A Aelf-supervised Tibetan-chinese Vocabulary Alignment Method Based On Adversarial Learning
This addresses vocabulary alignment for low-resource Tibetan language, though it appears incremental with modest gains.
The paper tackles the problem of Tibetan-Chinese vocabulary alignment with limited parallel data by proposing an improved self-supervised adversarial learning method using monolingual corpora and seed dictionaries, achieving accuracy improvements from 66.5/74.8 to 53.5 in both language directions.
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.