Open AccessA Self-Supervised Tibetan-Chinese Vocabulary Alignment Method based on Adversarial Learning
Author(s) -
Enshuai Hou,
Jie Zhu
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5121/csit.2021.111422
Subject(s) - computer science , artificial intelligence , adversarial system , natural language processing , similarity (geometry) , vocabulary , word (group theory) , economic shortage , supervised learning , chinese language , speech recognition , linguistics , artificial neural network , philosophy , government (linguistics) , image (mathematics)
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 self-supervised adversarial learning method of Tibetan and Chinese monolingual data alignment only. The experimental results are as follows. First, the experimental results of Tibetan syllables Chinese characters are not good, which reflects the weak semantic correlation between Tibetan syllables and Chinese characters; second, 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.