Using lexical knowledge of verbs in language-to-vision applications

M Ma, P McKevitt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

35 Citations (Scopus)

Abstract

In natural languages the default specification of arguments of verbs is often omitted in the surface form. The value of these arguments can be filled by lexical knowledge or commonsense knowledge of human readers, but it is a difficult task for computer programs. Here, we address the need for commonsense knowledge in computational lexicons, and discuss the requisite lexical knowledge of computational lexicons in the language-to-vision application CONFUCIUS. The underspecification problem in natural language visualisation is examined. We compare existing computational lexicons such as Word-Net, FrameNet, LCS database, and VerbNet, and show how lexical knowledge in a generative lexicon can be used for disambiguation and commonsense inferencing to fill unspecified argument structures for the task of language visualisation. The possibility of lexical inference with WordNet is explored in order to extract default and shadow arguments of verbs, and in particular, the default argument of implicit instruments/themes of action verbs, which can be used to improve CONFUCIUS' automated language-to-vision conversion through semantic understanding of the text, and to make animation generation more robust by employing the commonsense knowledge included in (or inferred from) lexical entries.
LanguageEnglish
Title of host publicationUnknown Host Publication
EditorsL McGinty, B Crean
Place of PublicationGalway-Mayo Institute of Technology (GMIT), Castlebar, Co. Mayo, Ireland
Pages255-264
Number of pages10
Publication statusPublished - Sep 2004
EventProc. of the 15th Irish Conference on Artificial Intelligence and Cognitive Science (AICS-04) - Galway-Mayo Institute of Technology (GMIT), Castlebar, Co.Mayo, Ireland
Duration: 1 Sep 2004 → …

Conference

ConferenceProc. of the 15th Irish Conference on Artificial Intelligence and Cognitive Science (AICS-04)
Period1/09/04 → …

Fingerprint

Verbs
Language
Lexical Knowledge
Computational
Lexicon
Natural Language
Visualization
WordNet
Lexical Entries
Generative Lexicon
Data Base
Reader
Argument Structure
Action Verbs
Underspecification
Animation
Inferencing
Inference
Surface Form
Disambiguation

Cite this

Ma, M., & McKevitt, P. (2004). Using lexical knowledge of verbs in language-to-vision applications. In L. McGinty, & B. Crean (Eds.), Unknown Host Publication (pp. 255-264). Galway-Mayo Institute of Technology (GMIT), Castlebar, Co. Mayo, Ireland.
Ma, M ; McKevitt, P. / Using lexical knowledge of verbs in language-to-vision applications. Unknown Host Publication. editor / L McGinty ; B Crean. Galway-Mayo Institute of Technology (GMIT), Castlebar, Co. Mayo, Ireland, 2004. pp. 255-264
@inproceedings{54f4244f29064b0485678cc2e9f01e49,
title = "Using lexical knowledge of verbs in language-to-vision applications",
abstract = "In natural languages the default specification of arguments of verbs is often omitted in the surface form. The value of these arguments can be filled by lexical knowledge or commonsense knowledge of human readers, but it is a difficult task for computer programs. Here, we address the need for commonsense knowledge in computational lexicons, and discuss the requisite lexical knowledge of computational lexicons in the language-to-vision application CONFUCIUS. The underspecification problem in natural language visualisation is examined. We compare existing computational lexicons such as Word-Net, FrameNet, LCS database, and VerbNet, and show how lexical knowledge in a generative lexicon can be used for disambiguation and commonsense inferencing to fill unspecified argument structures for the task of language visualisation. The possibility of lexical inference with WordNet is explored in order to extract default and shadow arguments of verbs, and in particular, the default argument of implicit instruments/themes of action verbs, which can be used to improve CONFUCIUS' automated language-to-vision conversion through semantic understanding of the text, and to make animation generation more robust by employing the commonsense knowledge included in (or inferred from) lexical entries.",
author = "M Ma and P McKevitt",
year = "2004",
month = "9",
language = "English",
isbn = "978-1-902277-89-9",
pages = "255--264",
editor = "L McGinty and B Crean",
booktitle = "Unknown Host Publication",

}

Ma, M & McKevitt, P 2004, Using lexical knowledge of verbs in language-to-vision applications. in L McGinty & B Crean (eds), Unknown Host Publication. Galway-Mayo Institute of Technology (GMIT), Castlebar, Co. Mayo, Ireland, pp. 255-264, Proc. of the 15th Irish Conference on Artificial Intelligence and Cognitive Science (AICS-04), 1/09/04.

Using lexical knowledge of verbs in language-to-vision applications. / Ma, M; McKevitt, P.

Unknown Host Publication. ed. / L McGinty; B Crean. Galway-Mayo Institute of Technology (GMIT), Castlebar, Co. Mayo, Ireland, 2004. p. 255-264.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Using lexical knowledge of verbs in language-to-vision applications

AU - Ma, M

AU - McKevitt, P

PY - 2004/9

Y1 - 2004/9

N2 - In natural languages the default specification of arguments of verbs is often omitted in the surface form. The value of these arguments can be filled by lexical knowledge or commonsense knowledge of human readers, but it is a difficult task for computer programs. Here, we address the need for commonsense knowledge in computational lexicons, and discuss the requisite lexical knowledge of computational lexicons in the language-to-vision application CONFUCIUS. The underspecification problem in natural language visualisation is examined. We compare existing computational lexicons such as Word-Net, FrameNet, LCS database, and VerbNet, and show how lexical knowledge in a generative lexicon can be used for disambiguation and commonsense inferencing to fill unspecified argument structures for the task of language visualisation. The possibility of lexical inference with WordNet is explored in order to extract default and shadow arguments of verbs, and in particular, the default argument of implicit instruments/themes of action verbs, which can be used to improve CONFUCIUS' automated language-to-vision conversion through semantic understanding of the text, and to make animation generation more robust by employing the commonsense knowledge included in (or inferred from) lexical entries.

AB - In natural languages the default specification of arguments of verbs is often omitted in the surface form. The value of these arguments can be filled by lexical knowledge or commonsense knowledge of human readers, but it is a difficult task for computer programs. Here, we address the need for commonsense knowledge in computational lexicons, and discuss the requisite lexical knowledge of computational lexicons in the language-to-vision application CONFUCIUS. The underspecification problem in natural language visualisation is examined. We compare existing computational lexicons such as Word-Net, FrameNet, LCS database, and VerbNet, and show how lexical knowledge in a generative lexicon can be used for disambiguation and commonsense inferencing to fill unspecified argument structures for the task of language visualisation. The possibility of lexical inference with WordNet is explored in order to extract default and shadow arguments of verbs, and in particular, the default argument of implicit instruments/themes of action verbs, which can be used to improve CONFUCIUS' automated language-to-vision conversion through semantic understanding of the text, and to make animation generation more robust by employing the commonsense knowledge included in (or inferred from) lexical entries.

M3 - Conference contribution

SN - 978-1-902277-89-9

SP - 255

EP - 264

BT - Unknown Host Publication

A2 - McGinty, L

A2 - Crean, B

CY - Galway-Mayo Institute of Technology (GMIT), Castlebar, Co. Mayo, Ireland

ER -

Ma M, McKevitt P. Using lexical knowledge of verbs in language-to-vision applications. In McGinty L, Crean B, editors, Unknown Host Publication. Galway-Mayo Institute of Technology (GMIT), Castlebar, Co. Mayo, Ireland. 2004. p. 255-264