Graph Convolutional Network for Word Sense Disambiguation
Word sense disambiguation (WSD) is an important research topic in natural language processing, which is widely applied to text classification, machine translation, and information retrieval. In order to improve disambiguation accuracy, this paper proposes a WSD method based on the graph convolutiona...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Discrete Dynamics in Nature and Society |
| Online Access: | http://dx.doi.org/10.1155/2021/2822126 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832561571375611904 |
|---|---|
| author | Chun-Xiang Zhang Rui Liu Xue-Yao Gao Bo Yu |
| author_facet | Chun-Xiang Zhang Rui Liu Xue-Yao Gao Bo Yu |
| author_sort | Chun-Xiang Zhang |
| collection | DOAJ |
| description | Word sense disambiguation (WSD) is an important research topic in natural language processing, which is widely applied to text classification, machine translation, and information retrieval. In order to improve disambiguation accuracy, this paper proposes a WSD method based on the graph convolutional network (GCN). Word, part of speech, and semantic category are extracted from contexts of the ambiguous word as discriminative features. Discriminative features and sentence containing the ambiguous word are used as nodes to construct the WSD graph. Word2Vec tool, Doc2Vec tool, pointwise mutual information (PMI), and TF-IDF are applied to compute embeddings of nodes and edge weights. GCN is used to fuse features of a node and its neighbors, and the softmax function is applied to determine the semantic category of the ambiguous word. Training corpus of SemEval-2007: Task #5 is adopted to optimize the proposed WSD classifier. Test corpus of SemEval-2007: Task #5 is used to test the performance of WSD classifier. Experimental results show that average accuracy of the proposed method is improved. |
| format | Article |
| id | doaj-art-771370356aae4829a2040866bef726c6 |
| institution | Kabale University |
| issn | 1026-0226 1607-887X |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Discrete Dynamics in Nature and Society |
| spelling | doaj-art-771370356aae4829a2040866bef726c62025-02-03T01:24:41ZengWileyDiscrete Dynamics in Nature and Society1026-02261607-887X2021-01-01202110.1155/2021/28221262822126Graph Convolutional Network for Word Sense DisambiguationChun-Xiang Zhang0Rui Liu1Xue-Yao Gao2Bo Yu3School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaWord sense disambiguation (WSD) is an important research topic in natural language processing, which is widely applied to text classification, machine translation, and information retrieval. In order to improve disambiguation accuracy, this paper proposes a WSD method based on the graph convolutional network (GCN). Word, part of speech, and semantic category are extracted from contexts of the ambiguous word as discriminative features. Discriminative features and sentence containing the ambiguous word are used as nodes to construct the WSD graph. Word2Vec tool, Doc2Vec tool, pointwise mutual information (PMI), and TF-IDF are applied to compute embeddings of nodes and edge weights. GCN is used to fuse features of a node and its neighbors, and the softmax function is applied to determine the semantic category of the ambiguous word. Training corpus of SemEval-2007: Task #5 is adopted to optimize the proposed WSD classifier. Test corpus of SemEval-2007: Task #5 is used to test the performance of WSD classifier. Experimental results show that average accuracy of the proposed method is improved.http://dx.doi.org/10.1155/2021/2822126 |
| spellingShingle | Chun-Xiang Zhang Rui Liu Xue-Yao Gao Bo Yu Graph Convolutional Network for Word Sense Disambiguation Discrete Dynamics in Nature and Society |
| title | Graph Convolutional Network for Word Sense Disambiguation |
| title_full | Graph Convolutional Network for Word Sense Disambiguation |
| title_fullStr | Graph Convolutional Network for Word Sense Disambiguation |
| title_full_unstemmed | Graph Convolutional Network for Word Sense Disambiguation |
| title_short | Graph Convolutional Network for Word Sense Disambiguation |
| title_sort | graph convolutional network for word sense disambiguation |
| url | http://dx.doi.org/10.1155/2021/2822126 |
| work_keys_str_mv | AT chunxiangzhang graphconvolutionalnetworkforwordsensedisambiguation AT ruiliu graphconvolutionalnetworkforwordsensedisambiguation AT xueyaogao graphconvolutionalnetworkforwordsensedisambiguation AT boyu graphconvolutionalnetworkforwordsensedisambiguation |