Enriching Semantic Knowledge for WSD

Junpeng CHEN; Wei YU

doi:10.1587/transinf.E97.D.2212

Enriching Semantic Knowledge for WSD

Junpeng CHEN, Wei YU

Full Text Views

0

Share
Cite this

Summary :

In our previous work, we proposed to combine ConceptNet and WordNet for Word Sense Disambiguation (WSD). The ConceptNet was automatically disambiguated through Normalized Google Distance (NGD) similarity. In this letter, we present several techniques to enhance the performance of the ConceptNet disambiguation and use this enriched semantic knowledge in WSD task. We propose to enrich both the WordNet semantic knowledge and NGD to disambiguate the concepts in ConceptNet. Furthermore, we apply the enriched semantic knowledge to improve the performance of WSD. From a number of experiments, the proposed method has been obtained enhanced results.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.8 pp.2212-2216

Publication Date: 2014/08/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E97.D.2212

Type of Manuscript: LETTER

Category: Natural Language Processing

Authors

Junpeng CHEN
Nanjing University of Finance & Economic
Wei YU
Nanjing University

Keyword

ConceptNet disambiguation, Normalized Google Distance, semantic similarity measure, Word Sense Disambiguation

Cite this

Copy

Junpeng CHEN, Wei YU, "Enriching Semantic Knowledge for WSD" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 8, pp. 2212-2216, August 2014, doi: 10.1587/transinf.E97.D.2212.
Abstract: In our previous work, we proposed to combine ConceptNet and WordNet for Word Sense Disambiguation (WSD). The ConceptNet was automatically disambiguated through Normalized Google Distance (NGD) similarity. In this letter, we present several techniques to enhance the performance of the ConceptNet disambiguation and use this enriched semantic knowledge in WSD task. We propose to enrich both the WordNet semantic knowledge and NGD to disambiguate the concepts in ConceptNet. Furthermore, we apply the enriched semantic knowledge to improve the performance of WSD. From a number of experiments, the proposed method has been obtained enhanced results.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E97.D.2212/_p

Copy

@ARTICLE{e97-d_8_2212,
author={Junpeng CHEN, Wei YU, },
journal={IEICE TRANSACTIONS on Information},
title={Enriching Semantic Knowledge for WSD},
year={2014},
volume={E97-D},
number={8},
pages={2212-2216},
abstract={In our previous work, we proposed to combine ConceptNet and WordNet for Word Sense Disambiguation (WSD). The ConceptNet was automatically disambiguated through Normalized Google Distance (NGD) similarity. In this letter, we present several techniques to enhance the performance of the ConceptNet disambiguation and use this enriched semantic knowledge in WSD task. We propose to enrich both the WordNet semantic knowledge and NGD to disambiguate the concepts in ConceptNet. Furthermore, we apply the enriched semantic knowledge to improve the performance of WSD. From a number of experiments, the proposed method has been obtained enhanced results.},
keywords={},
doi={10.1587/transinf.E97.D.2212},
ISSN={1745-1361},
month={August},}

Copy

TY - JOUR
TI - Enriching Semantic Knowledge for WSD
T2 - IEICE TRANSACTIONS on Information
SP - 2212
EP - 2216
AU - Junpeng CHEN
AU - Wei YU
PY - 2014
DO - 10.1587/transinf.E97.D.2212
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2014
AB - In our previous work, we proposed to combine ConceptNet and WordNet for Word Sense Disambiguation (WSD). The ConceptNet was automatically disambiguated through Normalized Google Distance (NGD) similarity. In this letter, we present several techniques to enhance the performance of the ConceptNet disambiguation and use this enriched semantic knowledge in WSD task. We propose to enrich both the WordNet semantic knowledge and NGD to disambiguate the concepts in ConceptNet. Furthermore, we apply the enriched semantic knowledge to improve the performance of WSD. From a number of experiments, the proposed method has been obtained enhanced results.
ER -