Identifying non-compositional idioms in text using WordNet synsets. Baron, F. Master's thesis, Department of Computer Science, University of Toronto, 2007. abstract bibtex Any natural language processing system that does not have a knowledge of non-compositional idioms and their interpretation will make mistakes. Previous authors have attempted to automatically identify these expressions through the property of non-substitutability: similar words cannot be successfully substituted for words in non-compositional idiom expressions without changing their meaning.
In this study, we use the non-substitutability property of idioms to contrast and expand the ideas of previous works, drawing on WordNet for the attempted substitutions. We attempt to determine the best way to automatically identify idioms through the comparison of algorithms including frequency counts, pointwise mutual information and PMI ranges; the evaluation of the importance of relative word position; and the assessment of the usefulness of syntactic relations. We discover that many of the techniques which we try are not useful for identifying idioms and confirm that non-compositionality doesn't appear to be a necessary or sufficient condition for idiomaticity.
@MastersThesis{ baron2,
author = {Faye Baron},
title = {{Identifying non-compositional idioms in text using
WordNet synsets}},
year = {2007},
school = {Department of Computer Science, University of Toronto},
abstract = {<p>Any natural language processing system that does not
have a knowledge of non-compositional idioms and their
interpretation will make mistakes. Previous authors have
attempted to automatically identify these expressions
through the property of non-substitutability: similar words
cannot be successfully substituted for words in
non-compositional idiom expressions without changing their
meaning.</p> <p>In this study, we use the
non-substitutability property of idioms to contrast and
expand the ideas of previous works, drawing on WordNet for
the attempted substitutions. We attempt to determine the
best way to automatically identify idioms through the
comparison of algorithms including frequency counts,
pointwise mutual information and PMI ranges; the evaluation
of the importance of relative word position; and the
assessment of the usefulness of syntactic relations. We
discover that many of the techniques which we try are not
useful for identifying idioms and confirm that
non-compositionality doesn't appear to be a necessary or
sufficient condition for idiomaticity. </p> },
download = {http://ftp.cs.toronto.edu/pub/gh/Baron-thesis.pdf}
}
Downloads: 0
{"_id":{"_str":"534282740e946d920a001aa8"},"__v":4,"authorIDs":["546c1bc7ec3c47a51800052f"],"author_short":["Baron, F."],"bibbaseid":"baron-identifyingnoncompositionalidiomsintextusingwordnetsynsets-2007","bibdata":{"bibtype":"mastersthesis","type":"mastersthesis","author":[{"firstnames":["Faye"],"propositions":[],"lastnames":["Baron"],"suffixes":[]}],"title":"Identifying non-compositional idioms in text using WordNet synsets","year":"2007","school":"Department of Computer Science, University of Toronto","abstract":"<p>Any natural language processing system that does not have a knowledge of non-compositional idioms and their interpretation will make mistakes. Previous authors have attempted to automatically identify these expressions through the property of non-substitutability: similar words cannot be successfully substituted for words in non-compositional idiom expressions without changing their meaning.</p> <p>In this study, we use the non-substitutability property of idioms to contrast and expand the ideas of previous works, drawing on WordNet for the attempted substitutions. We attempt to determine the best way to automatically identify idioms through the comparison of algorithms including frequency counts, pointwise mutual information and PMI ranges; the evaluation of the importance of relative word position; and the assessment of the usefulness of syntactic relations. We discover that many of the techniques which we try are not useful for identifying idioms and confirm that non-compositionality doesn't appear to be a necessary or sufficient condition for idiomaticity. </p> ","download":"http://ftp.cs.toronto.edu/pub/gh/Baron-thesis.pdf","bibtex":"@MastersThesis{\t baron2,\n author\t= {Faye Baron},\n title\t\t= {{Identifying non-compositional idioms in text using\n\t\t WordNet synsets}},\n year\t\t= {2007},\n school\t= {Department of Computer Science, University of Toronto},\n abstract\t= {<p>Any natural language processing system that does not\n\t\t have a knowledge of non-compositional idioms and their\n\t\t interpretation will make mistakes. Previous authors have\n\t\t attempted to automatically identify these expressions\n\t\t through the property of non-substitutability: similar words\n\t\t cannot be successfully substituted for words in\n\t\t non-compositional idiom expressions without changing their\n\t\t meaning.</p> <p>In this study, we use the\n\t\t non-substitutability property of idioms to contrast and\n\t\t expand the ideas of previous works, drawing on WordNet for\n\t\t the attempted substitutions. We attempt to determine the\n\t\t best way to automatically identify idioms through the\n\t\t comparison of algorithms including frequency counts,\n\t\t pointwise mutual information and PMI ranges; the evaluation\n\t\t of the importance of relative word position; and the\n\t\t assessment of the usefulness of syntactic relations. We\n\t\t discover that many of the techniques which we try are not\n\t\t useful for identifying idioms and confirm that\n\t\t non-compositionality doesn't appear to be a necessary or\n\t\t sufficient condition for idiomaticity. </p> },\n download\t= {http://ftp.cs.toronto.edu/pub/gh/Baron-thesis.pdf}\n}\n\n","author_short":["Baron, F."],"key":"baron2","id":"baron2","bibbaseid":"baron-identifyingnoncompositionalidiomsintextusingwordnetsynsets-2007","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"mastersthesis","biburl":"www.cs.toronto.edu/~fritz/tmp/compling.bib","downloads":0,"keywords":[],"search_terms":["identifying","non","compositional","idioms","text","using","wordnet","synsets","baron"],"title":"Identifying non-compositional idioms in text using WordNet synsets","year":2007,"dataSources":["n8jB5BJxaeSmH6mtR","6b6A9kbkw4CsEGnRX"]}