler. 1997. A Theory of Parallelism and the Case of VP ellipsis. In Proceedings of the 35th Annual Meeting, Madrid, Spain. Association for Computational Linguisitics. find
15. Jacobson, Pauline. 1992. Antecedent contained deletion in a variable-free semantics. In Proceedings of the Second Conference on Semantics and Linguistic Theory, Columbus, Ohio. find
16. Kehler, Andrew. 1993. The effect of establishing coherence in ellipsis and anaphora resolution. In Proceedings of the 31st Annual Meeting, Columbus, OH. Association for Computational Linguistics. find
17. Kitagawa, Yoshihisa. 1991. Copying identity. Natural Language and Linguistic Theory, 9(3):497-536. find
18. Lappin, Shalom. 1984. VP anaphora, quantifier scope, and logical form. Linguistic Analysis, 13(4):273-315. find
19. Lappin, Shalom. 1992. The syntactic basis of ellipsis resolution. In Proceedings of the Stuttgart Ellipsis Workshop, Stuttgart, Germany. find
20. Lappin, Shalom and Herbert J. Leass. 1994. An algorithm for pronominal anaphora resolution. Computational Linguistics. find our card
21. Lappin, Shalom and Michael McCord. 1990. Anaphora resolution in slot grammar. Computational Linguistics, 16(4). find
22. Malt, Barbara. 1984. The role of discourse structure in understanding anaphora. Journal of Memory and Language, 24:271-289. find
23. Marcus, Mitchell P., Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19(2). find our card
24. May, Robert. 1985. Logical Form: Its Structure and Derivation. MIT Press, Cambridge, MA. find
25. Priist, Hub, Remko Scha, and Martin van den Berg. 1991. A discourse perspective on verb phrase anaphora. Linguistics and Philosophy, 17(3):261-327. find
26. Ristad, E. S. 1990. Computational Structure of Human Language. Ph.D. thesis, Massachusetts Institute of Technology. find
27. Ross, H. 1967. Constraints on variables in syntax. MIT Department of Linguistics and Philosophy. find
28. Sag, Ivan and Jorge Hankamer. 1984. Towards a theory of anaphoric processing. Linguistics and Philosophy, 7:325-345. find
29. Sag, Ivan A. 1976. Deletion and Logical Form. Ph.D. thesis, Massachusetts Institute of Technology. (Published 1980 by Garland Publishing, New York). find
30. Walker, Marilyn. 1989. Evaluating discourse processing algorithms. In Proceedings of the 27th Annual Meeting, Vancouver, Canada. Association for Computational Linguistics. find
31. Webber, Bonnie Lynn. 1978. A Formal Approach to Discourse Anaphora. Ph.D. thesis, Harvard University. (Published 1979 by Garland Publishing, New York). find
32. Williams, Edwin. 1977. Discourse and logical form. Linguistic Inquiry, 8(1):101-139. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/cl-1997-hardt-empirical-approach-vp-ellipsis/