Differentiating Types of Verb Particle Constructions

What it is about

The paper takes a verb-particle construction (VPC) scheme from linguistic sources and asks whether it separates the meanings of phrasal verbs in context. The scheme has three classes: decomposable (about 44% of the data), non-decomposable (about 36%) and independent (about 19%). The data is a British National Corpus subset of about 6,000 sentences from roughly 70 verb-particle pairs, plus 400 sentences that a first classifier got wrong and that the authors tagged by hand. Features come from the sentence: the particle, the verb-particle distance, the tags of the surrounding noun phrases, and the verb's syllable count. The majority-class baseline is F 0.613 on the combined set, and the feature experiments are compared against it step by step. The paper also reports particle-tag F scores of 0.969, 0.990 and 0.833 for the three CLAWS adverb and preposition tags.

Ideas

• I1. Particle sense as a rule in en/src/expert.rs: separate adverbial from prepositional particles by the distance to the object and by the noun-phrase head tags. Measure: label accuracy on EWT test verb-particle cases, against the current en/src/ptag.rs tags, with two identical runs.
• I2. Use verb-particle distance as a feature in en/src/parse.rs when it decides between compound:prt and case for a particle. Measure: LAS on EWT test sentences with a particle, with and without the feature.
• I3. Test the syllable and Germanic-origin idea only as a probe: count how often a monosyllabic verb predicts the non-decomposable class in the BNC subset. Measure before anything enters the grammar. The data are NC, so the probe is test only.

For Mova

The chapter is languages/en/28-voice-and-passive.md only for particle objects; the main home is languages/en/23-complementation.md and languages/en/13-verbs.md. The code is en/src/expert.rs and en/src/parse.rs. The BNC subset is NC, so use it for tests only; numbers must come from EWT test.

Cite

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

@inproceedings{patrick2004differentiating,
  title = {{Differentiating Types of Verb Particle Constructions}},
  author = {Patrick, Jon and Fletcher, Jeremy},
  booktitle = {Proceedings of the Australasian Language Technology Workshop 2004},
  year = {2004},
  url = {https://aclanthology.org/U04-1022/}
}

