The Notion of Argument in Prepositional Phrase Attachment

What it is about

The paper treats PP attachment as a four-way problem: verb or noun site, crossed with argument or adjunct. It learns the argument-adjunct distinction from Penn Treebank data, using features that are lexical items, verb and noun classes, and diagnostics taken from linguistic tests of argumenthood. The best feature set reaches 79.8% accuracy for verb-attached PPs, a 37% reduction of error over the baseline. In the four-way task, arguments have 80% precision and 85% recall, and adjuncts have 80% precision and 73% recall. Attachment-site accuracy is 83.6% without "of", and falls only to 82.7% in the four-way setting. For verb arguments, a support vector machine raises the F-score from 36.0% to 55.9%.

Ideas

• I1. en/src/expert.rs: write the linguistic diagnostics as explicit rules (optionality, iterativity, dependence on the head, order) that label each PP as argument or adjunct and print the rule that fired. Measure accuracy on a hand-checked sample of UD EWT PPs, and the agreement of the rules with the labels they give.
• I2. world/src/frames.rs and onto: map the verb of each PP to its VerbNet class and the PP-internal noun to its WordNet lexicographer file, and feed both as features to the en perceptron in en/src/parse.rs. The paper finds classes more useful than single words; measure LAS and PP accuracy on EWT test.
• I3. Keep the attachment site as step one and the argument label as step two, and report both. Measure how far the two-way attachment accuracy falls on EWT test, as the paper's 83.6% to 82.7% does.

For Mova

The chapters are 23. Complementation and 22-phrases.md. The code is en/src/expert.rs, en/src/parse.rs and world/src/frames.rs. The data is Penn Treebank, so the paper's tables are for test only; the rule set and the class features must be checked on UD EWT test before any claim.

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.1162/coli.2006.32.3.341

@article{merlo2006notion,
  title = {{The Notion of Argument in Prepositional Phrase Attachment}},
  author = {Merlo, Paola and Ferrer, Eva Esteve},
  journal = {Computational Linguistics},
  year = {2006},
  doi = {10.1162/coli.2006.32.3.341},
  url = {https://doi.org/10.1162/coli.2006.32.3.341}
}

