NooJ 2016: Automatic Processing of Natural-Language Electronic Texts with NooJ pp 169-181 | Cite as
Phrasal Verb Disambiguation Grammars: Cutting Out Noise Automatically
Abstract
Previous research [1, 2] showed how NooJ could automatically annotate English Phrasal Verbs (PV), both continuous and discontinuous, in large corpora. Due to certain restrictions, however, not all discontinuous PV listed in the PV Dictionary were successfully identified in texts. Further research [3] showed how a simplified PV grammar could identify more PV and improve recall, but it created an excessive amount of noise. Some of it could be automatically removed with disambiguation grammars, yet accuracy was still limited to 70–74%. In this article we show how incorporating additional dictionaries and disambiguation grammars – modifying them with unique NooJ functionalities such as +EXCLUDE and +UNAMB – can allow us to remove even more noise and achieve a better overall accuracy of 88%.
Keywords
NooJ Natural Language Processing Multiword expressions English Phrasal Verbs Particles Prepositions Disambiguation Historical Linguistics Dickens MelvilleReferences
- 1.Machonis, P.A.: NooJ: a practical method for parsing phrasal verbs. In: Blanco, X., Silberztein, M. (eds.) Proceedings of the 2007 International NooJ Conference, pp. 149–161. Cambridge Scholars Publishing, Newcastle upon Tyne (2008)Google Scholar
- 2.Machonis, P.A.: English phrasal verbs: from lexicon-grammar to natural language processing. South. J. Linguist. 34(1), 21–48 (2010)Google Scholar
- 3.Machonis, P.A.: Sorting NooJ out to take multiword expressions into account. In: Vučković, K., Bekavac, B., Silberztein, M. (eds.) Automatic Processing of Various Levels of Linguistic Phenomena: Selected Papers from the NooJ 2011 International Conference, pp. 152–165. Cambridge Scholars Publishing, Newcastle upon Tyne (2012)Google Scholar
- 4.Talmy, L.: Lexicalization patterns: semantic structure. In: Shopen, T. (ed.) Lexical Forms in Language Typology and Syntactic Description, pp. 57–149. Cambridge University Press, New York (1985)Google Scholar
- 5.Silberztein, M.: Formalizing Natural Languages: The NooJ Approach. Wiley ISTE, London (2016)CrossRefGoogle Scholar
- 6.Machonis, P.A.: Support verbs: an analysis of be prep X idioms. SECOL Rev. 12(2), 95–125 (1988)Google Scholar
- 7.Giannasi, R.: Expressions figées: be Prep X en anglais américain. M.A. thesis. Mémoires du CERIL 7, pp. 117–202. Université Paris 7, Paris (1990)Google Scholar
- 8.Silberztein, M.: Syntactic parsing with NooJ. In: Ben Hamadou, A., Mesfar, S., Silberztein, M. (eds.) NooJ 2009 International Conference and Workshop on Finite State Language Engineering, pp. 177–189. Centre de Publication Universitaire, Sfax (2010)Google Scholar
- 9.Kennedy, A.G.: The Modern English Verb-Adverb Combination. Stanford University Press, Stanford (1920)Google Scholar
- 10.Thim, S.: The English Verb-Particle Construction and its History. De Gruyter Mouton, Berlin (2012)Google Scholar