Automatic acquisition of knowledge about multiword predicates. Fazly, A. & Stevenson, S. In Proceedings of the 19th Pacific Asia Conference on Language, Information, and Computation (PACLIC), Taipei, Taiwan, December, 2005. overview paper for an invited talk by Suzanne Stevensonabstract bibtex Human interpretation of natural language relies heavily on cognitive processes involving metaphorical and idiomatic meanings. One area of computational linguistics in which such processes play an important, but largely unaddressed, role is the determination of the properties of multiword predicates (MWPs). MWPs such as give a groan and cut taxes involve metaphorical meaning extensions of highly frequent, and highly polysemous, verbs. Tools for automatically identifying such MWPs, and extracting their lexical and syntactic properties, are crucial to the adequate treatment of text in a computational system, due to the productive nature of MWPs across many languages. This paper gives an overview of our work addressing these issues. We begin by relating linguistic properties of metaphorical uses of verbs to their distributional properties. We devise automatic methods for assessing whether a verb phrase is literal, metaphorical, or idiomatic. Since metaphorical MWPs are generally semi-productive, we also develop computational measures of their individual acceptability and of their productivity over semantically related combinations. Our results demonstrate that combining statistical approaches with linguistic information is beneficial, both for the acquisition of knowledge about metaphorical and idiomatic MWPs, and for the organization of such knowledge in a computational lexicon.
@InProceedings{ fazly3,
author = {Afsaneh Fazly and Suzanne Stevenson},
title = {Automatic acquisition of knowledge about multiword
predicates},
note = {overview paper for an invited talk by Suzanne Stevenson},
booktitle = {Proceedings of the 19th Pacific Asia Conference on
Language, Information, and Computation (PACLIC)},
address = {Taipei, Taiwan},
month = {December},
year = {2005},
abstract = {Human interpretation of natural language relies heavily on
cognitive processes involving metaphorical and idiomatic
meanings. One area of computational linguistics in which
such processes play an important, but largely unaddressed,
role is the determination of the properties of multiword
predicates (MWPs). MWPs such as <I>give a groan</I> and
<I>cut taxes</I> involve metaphorical meaning extensions of
highly frequent, and highly polysemous, verbs. Tools for
automatically identifying such MWPs, and extracting their
lexical and syntactic properties, are crucial to the
adequate treatment of text in a computational system, due
to the productive nature of MWPs across many languages.
This paper gives an overview of our work addressing these
issues. We begin by relating linguistic properties of
metaphorical uses of verbs to their distributional
properties. We devise automatic methods for assessing
whether a verb phrase is literal, metaphorical, or
idiomatic. Since metaphorical MWPs are generally
semi-productive, we also develop computational measures of
their individual acceptability and of their productivity
over semantically related combinations. Our results
demonstrate that combining statistical approaches with
linguistic information is beneficial, both for the
acquisition of knowledge about metaphorical and idiomatic
MWPs, and for the organization of such knowledge in a
computational lexicon.},
download = {http://ftp.cs.toronto.edu/pub/gh/Fazly+Stevenson-2005.pdf}
}
Downloads: 0
{"_id":{"_str":"534282740e946d920a001b21"},"__v":5,"authorIDs":["5457f20a2abc8e9f370008f4","54598175b43425b772000634"],"author_short":["Fazly, A.","Stevenson, S."],"bibbaseid":"fazly-stevenson-automaticacquisitionofknowledgeaboutmultiwordpredicates-2005","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Afsaneh"],"propositions":[],"lastnames":["Fazly"],"suffixes":[]},{"firstnames":["Suzanne"],"propositions":[],"lastnames":["Stevenson"],"suffixes":[]}],"title":"Automatic acquisition of knowledge about multiword predicates","note":"overview paper for an invited talk by Suzanne Stevenson","booktitle":"Proceedings of the 19th Pacific Asia Conference