Building Instance Knowledge Network for Word Sense Disambiguation

Shangfeng Hu, Chengfei Liu, Xiaohui ZHAO, Marek Kowalkiewicz

Research output: A Conference proceeding or a Chapter in BookConference contribution

1 Citation (Scopus)

Abstract

In this paper, a new high precision focused word sense disambiguation (WSD) approach is proposed, which not only attempts to identify the proper sense for a word but also provides the probabilistic evaluation for the identification confidence at the same time. A novel Instance Knowledge Network (IKN) is built to generate and maintain semantic knowledge at the word, type synonym set and instance levels. Related algorithms based on graph matching are developed to train IKN with probabilistic knowledge and to use IKN for probabilistic word sense disambiguation. Based on the Senseval-3 all-words task, we run extensive experiments to show the performance enhancements in different precision ranges and the rationality of probabilistic based automatic confidence evaluation of disambiguation. We combine our WSD algorithm with five best WSD algorithms in senseval-3 all words tasks. The results show that the combined algorithms all outperform the corresponding algorithms
Original languageEnglish
Title of host publication34th Australasian Computer Science Conference
EditorsM Reynolds
Place of PublicationSydney
PublisherAustralian Computer Society
Pages1-8
Number of pages8
Publication statusPublished - 2011
Externally publishedYes
Event34th Australasian Computer Science Conference (ACSC 2011) - Perth, Perth, Australia
Duration: 17 Jan 201120 Jan 2011
https://50years.acs.org.au/content/dam/acs/50-years/journals/crpit/Vol113.pdf

Conference

Conference34th Australasian Computer Science Conference (ACSC 2011)
Abbreviated titleACSC 2011
CountryAustralia
CityPerth
Period17/01/1120/01/11
Internet address

Fingerprint

Semantics
Experiments

Cite this

Hu, S., Liu, C., ZHAO, X., & Kowalkiewicz, M. (2011). Building Instance Knowledge Network for Word Sense Disambiguation. In M. Reynolds (Ed.), 34th Australasian Computer Science Conference (pp. 1-8). Sydney: Australian Computer Society.
Hu, Shangfeng ; Liu, Chengfei ; ZHAO, Xiaohui ; Kowalkiewicz, Marek. / Building Instance Knowledge Network for Word Sense Disambiguation. 34th Australasian Computer Science Conference. editor / M Reynolds. Sydney : Australian Computer Society, 2011. pp. 1-8
@inproceedings{94b1bf01cfef4cd08032d751554e1608,
title = "Building Instance Knowledge Network for Word Sense Disambiguation",
abstract = "In this paper, a new high precision focused word sense disambiguation (WSD) approach is proposed, which not only attempts to identify the proper sense for a word but also provides the probabilistic evaluation for the identification confidence at the same time. A novel Instance Knowledge Network (IKN) is built to generate and maintain semantic knowledge at the word, type synonym set and instance levels. Related algorithms based on graph matching are developed to train IKN with probabilistic knowledge and to use IKN for probabilistic word sense disambiguation. Based on the Senseval-3 all-words task, we run extensive experiments to show the performance enhancements in different precision ranges and the rationality of probabilistic based automatic confidence evaluation of disambiguation. We combine our WSD algorithm with five best WSD algorithms in senseval-3 all words tasks. The results show that the combined algorithms all outperform the corresponding algorithms",
author = "Shangfeng Hu and Chengfei Liu and Xiaohui ZHAO and Marek Kowalkiewicz",
year = "2011",
language = "English",
pages = "1--8",
editor = "M Reynolds",
booktitle = "34th Australasian Computer Science Conference",
publisher = "Australian Computer Society",
address = "Australia",

}

Hu, S, Liu, C, ZHAO, X & Kowalkiewicz, M 2011, Building Instance Knowledge Network for Word Sense Disambiguation. in M Reynolds (ed.), 34th Australasian Computer Science Conference. Australian Computer Society, Sydney, pp. 1-8, 34th Australasian Computer Science Conference (ACSC 2011), Perth, Australia, 17/01/11.

Building Instance Knowledge Network for Word Sense Disambiguation. / Hu, Shangfeng; Liu, Chengfei; ZHAO, Xiaohui; Kowalkiewicz, Marek.

34th Australasian Computer Science Conference. ed. / M Reynolds. Sydney : Australian Computer Society, 2011. p. 1-8.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Building Instance Knowledge Network for Word Sense Disambiguation

AU - Hu, Shangfeng

AU - Liu, Chengfei

AU - ZHAO, Xiaohui

AU - Kowalkiewicz, Marek

PY - 2011

Y1 - 2011

N2 - In this paper, a new high precision focused word sense disambiguation (WSD) approach is proposed, which not only attempts to identify the proper sense for a word but also provides the probabilistic evaluation for the identification confidence at the same time. A novel Instance Knowledge Network (IKN) is built to generate and maintain semantic knowledge at the word, type synonym set and instance levels. Related algorithms based on graph matching are developed to train IKN with probabilistic knowledge and to use IKN for probabilistic word sense disambiguation. Based on the Senseval-3 all-words task, we run extensive experiments to show the performance enhancements in different precision ranges and the rationality of probabilistic based automatic confidence evaluation of disambiguation. We combine our WSD algorithm with five best WSD algorithms in senseval-3 all words tasks. The results show that the combined algorithms all outperform the corresponding algorithms

AB - In this paper, a new high precision focused word sense disambiguation (WSD) approach is proposed, which not only attempts to identify the proper sense for a word but also provides the probabilistic evaluation for the identification confidence at the same time. A novel Instance Knowledge Network (IKN) is built to generate and maintain semantic knowledge at the word, type synonym set and instance levels. Related algorithms based on graph matching are developed to train IKN with probabilistic knowledge and to use IKN for probabilistic word sense disambiguation. Based on the Senseval-3 all-words task, we run extensive experiments to show the performance enhancements in different precision ranges and the rationality of probabilistic based automatic confidence evaluation of disambiguation. We combine our WSD algorithm with five best WSD algorithms in senseval-3 all words tasks. The results show that the combined algorithms all outperform the corresponding algorithms

M3 - Conference contribution

SP - 1

EP - 8

BT - 34th Australasian Computer Science Conference

A2 - Reynolds, M

PB - Australian Computer Society

CY - Sydney

ER -

Hu S, Liu C, ZHAO X, Kowalkiewicz M. Building Instance Knowledge Network for Word Sense Disambiguation. In Reynolds M, editor, 34th Australasian Computer Science Conference. Sydney: Australian Computer Society. 2011. p. 1-8