References

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

1. Abeillé, A. 1988. Light verb constructions and extraction out of NP in a tree adjoining grammar. In Papers of the 24th Regional Meeting of the Chicago Ling. Soc. find
2. Abeillé, A. 1995. The flexibility of French idioms: A representation with Lexicalised Tree Adjoining Grammar. In M. Everaert, E-J. van der Linden, A. Schenk, and R. Schreuder, editors, Idioms: Structural and Psychological Perspectives, chapter 1. Lawrence Erlbaum Associates. find
3. Baldwin, T. and Villavicencio, A. 2002. Extracting the Unextractable: A case study on verb-particles. In Proc. of the 6 th Conference on Natural Language Learning (CoNLL-2002), Taipei, Taiwan Bannard, C., Baldwin, T. and Lascarides, A.. 2003. A Statistical Approach to the Semantics of Verb-Particles… find
4. Bannard, C. 2002. Statistical techniques for automatically inferring the semantics of verb-particle constructions. LinGO Working Paper No. 2002-06. find
5. Barkema, H. 1994. The idiomatic, syntactic and collocational characteristics of received NPs: some basic statistics. Hermes 13: 19-40. Aarhus School of Business. find
6. Basili, R., Pazienza, M. and Velardi, P. 1993. Semi-automatic extraction of linguistic information for syntactic disambiguation. Applied Artificial Intelligence, 7:339-64. find
7. Blaheta, D. and Johnson, M. 2001. Unsupervised learning of multi-word verbs. In Proc. of the ACL/EACL 2001 Workshop on the Computational Extraction, Analysis and Exploitation of Collocations, pp 54-60. find
8. Brill, E. 1995. “Transformation-based error-driven learning and natural language processing: A case study in part-of-speech tagging”, Computational Linguistics. 21:543-65. find our card
9. Calzolari, N., Fillmore, C., Grishman, R., Ide, N., Lencu, A., MacLeod, C. and Zampolli, A. 2002. Towards best practice for multiword expressions in computational lexicons. In Proc. of the 3 rd International Conference on Language Resources and Evaluation (LREC 2002), pp 1934-40 find
10. Copestake, A., Lambeau, F., Villavicencio, A., Bond, F., Baldwin, T., Sag, I.A. and Flickinger, D. 2002. Multiword expressions: linguistic precision and reusability. In Proc. Third conference on Language Resources and Evaluation (LREC-2002), pp. 1941— 1947. Las Palmas, Canary Islands. find our card
11. Dixon, R. M. W. 1982. The Grammar of English Phrasal Verbs. Australian Journal of Linguistics, 2:149-247. find
12. Kaalep, K. and Muischnek, K. 2002. Using the text corpus to create a comprehensive list of phrasal verbs. In Proc. of the 3 rd International conference on Language Resources and Evaluation (LREC 2002), pp 101-5. find
13. Krenn, B. and Evert, S. 2001. Can we do better than frequency? A case study on extracting PP-verb collocations. In Proceedings of the ACL Workshop on Collocations, Toulouse, France, pp 39-46. find
14. Krovetz, R. and Croft, W.B. 1989. Word sense disambiguation using machine-readable dictionaries. In Proc. Annual ACM Conference on Research and Development in Information Retrieval 1989. find
15. Lin, D. 1999. Automatic Identification of Non-compositional Phrases. In Proc. 37 th Annual Meeting of the ACL, pp 317-24. find
16. Lindstromberg, S. 1998. English Prepositions Explained. Amsterdam: John Benjamins. find
17. Maynard, D. and Ananiadou, S. 1999. Identifying contextual information for multi-word term extraction. In 5th International Congress on Terminology and Knowledge Engineering (TKE 99), pp 212-21. find
18. Maynard, D. and Ananiadou, S. 1998. Acquiring contextual information for term disambiguation. In Proc. of 1 st Workshop Computational Terminology, Computerm ’98, Montreal, Canada. find
19. Meyer, G. A. 1975. The Two-Word Verb, A Dictionary of the Verb-Prepositional Phrases in American English. The Hague: Mouton. find
20. Patrick, J., Palko, D., Munro, R., Zappavigna, M. 2003. Inferring semantic structure from format, Computing Arts: Digital Resources in the Humanities, (ed) C. Cole & H. Craig, Sydney: The Uni of Sydney, pp150-168. find
21. McCarthy, D., Keller, B., Carroll, J. 2003, Detecting a Continuum of Compositionality in Phrasal Verbs. In Proceedings of the ACL-2003 Workshop on Multiword Expressions: Analysis, Acquisition and Treatment, Sapporo, Japan, pp. 65-72. find
22. Miller, G.A., Beckwith, R., Fellcaum, C., Gross, D. and Miller, K.J. 1990. Introduction to WordNet: an online lexical database. International Journal of Lexicography, 3(4):235-44. find
23. O’Hara, T and Wiebe J. 2003. Preposition Semantic Classification via P ENN T REEBANK and F RAME N ET . In Proc. of Computational Natural Language Learning-2003 (CoNLL-03). find
24. Sag, I.A., Baldwin, T., Bond, F., Copestake, A. and Flickinger, D. 2002. Multiword expressions: A pain in the neck for NLP. In Proc. of the 3rd International Conference on Intelligent Text Processing and Computational Linguistics (CICLing-2002), pp 1-15, Mexico City, Mexico. find our card
25. Smadja, F. 1993. Retrieving collocations from text: Xtract. In Computational Linguistics, 19(1):143-78. find our card
26. Wehrli, E. 1998. Translating idioms. In Proc. of the 36th Annual Meeting of the ACL and 17th International Conference on Computational Linguistics: COLING/ACL-98, pp 1388-92, Montreal, Canada. find
27. Yarowsky, D. 1992. Word-Sense Disambiguation Using Statistical Models of Roget’s Categories Trained on Large Corpora. In Proceedings, COLING-92. pp 454-460. find
28. Yarowsky, D. 1995. Unsupervised Word Sense Disambiguation Rivalling Supervised Methods. Proc 33rd Ann. Meet.of the ACL. find