Automatically Classifying English Verb-Particle Constructions by Particle Semantics. Cook, P. Master's thesis, Department of Computer Science, University of Toronto, August, 2006. abstract bibtex We address the issue of automatically determining the semantic contribution of the particle in a verb-particle construction (VPC), a task which has been previously ignored in computational work on VPCs. Adopting a cognitive linguistic standpoint, we assume that every VPC is compositional, and that the semantic contribution of a particle corresponds to one of a small number of senses. We develop a feature space based on syntactic and semantic properties of verbs and VPCs for type classification of English VPCs according to the sense contributed by their particle. We focus on VPCs using the particle up since it is very frequent and exhibits a wide range of meanings. In our experiments on unseen test VPCs, features which are motivated by properties specific to verbs and VPCs outperform linguistically uninformed word co-occurrence features, and give a reduction in error rate of around 20-30% over a chance baseline.
@MastersThesis{ cook1,
author = {Paul Cook},
title = {Automatically Classifying English Verb-Particle
Constructions by Particle Semantics},
school = {Department of Computer Science, University of Toronto},
month = {August},
year = {2006},
abstract = {We address the issue of automatically determining the
semantic contribution of the particle in a verb-particle
construction (VPC), a task which has been previously
ignored in computational work on VPCs. Adopting a cognitive
linguistic standpoint, we assume that every VPC is
compositional, and that the semantic contribution of a
particle corresponds to one of a small number of senses. We
develop a feature space based on syntactic and semantic
properties of verbs and VPCs for type classification of
English VPCs according to the sense contributed by their
particle. We focus on VPCs using the particle <i>up</i>
since it is very frequent and exhibits a wide range of
meanings. In our experiments on unseen test VPCs, features
which are motivated by properties specific to verbs and
VPCs outperform linguistically uninformed word
co-occurrence features, and give a reduction in error rate
of around 20-30% over a chance baseline.},
download = {http://www.cs.toronto.edu/~pcook/Cook2006.pdf}
}
Downloads: 0
{"_id":{"_str":"534282740e946d920a001b58"},"__v":4,"authorIDs":["546934bfbc7d6a460d001214"],"author_short":["Cook, P."],"bibbaseid":"cook-automaticallyclassifyingenglishverbparticleconstructionsbyparticlesemantics-2006","bibdata":{"bibtype":"mastersthesis","type":"mastersthesis","author":[{"firstnames":["Paul"],"propositions":[],"lastnames":["Cook"],"suffixes":[]}],"title":"Automatically Classifying English Verb-Particle Constructions by Particle Semantics","school":"Department of Computer Science, University of Toronto","month":"August","year":"2006","abstract":"We address the issue of automatically determining the semantic contribution of the particle in a verb-particle construction (VPC), a task which has been previously ignored in computational work on VPCs. Adopting a cognitive linguistic standpoint, we assume that every VPC is compositional, and that the semantic contribution of a particle corresponds to one of a small number of senses. We develop a feature space based on syntactic and semantic properties of verbs and VPCs for type classification of English VPCs according to the sense contributed by their particle. We focus on VPCs using the particle <i>up</i> since it is very frequent and exhibits a wide range of meanings. In our experiments on unseen test VPCs, features which are motivated by properties specific to verbs and VPCs outperform linguistically uninformed word co-occurrence features, and give a reduction in error rate of around 20-30% over a chance baseline.","download":"http://www.cs.toronto.edu/~pcook/Cook2006.pdf","bibtex":"@MastersThesis{\t cook1,\n author\t= {Paul Cook},\n title\t\t= {Automatically Classifying English Verb-Particle\n\t\t Constructions by Particle Semantics},\n school\t= {Department of Computer Science, University of Toronto},\n month\t\t= {August},\n year\t\t= {2006},\n abstract\t= {We address the issue of automatically determining the\n\t\t semantic contribution of the particle in a verb-particle\n\t\t construction (VPC), a task which has been previously\n\t\t ignored in computational work on VPCs. Adopting a cognitive\n\t\t linguistic standpoint, we assume that every VPC is\n\t\t compositional, and that the semantic contribution of a\n\t\t particle corresponds to one of a small number of senses. We\n\t\t develop a feature space based on syntactic and semantic\n\t\t properties of verbs and VPCs for type classification of\n\t\t English VPCs according to the sense contributed by their\n\t\t particle. We focus on VPCs using the particle <i>up</i>\n\t\t since it is very frequent and exhibits a wide range of\n\t\t meanings. In our experiments on unseen test VPCs, features\n\t\t which are motivated by properties specific to verbs and\n\t\t VPCs outperform linguistically uninformed word\n\t\t co-occurrence features, and give a reduction in error rate\n\t\t of around 20-30% over a chance baseline.},\n download\t= {http://www.cs.toronto.edu/~pcook/Cook2006.pdf}\n}\n\n","author_short":["Cook, P."],"key":"cook1","id":"cook1","bibbaseid":"cook-automaticallyclassifyingenglishverbparticleconstructionsbyparticlesemantics-2006","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"mastersthesis","biburl":"www.cs.toronto.edu/~fritz/tmp/compling.bib","downloads":0,"keywords":[],"search_terms":["automatically","classifying","english","verb","particle","constructions","particle","semantics","cook"],"title":"Automatically Classifying English Verb-Particle Constructions by Particle Semantics","year":2006,"dataSources":["n8jB5BJxaeSmH6mtR","6b6A9kbkw4CsEGnRX"]}