Prepositional Phrase Attachment without Oracles

What it is about

Most PP attachment work gives the classifier the two candidate heads from gold parse trees, which the authors call an oracle. They remove the oracle and run the Bikel parser instead. In the realistic setting, 45,156 Penn Treebank sentences train the parser and 3,097 sentences serve as the test set. Oracle-based disambiguation reaches 84.14%, against 80.01% without an oracle. The published reattachers that use gold information score 84.18% (Collins and Brooks), 84.60% (Olteanu and Moldovan) and 85.86% (Toutanova, Manning and Ng) on the RRR set. The authors conclude that evaluating PP attachment in isolation gives numbers that are too optimistic for parsing.

Ideas

• I1. en parse-eval: report PP attachment accuracy taken from the predicted tree, not from gold (v, n1, p, n2) tuples, next to LAS on UD EWT test. Count the PP cases the parser misses as a separate number.
• I2. Report three figures for every PP score, as the paper does: missed cases counted as errors, missed cases given the noun attachment, and missed cases discarded. A score that rises only when cases are discarded must not pass the gate.
• I3. en/src/parse.rs: add the head of the PP object as a feature only when the object is a single token that the parser has tagged as a noun. The paper finds noisy head information lowers accuracy. Measure LAS on EWT test with and without the feature.

For Mova

The chapter is 22. Phrases: noun, adjective, adverb and prepositional phrases. The code is en/src/parse.rs and the command en parse-eval. The paper's data is Penn Treebank, so the RRR numbers are test only. Its results are for a Bikel parser and 2007 data; the first Mova measurement must be LAS and attachment accuracy from the en parser on EWT test.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.1162/coli.2007.33.4.469

@article{atterer2007prepositional,
  title = {{Prepositional Phrase Attachment without Oracles}},
  author = {Atterer, Michaela and Schütze, Hinrich},
  journal = {Computational Linguistics},
  year = {2007},
  doi = {10.1162/coli.2007.33.4.469},
  url = {https://doi.org/10.1162/coli.2007.33.4.469}
}

References

20 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Atterer, Michaela and Hinrich Schütze. 2006. The effect of corpus size in combining supervised and unsupervised training for disambiguation. In Proceedings of the Joint Conference of the International Committee on Computational Linguistics and the Association for Computational Linguistics (COLING/… find
2. Bharati, Akshar, U. Rohini, P. Vishnu, Sushma Bendre, and Rajeev Sangal. 2005. A hybrid approach to single and multiple PP attachment using WordNet. In Proceedings of International Joint Conference on Natural Language Processing (IJCNLP) 2005, pages 211–222, Jeju Island, Korea. find
3. Bikel, Daniel M. 2004. Intricacies of Collins parsing model. Computational Linguistics, 30(4):479–512. find
4. Calvo, Hiram, Alexander Gelbukh, and Adam Kilgarriff. 2005. Distributional thesaurus vs. WordNet: A comparison of backoff techniques for unsupervised PP attachment. In Proceedings of the Sixth International Conference on Intelligent Text Processing and Computational Linguistics (CICLing-2005), pages… find
5. Charniak, Eugene and Mark Johnson. 2005. Coarse-to-fine n-best parsing and MaxEnt discriminative reranking. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL), pages 173–180, Ann Arbor, MI. find our card
6. Collins, Michael and James Brooks. 1995. Prepositional phrase attachment through a backed-off model. In Proceedings of the Third Workshop on Very Large Corpora, pages 27–38, Somerset, NJ. find our card
7. Collins, Michael and Terry Koo. 2005. Discriminative reranking for natural language parsing. Computational Linguistics, 31(1):25–70. find our card
8. Foth, Kilian A. and Wolfgang Menzel. 2006. The benefit of stochastic PP attachment to a rule-based parser. In Proceedings of the Joint Conference of the International Committee on Computational Linguistics and the Association for Computational Linguistics (COLING/ACL) 2006 Main Conference Poster Ses… find
9. Hindle, Donald and Mats Rooth. 1993. Structural ambiguity and lexical relations. Computational Linguistics, 19(1):103–120. find
10. Merlo, Paola and Eva Esteve Ferrer. 2006. The notion of argument in prepositional phrase attachment. Computational Linguistics, 32(3):341–378. find our card
11. Mitchell, Brian. 2004. Prepositional Phrase Attachment using Machine Learning Algorithms. Ph.D. thesis, Natural Language Processing Group, Department of Computer Science, University of Sheffield, UK. find
12. Olteanu, Marian and Dan Moldovan. 2005. PP-attachment disambiguation using large context. In Proceedings of Human Language Technology Conference/Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), pages 273–280, Vancouver, Canada. find
13. Olteanu, Marian G. 2004. Prepositional phrase attachment ambiguity resolution through a rich syntactic, lexical and semantic set of features applied in support vector machines learner. Masters thesis, University of Texas, Dallas. find
14. Pantel, Patrick and Dekang Lin. 2000. An unsupervised approach to prepositional phrase attachment using contextually similar words. In Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics (ACL), pages 101–108, Hong Kong, China. find our card
15. Ratnaparkhi, Adwait. 1998. Unsupervised statistical models for prepositional phrase attachment. In Proceedings of International Conference on Computational Linguistics and the Association for Computational Linguistics (COLING-ACL98), pages 1079–1085, Montreal, Canada. find
16. Ratnaparkhi, Adwait, Jeff Reynar, and Salim Roukos. 1994. A maximum entropy model for prepositional phrase attachment. In Workshop on Human Language Technology, pages 250–255, Plainsboro, NJ. find our card
17. Srinivas, Medimi and Pushpak Bhattacharyya. 2007. A flexible unsupervised PP-attachment method using semantic information. In Proceedings of Internationl Joint Conference on Artificial Intelligence (IJCAI 2007), pages 1677–1682, Hyderabad, India. find
18. Stetina, Jiri and Makoto Nagao. 1997. Corpus based PP attachment ambiguity resolution with a semantic dictionary. In Proceedings of the Fifth Workshop on Very Large Corpora, pages 66–80, Hong Kong, China. find
19. Toutanova, Kristina, Christopher D. Manning, and Andrew Y. Ng. 2004. Learning random walk models for inducing word dependency distributions. In Proceedings of the Twenty-first International Conference on Machine Learning (ICML ’04), pages 815–822, Banff, Alberta, Canada. find
20. Volk, Martin. 2006. How bad is the problem of PP-attachment? A comparison of English, German and Swedish. In Proceedings of Association for Computational Linguistics—Special Interest Group on Computational Semantics (ACL-SIGSEM) Workshop on Prepositions, pages 81–88, Trento, Italy. find our card

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/cl-2007-atterer-squibs-prepositional-phrase-attachment-without/