Co-occurrence Networks for Word Sense Induction

被引：0

作者：

Humonen, Innokentiy S. ^{[1
,2
]}

Makarov, Ilya ^{[1
,2
,3
]}

机构：

[1] HSE Univ, Moscow, Russia

[2] Artificial Intelligence Res Inst AIRI, Moscow, Russia

[3] Natl Univ Sci & Technol MISIS, AI Ctr, Moscow, Russia

来源：

2023 IEEE 21ST WORLD SYMPOSIUM ON APPLIED MACHINE INTELLIGENCE AND INFORMATICS, SAMI | 2023年

基金：

俄罗斯科学基金会;

关键词：

word sense induction; co-occurrence networks; graph neural networks; clustering; natural language processing;

D O I：

10.1109/SAMI58000.2023.10044503

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Word sense induction (WSI) is the unsupervised and knowledge-free task of clustering occurrences of homonymous or ambiguous words by their meanings. This problem has been relevant since the second half of the 20th century [1] and arises in various natural language processing areas, such as machine translation, sentiment analysis, chatbots, etc. In this work, we applied graph neural networks to the WSI-problem using a co-occurrence network and evaluated it on the RUSSE'2018 task [2]. Proposed approach demonstrates satisfactory results with low consumption of computational resources.

引用

页码：97 / 102

页数：6

共 50 条

[1] Word sense determination using WordNet and sense co-occurrence
Yang, Che-Yu
Hung, Jason C.
20TH INTERNATIONAL CONFERENCE ON ADVANCED INFORMATION NETWORKING AND APPLICATIONS, VOL 1, PROCEEDINGS, 2006, : 779 - +
[2] Conceptual grouping in word co-occurrence networks
Veling, A
van der Weerd, P
IJCAI-99: PROCEEDINGS OF THE SIXTEENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOLS 1 & 2, 1999, : 694 - 699
[3] Hashtag Sense Induction Based on Co-occurrence Graphs
Wang, Mengmeng
Iwaihara, Mizuho
WEB TECHNOLOGIES AND APPLICATIONS (APWEB 2015), 2015, 9313 : 154 - 165
[4] Co-occurrence graphs for word sense disambiguation in the biomedical domain
Duque, Andres
Stevenson, Mark
Martinez-Romo, Juan
Araujo, Lourdes
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2018, 87 : 9 - 19
[5] Sentiment and structure in word co-occurrence networks on Twitter
Mikaela Irene Fudolig
Thayer Alshaabi
Michael V. Arnold
Christopher M. Danforth
Peter Sheridan Dodds
Applied Network Science, 7
[6] Spectra of English evolving word co-occurrence networks
Liang, Wei
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2017, 468 : 802 - 808
[7] Construction and Analysis of Mongolian Word Co-occurrence Networks
Bao, Lingxiong
Dahubaiyila
2022 INTERNATIONAL CONFERENCE ON ASIAN LANGUAGE PROCESSING (IALP 2022), 2022, : 110 - 115
[8] Sentiment and structure in word co-occurrence networks on Twitter
Fudolig, Mikaela Irene
Alshaabi, Thayer
Arnold, Michael, V
Danforth, Christopher M.
Dodds, Peter Sheridan
APPLIED NETWORK SCIENCE, 2022, 7 (01)
[9] Chinese word sense disambiguation method based on primitive co-occurrence data
Yang, E.H.
Zhang, G.Q.
Zhang, Y.K.
Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2001, 38 (07):
[10] Learning of word sense disambiguation rules by Co-training, checking co-occurrence of features
Ibaraki University, 4-12-1 Nakanarusawa, Hitachi Ibaraki
316-8511, Japan
Proc. Int. Conf. Lang. Resourc. Eval., LREC, 1600, (1380-1384):

← 1 2 3 4 5 →