Open AccessA Self-Supervised Tibetan-Chinese Vocabulary Alignment Method
Author(s) -
Enshuai Hou,
Jie Zhu,
Liangcheng Yin,
Ning Ma
Publication year - 2021
Publication title -
international journal of web and semantic technology
Language(s) - English
Resource type - Journals
eISSN - 0976-2280
pISSN - 0975-9026
DOI - 10.5121/ijwest.2021.12402
Subject(s) - computer science , similarity (geometry) , artificial intelligence , adversarial system , natural language processing , vocabulary , word (group theory) , economic shortage , chinese language , supervised learning , labeled data , pattern recognition (psychology) , linguistics , image (mathematics) , artificial neural network , philosophy , government (linguistics)
Tibetan is a low-resource language. In order to alleviate the shortage of parallel corpus between Tibetan and Chinese, this paper uses two monolingual corpora and a small number of seed dictionaries to learn the semi-supervised method with seed dictionaries and self-supervised adversarial training method through the similarity calculation of word clusters in different embedded spaces and puts forward an improved selfsupervised adversarial learning method of Tibetan and Chinese monolingual data alignment only. The experimental results are as follows. The seed dictionary of semi-supervised method made before 10 predicted word accuracy of 66.5 (Tibetan - Chinese) and 74.8 (Chinese - Tibetan) results, to improve the self-supervision methods in both language directions have reached 53.5 accuracy.