Verb Phrase Ellipsis detection using Automatically Parsed Text

What it is about

Nielsen builds a detector for VP ellipsis, the first stage of a full resolver. It works on free text that has been parsed automatically. Three learners are compared: memory-based learning and two maximum-entropy models (GIS and L-BFGS). The detector reaches 72% F1 on a mixed corpus. Earlier work by Hardt reports 48% F1 for the same task. Using the Penn Treebank with empty-category information, the empty VP feature alone reaches 70% F1, and the full system 82%. Re-parsing the treebank gives 67%, and parsing parts of the BNC gives 71%. Combining the two gives 71–72%. The empty VP feature is the most informative one, and the drop from gold to parsed input is the main loss.

Ideas

• I1. en/src/expert.rs: a rule detector for the trigger. An auxiliary or modal with no verbal complement (no xcomp, ccomp or conjoined verb in the UD tree) is a candidate VPE site. Measure precision and recall on any VPE-annotated set whose licence allows testing.
• I2. Learned detector with the same features: a per-token binary classifier on en features (aux token, tag, next punctuation, sentence position), trained on the training part and scored with en folds. Report F1 by feature group, so that each group can be judged alone.
• I3. Gold against parsed input: report detection F1 on gold trees and on en trees for the same sentences. The gap between the two is the figure that tells the operator how much parser error costs the detector.

For Mova

The code is en/src/expert.rs and en/src/ptag.rs. The chapter is 29. Ellipsis, word order and information structure. The BNC is NC, so any BNC material is for measurement only. Measure first: the rule detector against the gold-tree and parsed-tree gap on a test set we are allowed to use.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.3115/1220355.1220512

@inproceedings{nielsen2004verb,
  title = {{Verb Phrase Ellipsis detection using Automatically Parsed Text}},
  author = {Nielsen, Leif Arda},
  booktitle = {COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics},
  year = {2004},
  doi = {10.3115/1220355.1220512},
  url = {https://doi.org/10.3115/1220355.1220512}
}

References

25 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Eric Brill. 1995. Transformation-based error-driven learning and natural language processing: A case study in part-of-speech tagging. Computational Linguistics, 21(4):543– 565. find
2. E. Briscoe and J. Carroll. 2002. Robust accurate statistical annotation of general text. In Proceedings of the 3rd International Conference on Language Resources and Evaluation, Las Palmas, Gran Canaria. find
3. Aoife Cahill, Mairead McCarthy, Josef van Genabith, and Andy Way. 2002. Evaluating automatic f-structure annotation for the penn-ii treebank. In Proceedings of the First Workshop on Treebanks and Linguistic Theories (TLT 2002), pages 42–60. find
4. Eugene Charniak. 2000. A maximum-entropy-inspired parser. In Meeting of the North American Chapter of the ACL, pages 132–139. find
5. Walter Daelemans, Jakub Zavrel, Ko van der Sloot, and Antal van den Bosch. 2002. Tilburg memory based learner, version 4.3, reference guide. Downloadable from http://ilk.kub.nl/downloads/pub/papers/ilk0210.ps.gz. ↗
6. Mary Dalrymple, Stuart M. Shieber, and Fernando Pereira. 1991. Ellipsis and higher-order unification. Linguistics and Philosophy, 14:399–452. find
7. Robert Fiengo and Robert May. 1994. Indices and Identity. MIT Press, Cambridge, MA. find
8. Daniel Hardt. 1993. VP Ellipsis: Form, Meaning, and Processing. Ph.D. thesis, University of Pennsylvania. find
9. Daniel Hardt. 1997. An empirical approach to vp ellipsis. Computational Linguistics, 23(4). find our card
10. Mark Johnson. 2002. A simple pattern-matching algorithm for recovering empty nodes and their antecedents. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. find
11. Andrew Kehler and Gregory Ward. 1999. On the semantics and pragmatics of ‘identifier so’. In Ken Turner, editor, The Semantics/Pragmatics Interface from Different Points of View (Current Research in the Semantics/Pragmatics Interface Series, Volume I). Amsterdam: Elsevier. find
12. Andrew Kehler. 1993. A discourse copying algorithm for ellipsis and anaphora resolution. In Proceedings of the Sixth Conference of the European Chapter of the Association for Computational Linguistics (EACL-93), Utrecht, the Netherlands. find
13. Torbjorn Lager. 1999. The mu-tbl system: Logic programming tools for transformation-based learning. In Third International Workshop on Computational Natural Language Learning (CoNLL’99). Downloadable from http://www.ling.gu.se/ lager/mutbl.html. ↗
14. Shalom Lappin, I. Golan, and M. Rimon. 1989. Computing grammatical functions from configurational parse trees. Technical Report 88.268, IBM Science and Technology and Scientific Center, Haifa, June. find
15. Shalom Lappin. 1993. The syntactic basis of ellipsis resolution. In S. Berman and A. Hestvik, editors, Proceedings of the Stuttgart Ellipsis Workshop, Arbeitspapiere des Sonderforschungsbereichs 340, Bericht Nr. 29-1992. University of Stuttgart, Stuttgart. find
16. Shalom Lappin. 1996. The interpretation of ellipsis. In Shalom Lappin, editor, The Handbook of Contemporary Semantic Theory, pages 145–175. Oxford: Blackwell. find
17. G. Leech. 1992. 100 million words of english : The British National Corpus. Language Research, 28(1):1–13. find
18. Robert Malouf. 2002. A comparison of algorithms for maximum entropy parameter estimation. In Proceedings of the Sixth Conference on Natural Language Learning (CoNLL-2002), pages 49–55. find
19. M. Marcus, G. Kim, M. Marcinkiewicz, R. MacIntyre, M. Bies, M. Ferguson, K. Katz, and B. Schasberger. 1994. The Penn Treebank: Annotating predicate argument structure. In Proceedings of the Human Language Technology Workshop. Morgan Kaufmann, San Francisco. find our card
20. Leif Arda Nielsen. 2003a. A corpus-based study of verb phrase ellipsis. In Proceedings of the 6th Annual CLUK Research Colloquium, pages 109–115. find
21. Leif Arda Nielsen. 2003b. Using machine learning techniques for VPE detection. In Proceedings of RANLP, pages 339– 346. find
22. Judita Preiss. 2003. Choosing a parser for anaphora resolution. In Proceedings of DAARC, pages 175–180. find
23. R. Quinlan. 1993. C4.5: Programs for Machine Learning. San Mateo, CA: Morgan Kaufmann. find our card
24. Adwait Ratnaparkhi. 1998. Maximum Entropy Models for Natural Language Ambiguity Resolution. Ph.D. thesis, University of Pennsylvania. find
25. Stuart Shieber, Fernando Pereira, and Mary Dalrymple. 1996. Interactions of scope and ellipsis. Linguistics and Philosophy, 19(5):527–552. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2004-nielsen-verb-phrase-ellipsis-detection-automatically/