on Language, Information, and Computation (PACLIC)","address":"Taipei, Taiwan","month":"December","year":"2005","abstract":"Human interpretation of natural language relies heavily on cognitive processes involving metaphorical and idiomatic meanings. One area of computational linguistics in which such processes play an important, but largely unaddressed, role is the determination of the properties of multiword predicates (MWPs). MWPs such as <I>give a groan</I> and <I>cut taxes</I> involve metaphorical meaning extensions of highly frequent, and highly polysemous, verbs. Tools for automatically identifying such MWPs, and extracting their lexical and syntactic properties, are crucial to the adequate treatment of text in a computational system, due to the productive nature of MWPs across many languages. This paper gives an overview of our work addressing these issues. We begin by relating linguistic properties of metaphorical uses of verbs to their distributional properties. We devise automatic methods for assessing whether a verb phrase is literal, metaphorical, or idiomatic. Since metaphorical MWPs are generally semi-productive, we also develop computational measures of their individual acceptability and of their productivity over semantically related combinations. Our results demonstrate that combining statistical approaches with linguistic information is beneficial, both for the acquisition of knowledge about metaphorical and idiomatic MWPs, and for the organization of such knowledge in a computational lexicon.","download":"http://ftp.cs.toronto.edu/pub/gh/Fazly+Stevenson-2005.pdf","bibtex":"@InProceedings{\t fazly3,\n author\t= {Afsaneh Fazly and Suzanne Stevenson},\n title\t\t= {Automatic acquisition of knowledge about multiword\n\t\t predicates},\n note\t\t= {overview paper for an invited talk by Suzanne Stevenson},\n booktitle\t= {Proceedings of the 19th Pacific Asia Conference on\n\t\t Language, Information, and Computation (PACLIC)},\n address\t= {Taipei, Taiwan},\n month\t\t= {December},\n year\t\t= {2005},\n abstract\t= {Human interpretation of natural language relies heavily on\n\t\t cognitive processes involving metaphorical and idiomatic\n\t\t meanings. One area of computational linguistics in which\n\t\t such processes play an important, but largely unaddressed,\n\t\t role is the determination of the properties of multiword\n\t\t predicates (MWPs). MWPs such as <I>give a groan</I> and\n\t\t <I>cut taxes</I> involve metaphorical meaning extensions of\n\t\t highly frequent, and highly polysemous, verbs. Tools for\n\t\t automatically identifying such MWPs, and extracting their\n\t\t lexical and syntactic properties, are crucial to the\n\t\t adequate treatment of text in a computational system, due\n\t\t to the productive nature of MWPs across many languages.\n\t\t This paper gives an overview of our work addressing these\n\t\t issues. We begin by relating linguistic properties of\n\t\t metaphorical uses of verbs to their distributional\n\t\t properties. We devise automatic methods for assessing\n\t\t whether a verb phrase is literal, metaphorical, or\n\t\t idiomatic. Since metaphorical MWPs are generally\n\t\t semi-productive, we also develop computational measures of\n\t\t their individual acceptability and of their productivity\n\t\t over semantically related combinations. Our results\n\t\t demonstrate that combining statistical approaches with\n\t\t linguistic information is beneficial, both for the\n\t\t acquisition of knowledge about metaphorical and idiomatic\n\t\t MWPs, and for the organization of such knowledge in a\n\t\t computational lexicon.},\n download\t= {http://ftp.cs.toronto.edu/pub/gh/Fazly+Stevenson-2005.pdf}\n}\n\n","author_short":["Fazly, A.","Stevenson, S."],"key":"fazly3","id":"fazly3","bibbaseid":"fazly-stevenson-automaticacquisitionofknowledgeaboutmultiwordpredicates-2005","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"www.cs.toronto.edu/~fritz/tmp/compling.bib","downloads":0,"keywords":[],"search_terms":["automatic","acquisition","knowledge","multiword","predicates","fazly","stevenson"],"title":"Automatic acquisition of knowledge about multiword predicates","year":2005,"dataSources":["n8jB5BJxaeSmH6mtR","6b6A9kbkw4CsEGnRX"]}