References

49 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Aldezabal, Izaskun, Maxux Aranzabe, Koldo Gojenola, Kepa Sarasola, and Aitziber Atutxa. 2002. Learning argument/adjunct distinction for Basque. In Proceedings of the Workshop of the ACL Special Interest Group on the Lexicon on Unsupervised Lexical Acquisition, pages 42–50, Philadelphia, PA. find
2. Argaman, Vered and Neal Pearlmutter. 2002. Lexical semantics as a basis for argument structure frequency bias. In Paola Merlo and Suzanne Stevenson, editors, The Lexical Basis of Sentence Processing: Formal, Computational and Experimental Issues. John Benjamins, Amsterdam/Philadelphia, pages 303–324… find
3. Baker, Collin F., Charles J. Fillmore, and John B. Lowe. 1998. The Berkeley FrameNet project. In Proceedings of the Thirty-sixth Annual Meeting of the Association for Computational Linguistics and Seventeenth International Conference on Computational Linguistics (ACL-COLING’98), pages 86–90, Montrea… find our card
4. Bies, Ann, Mark Ferguson, Karen Katz, and Robert MacIntyre. 1995. Bracketing guidelines for Treebank II style, Penn Treebank Project. Technical report, University of Pennsylvania, Philadephia. find
5. Buchholz, Sabine. 1999. Distinguishing complements from adjuncts using memory-based learning. ILK, Computational Linguistics, Tilburg University. find
6. Chang, Chih-Chung and Chih-Jen Lin. 2001. LIBSVM: A Library for Support Vector Machines. Software available at http://www.csie.ntu.edu.tw/ ∼ cjlin/ libsvm. ↗
7. 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, Cambridge, MA. find our card
8. CoNNL. 2004. Eighth Conference on Computational Natural Language Learning (CoNLL-2004). Boston, MA. find
9. CoNLL. 2005. Ninth Conference on Computational Natural Language Learning (CoNLL-2005). Ann Arbor, MI. find
10. Dorr, Bonnie. 1997. Large-scale dictionary construction for foreign language tutoring and interlingual machine translation. Machine Translation, 12(4):1–55. find
11. Fabre, Cécile and Didier Bourigault. 2001. Linguistic clues for corpus-based acquisition of lexical dependencies. In Proceedings of the Corpus Linguistics Conference, pages 176–184, Lancaster, UK. find
12. Gildea, Daniel and Daniel Jurafsky. 2002. Automatic labeling of semantic roles. Computational Linguistics, 28(3):245–288. find our card
13. Grimshaw, Jane. 1990. Argument Structure. MIT Press. find
14. Hindle, Donald and Mats Rooth. 1993. Structural ambiguity and lexical relations. Computational Linguistics, 19(1):103–120. find
15. Jackendoff, Ray. 1977. X  Syntax: A Study of Phrase Structure. MIT Press, Cambridge, MA. find
16. Korhonen, Anna. 2002a. Semantically motivated subcategorization acquisition. In Proceedings of the Workshop of the ACL Special Interest Group on the Lexicon on Unsupervised Lexical Acquisition, pages 51–58, Philadelphia, PA, July. find
17. Korhonen, Anna. 2002b. Subcategorisation Acquisition. Ph.D. thesis, University of Cambridge. find
18. Levin, Beth. 1993. English Verb Classes and Alternations. University of Chicago Press, Chicago, IL. find
19. Manning, Christopher. 2003. Probabilistic syntax. In Rens Bod, Jennifer Hay, and Stephanie Jannedy, editors, Probabilistic Linguistics. MIT Press, pages 289–314. find
20. Marantz, Alex. 1984. On the Nature of Grammatical Relations. MIT Press, Cambridge, MA. find
21. Marcus, M., G. Kim, A. Marcinkiewicz, R. Macintyre, A. Bies, M. Ferguson, K. Katz, and B. Schasberger. 1994. The Penn Treebank: Annotating predicate argument structure. In Proceedings of the ARPA Workshop on Human Language Technology, pages 114–119, Plainsboro, NJ. find our card
22. Marcus, Mitch, Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19:313–330. find our card
23. Merlo, Paola. 2003. Generalised PP-attachment disambiguation using corpus-based linguistic diagnostics. find
24. In Proceedings of the Tenth Conference of the European Chapter of the Association for Computational Linguistics (EACL’03), pages 251–258, Budapest, Hungary. find
25. Merlo, Paola, Matt Crocker, and Cathy Berthouzoz. 1997. Attaching multiple prepositional phrases: Generalized backed-off estimation. In Proceedings of the Second Conference on Empirical Methods in Natural Language Processing, pages 145–154, Providence, RI. find
26. Merlo, Paola and Matthias Leybold. 2001. Automatic distinction of arguments and modifiers: The case of prepositional phrases. In Proceedings of the Fifth Computational Natural Language Learning Workshop (CoNLL-2001), pages 121–128, Toulouse, France. find
27. Merlo, Paola and Suzanne Stevenson. 2001. Automatic verb classification based on statistical distributions of argument structure. Computational Linguistics, 27(3):373–408. find
28. Miller, George, Richard Beckwith, Christiane Fellbaum, Derek Gross, and Katherine Miller. 1990. Five papers on Wordnet. Technical report, Cognitive Science Laboratory, Princeton University. find
29. Nielsen, Rodney and Sameer Pradhan. 2004. Mixing weak learners in semantic parsing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-2004), pages 80–87, Barcelona, Spain, July. find
30. Palmer, Martha, Daniel Gildea, and Paul Kingsbury. 2005. The Proposition Bank: An annotated corpus of semantic roles. Computational Linguistics, 31:71–105. find our card
31. Phillips, William and Ellen Riloff. 2002. Exploiting strong syntactic heuristics and co-training to learn semantic lexicons. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002), pages 125–132, Philadelphia, PA. find
32. Pollard, Carl and Ivan Sag. 1987. An Information-based Syntax and Semantics, volume 13. CSLI Lecture Notes, Stanford University. find
33. Quinlan, J. Ross. 1993. C4.5 : Programs for Machine Learning. Series in Machine Learning. Morgan Kaufmann, San Mateo, CA. find our card
34. Quirk, Randolph, Sidney Greenbaum, Geoffrey Leech, and Jan Svartvik. 1985. A Comprehensive Grammar of the English Language. Longman, London. find
35. Ratnaparkhi, Adwait. 1997. A linear observed time statistical parser based on maximum entropy models. In Proceedings of the Second Conference on Empirical Methods in Natural Language Processing, pages 1–10, Providence, RI. find
36. Ratnaparkhi, Adwait, Jeffrey Reynar, and Salim Roukos. 1994. A maximum entropy model for prepositional phrase attachment. In Proceedings of the ARPA Workshop on Human Language Technology, pages 250–255, Plainsboro, NJ. find our card
37. Riloff, Ellen and Mark Schmelzenbach. 1998. An empirical approach to conceptual case frame acquisition. In Proceedings of the Sixth Workshop on Very Large Corpora, pages 49–56, Montreal. find
38. Schütze, Carson T. 1995. PP Attachment and Argumenthood. MIT Working Papers in Linguistics, 26:95–151. find
39. SENSEVAL-3. 2004. Third International Workshop on the Evaluation of Systems for the Semantic Analysis of Text (SENSEVAL-3). Barcelona, Spain. find
40. Srinivas, Bangalore and Aravind K. Joshi. 1999. Supertagging: An approach to almost parsing. Computational Linguistics, 25(2):237–265. find
41. Stede, Manfred. 1998. A generative perspective on verb alternations. Computational Linguistics, 24(3):401–430. find
42. 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, Beijing/ Hong Kong. find
43. Swier, Robert and Suzanne Stevenson. 2005. Exploiting a verb lexicon in automatic semantic role labelling. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-05), pages 883–890, Vancouver, Canada. find
44. Vapnik, V. 1995. The Nature of Statistical Learning Theory. Springer. find
45. Villavicencio, Aline. 2002. Learning to distinguish PP arguments from adjuncts. In Proceedings of the 6th Conference on Natural Language Learning (CoNLL-2002), pages 84–90, Taipei, Taiwan. find
46. Xue, Nianwen. 2004. Handling dislocated and discontinuous constituents in Chinese semantic role labelling. In Proceedings of the Fourth Workshop on Asian Language Resources (ALR04), pages 19–26, Hainan Island, China. find
47. Xue, Nianwen and Martha Palmer. 2004. Calibrating features for semantic role labeling. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP-2004), pages 88–94, Barcelona, Spain. find
48. Yeh, Alexander. 2000. More accurate tests for the statistical significance of result differences. In Proceedings of the 18th International Conference in Computational Linguistics (COLING 2000), pages 947–953, Saarbruecken, Germany. find
49. Zhao, Shaojun and Dekang Lin. 2004. A nearest-neighbor method for resolving PP-attachment ambiguities. In The First International Joint Conference on Natural Language Processing (IJCNLP-04), pages 545–554, Hainan Island, China. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/cl-2006-merlo-notion-argument-prepositional-phrase-attachment/