Antecedent Selection for Sluicing: Structure and Content

What it is about

The paper asks which earlier sentence or clause a sluice refers to. It argues that both syntax and discourse matter, and it builds features for the structural relation between the sluice and each candidate, for discourse relations, and for the match between the candidate's content and the wh-type of the sluice. A linear model is trained with hill-climbing on the 4,100 sluices from the New York Times in the Anand and McCloskey (2015) data. The development set has 453 sluices from 1994–95, and the test set 1,732 from 1996–2000, with 10-fold cross-validation. The model reaches 72.4% accuracy, well above strong hand-built baselines. Distance is the strongest single group: 63% of antecedents are in the same sentence as the sluice, and 33% in the sentence before.

Ideas

• I1. en/src/ctx.rs: use the paper's distance feature as the first candidate ranking, since it carries most of the signal. Measure accuracy on a sluice test set whose licence allows testing, against a random candidate baseline.
• I2. wh-type check in en/src/expert.rs: a candidate must match the sluice's wh-type on the content it supplies (for example, "how much" needs a measure, "how" needs a manner clause). Report the error rate per wh-type, as the paper does by sluice type.
• I3. Model comparison on the same features: compare the hill-climbing model with the averaged perceptron of en on the development part only, with en folds. Keep the test set held out until the release check.

For Mova

The code is en/src/ctx.rs, en/src/expert.rs and the perceptron in en/src/parse.rs. The chapter is 29. Ellipsis, word order and information structure. The sluice data is NC, so it is for tests only. Measure first: the distance-only ranking on any sluice set we may test on.

Topics: Discourse analysis · Coreference resolution

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/d16-1131

@inproceedings{anand2016antecedent,
  title = {{Antecedent Selection for Sluicing: Structure and Content}},
  author = {Anand, Pranav and Hardt, Daniel},
  booktitle = {Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing},
  year = {2016},
  doi = {10.18653/v1/d16-1131},
  url = {https://doi.org/10.18653/v1/d16-1131}
}

References

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

1. Pranav Anand and Jim McCloskey. 2015. Annotating the implicit content of sluices. In The 9th Linguistic Annotation Workshop held in conjuncion with NAACL 2015, page 178. find our card
2. Scott AnderBois. 2014. The semantics of sluicing: Beyond truth conditions. Language, 90(4):887–926. find
3. Nicholas Asher. 1993. Reference to Abstract Objects in English. find
4. Dordrecht. Henry Beecher. 2008. Pramatic inference in the interpretation of sluiced Prepositional Phrases. In San Diego Linguistic Papers, volume 3, pages 2–10. Department of Linguistics, UCSD, La Jolla, California. find
5. Eric Bengtson and Dan Roth. 2008. Understanding the value of features for coreference resolution. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 294–303. Association for Computational Linguistics. find
6. Johan Bos and Jennifer Spenader. 2011. An annotated corpus for the analysis of vp ellipsis. Language Resources and Evaluation, 45(4):463–494. find
7. Sara Cantor. 2013. Ungrammatical double-island sluicing as a diagnostic of left-branch positioning. find
8. S. Chung, W. Ladusaw, and J. McCloskey. 1995. Sluicing and logical form. Natural Language Semantics, 3:1–44. find
9. Mary Dalrymple, Stuart Shieber, and Fernando Pereira. 1991. Ellipsis and higher-order unification. Linguistics and Philosophy, 14(4), August. find
10. Pascal Denis and Jason Baldridge. 2008. Specialized models and ranking for coreference resolution. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 660–669. Raquel Fernández, Jonathan Ginzburg, and Shalom Lappin. 2005. Automatic bare sluice disambigua… find
11. Springer. Jonathan Ginzburg and Ivan Sag. 2000. Interrogative Investigations: The Form, Meaning and Use of English Interrogatives. find
12. CSLI Publications, Stanford, Calif. Daniel Hardt and Maribel Romero. 2004. Ellipsis and the structure of discourse. Journal of Semantics, 24(5):375–414. find
13. Daniel Hardt. 1997. An empirical approach to vp ellipsis. Computational Lingusitics, 23(4):525–541. find our card
14. Daniel Hardt. 1999. Dynamic interpretation of verb phrase ellipsis. Linguistics & Philosophy, 22(2):187– 221. find
15. Donald Hindle and Mats Rooth. 1993. Structural ambiguity and lexical relations. Computational linguistics, 19(1):103–120. find
16. Varada Kolhatkar and Graeme Hirst. 2012. Resolving “this-issue” anaphora. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 1255–65. find
17. Varada Kolhatkar, Heike Zinmeister, and Graeme Hirst. 2013. Interpreting anaphoric shell nouns using antecedents of ctaphoric shell nouns as training data. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. find
18. Ken Litowski and Orin Hargraves. 2005. The preposition project. In ACL-SIGSEM Workshop on ”The Linguistic Dimension of Prepositions and Their Use in Computational Linguistic Formalisms and Applications, pages 171–179. find
19. Anne Lobeck. 1995. Ellipsis: Functional heads, licensing and identification. find
20. Oxford University Press. Jason Merchant. 2001. The syntax of silence: Sluicing, islands, and identity in ellipsis. find
21. Oxford. Leif Nielsen. 2005. A Corpus-Based Study of Verb Phrase Ellipsis Identification and Resolution. Ph.D. thesis, King’s College London. find
22. Johanna Nykiel. 2010. Whatever happened to Old English sluicing. In Robert A. Cloutier, Anne Marie Hamilton-Brehm, and Jr. William A. Kretzschmar, editors, Studies in the History of the English Language V: Variation and Change in English Grammar and Lexicon: Contemporary Approaches, pages 37–59. find
23. Walter de Gruyter. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind K Joshi, and Bonnie L Webber. 2008. The penn discourse treebank 2.0. In LREC. Citeseer. Hub Prüst, Remko Scha, and Martin van den Berg. 1994. A discourse perspective on verb phrase anaphora. Linguist… find our card
24. James Pustejovesky, Marc Verhagen, Roser Sauri, Jessica Littman, Robert Gaizauskas, Graham Katz, Inderjeet Mani, Robert Knippen, and Andrea Setzer. 2016. Timebank 1.2. LDC2006T08, April. find
25. Ivan A. Sag. 1976. Deletion and Logical Form. Ph.D. thesis, Massachusetts Institute of Technology. (Published 1980 by Garland Publishing, New York). find
26. W. M. Soon, H.T. Ng, and D. C. Y Lim. 2001. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4):521– 44. find our card

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2016-anand-antecedent-selection-sluicing-structure-content/