Linguistically-motivated automatic morphological analysis for Wordnet enrichment

Thomas Richens

Linguistically-motivated automatic morphological analysis for Wordnet enrichment

Thomas Richens

Computer Science

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

Performance of NLP systems can only be as good as the lexical resources they employ. By modelling the evolved structure of language, there is scope for morpho-semantic enrichment of these resources. A set of linguistically-informed morphological rules is formulated from the CatVar database, implemented in a Java model of WordNet and tested on suffixation and desuffixation. Overgeneration and undergeneration are measured and an approach to improving these by using multilingual resources is proposed.

Original language	English
Title of host publication	Natural Language Processing and Cognitive Science - Proceedings of the 6th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2009 In Conjunction with ICEIS 2009
Pages	36-45
Number of pages	10
Publication status	Published - 1 Dec 2009
Event	6th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2009 In Conjunction with ICEIS 2009 - Milan, United Kingdom Duration: 1 May 2009 → 1 May 2009

Conference

Conference	6th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2009 In Conjunction with ICEIS 2009
Country/Territory	United Kingdom
City	Milan
Period	1/05/09 → 1/05/09

Cite this

@inproceedings{22c6f2761eec4ee3ad2d1755b688d16b,

title = "Linguistically-motivated automatic morphological analysis for Wordnet enrichment",

abstract = "Performance of NLP systems can only be as good as the lexical resources they employ. By modelling the evolved structure of language, there is scope for morpho-semantic enrichment of these resources. A set of linguistically-informed morphological rules is formulated from the CatVar database, implemented in a Java model of WordNet and tested on suffixation and desuffixation. Overgeneration and undergeneration are measured and an approach to improving these by using multilingual resources is proposed.",

author = "Thomas Richens",

year = "2009",

month = dec,

day = "1",

language = "English",

isbn = "9789898111920",

pages = "36--45",

booktitle = "Natural Language Processing and Cognitive Science - Proceedings of the 6th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2009 In Conjunction with ICEIS 2009",

note = "6th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2009 In Conjunction with ICEIS 2009 ; Conference date: 01-05-2009 Through 01-05-2009",

}

Richens, T 2009, Linguistically-motivated automatic morphological analysis for Wordnet enrichment. in Natural Language Processing and Cognitive Science - Proceedings of the 6th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2009 In Conjunction with ICEIS 2009. pp. 36-45, 6th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2009 In Conjunction with ICEIS 2009, Milan, United Kingdom, 1/05/09.

Linguistically-motivated automatic morphological analysis for Wordnet enrichment. / Richens, Thomas.
Natural Language Processing and Cognitive Science - Proceedings of the 6th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2009 In Conjunction with ICEIS 2009. 2009. p. 36-45.

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Linguistically-motivated automatic morphological analysis for Wordnet enrichment

AU - Richens, Thomas

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Performance of NLP systems can only be as good as the lexical resources they employ. By modelling the evolved structure of language, there is scope for morpho-semantic enrichment of these resources. A set of linguistically-informed morphological rules is formulated from the CatVar database, implemented in a Java model of WordNet and tested on suffixation and desuffixation. Overgeneration and undergeneration are measured and an approach to improving these by using multilingual resources is proposed.

AB - Performance of NLP systems can only be as good as the lexical resources they employ. By modelling the evolved structure of language, there is scope for morpho-semantic enrichment of these resources. A set of linguistically-informed morphological rules is formulated from the CatVar database, implemented in a Java model of WordNet and tested on suffixation and desuffixation. Overgeneration and undergeneration are measured and an approach to improving these by using multilingual resources is proposed.

UR - http://www.scopus.com/inward/record.url?scp=74549117158&partnerID=8YFLogxK

M3 - Conference publication

AN - SCOPUS:74549117158

SN - 9789898111920

SP - 36

EP - 45

BT - Natural Language Processing and Cognitive Science - Proceedings of the 6th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2009 In Conjunction with ICEIS 2009

T2 - 6th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2009 In Conjunction with ICEIS 2009

Y2 - 1 May 2009 through 1 May 2009

ER -

Linguistically-motivated automatic morphological analysis for Wordnet enrichment

Abstract

Conference

Other files and links

Fingerprint

Cite this