Premium
Combining and learning word embedding with WordNet for semantic relatedness and similarity measurement
Author(s) -
Lee YangYin,
Ke Hao,
Yen TingYu,
Huang HenHsen,
Chen HsinHsi
Publication year - 2020
Publication title -
journal of the association for information science and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.903
H-Index - 145
eISSN - 2330-1643
pISSN - 2330-1635
DOI - 10.1002/asi.24289
Subject(s) - wordnet , word embedding , benchmark (surveying) , computer science , semantic similarity , artificial intelligence , word (group theory) , natural language processing , embedding , similarity (geometry) , measure (data warehouse) , information retrieval , mathematics , data mining , image (mathematics) , geometry , geodesy , geography
In this research, we propose 3 different approaches to measure the semantic relatedness between 2 words: (i) boost the performance of GloVe word embedding model via removing or transforming abnormal dimensions; (ii) linearly combine the information extracted from WordNet and word embeddings; and (iii) utilize word embedding and 12 linguistic information extracted from WordNet as features for Support Vector Regression. We conducted our experiments on 8 benchmark data sets, and computed Spearman correlations between the outputs of our methods and the ground truth. We report our results together with 3 state‐of‐the‐art approaches. The experimental results show that our method can outperform state‐of‐the‐art approaches in all the selected English benchmark data sets.