2026-10-14T08:54:48Z https://www.scidb.cn/oai

10.11922/sciencedb.o00114.00034 2021-12-10T14:51:32Z

2021-12-10 Unsupervised adversarial training-based Chinese-Korean cross-lingual text classification method doi:10.11922/sciencedb.o00114.00034 en This paper proposes a cross-lingual text classification model combining unsupervised word embedding mapping and adversarial training. Firstly, pre-trained monolingual word vectors were mapped into the same semantic space by a linear mapping method, and then adversarial training was performed using the source and target lang uages, thus guiding the classification model to be able to learn language-independent features for the purpose of improving cross-lingual text classification performance. The experimental results show that the method in this paper significantly improves the accuracy of cross-lingual text classification compared with the direct use of cross-lingua l word vectors. Text classification; Cross-language word embedding; Confrontation training CUI Dong-hu CUI Rong-Yi ZHAO Ya-hui PUBLIC https://creativecommons.org/licenses/by/4.0/ dataset Science Data Bank