@Article{cmes.2020.010579,
AUTHOR = {Fulian Yin, Yanyan Wang, Jianbo Liu, Meiqi Ji},
TITLE = {Enhancing Embedding-Based Chinese Word Similarity Evaluation with Concepts and Synonyms Knowledge},
JOURNAL = {Computer Modeling in Engineering \& Sciences},
VOLUME = {124},
YEAR = {2020},
NUMBER = {2},
PAGES = {747--764},
URL = {http://www.techscience.com/CMES/v124n2/39548},
ISSN = {1526-1506},
ABSTRACT = {Word similarity (WS) is a fundamental and critical task in natural language processing. Existing approaches to WS are mainly to calculate the similarity or relatedness of word pairs based on word embedding obtained by massive
and high-quality corpus. However, it may suffer from poor performance for insuf-
ficient corpus in some specific fields, and cannot capture rich semantic and sentimental information. To address these above problems, we propose an enhancing
embedding-based word similarity evaluation with character-word concepts and
synonyms knowledge, namely EWS-CS model, which can provide extra semantic
information to enhance word similarity evaluation. The core of our approach contains knowledge encoder and word encoder. In knowledge encoder, we incorporate the semantic knowledge extracted from knowledge resources, including
character-word concepts, synonyms and sentiment lexicons, to obtain knowledge
representation. Word encoder is to learn enhancing embedding-based word representation from pre-trained model and knowledge representation based on similarity task. Finally, compared with baseline models, the experiments on four
similarity evaluation datasets validate the effectiveness of our EWS-CS model
in WS task.},
DOI = {10.32604/cmes.2020.010579}
}