A Aelf-supervised Tibetan-chinese Vocabulary Alignment Method Based On Adversarial Learning

TL;DR

This paper proposes a semi-supervised adversarial learning approach to align Tibetan and Chinese vocabularies using monolingual data and seed dictionaries, improving cross-lingual word alignment accuracy.

Contribution

It introduces an improved self-supervised adversarial method specifically designed for Tibetan-Chinese vocabulary alignment with limited parallel data.

Findings

Seed dictionary-based method achieved 66.5% accuracy (Tibetan-Chinese)

Self-supervised adversarial method improved accuracy to 53.5%

Weak semantic correlation observed between Tibetan syllables and Chinese characters

Abstract

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.