[4N3-GS-6] Language media processing:

[4N3-GS-6-03] Multi-Source Text Classification for Multilingual Language Models with Machine Translation

〇Reon Kajikawa¹, Keiichiro Yamada², Tomoyuki Kajiwara¹, Takashi Ninomiya¹ (1. Ehime University, 2. Tokyo Metropolitan College of Industrial Technology)

Keywords:Natural Language Processing, Multilingual Language Model, Multi-Source, Text Classification

To reduce the cost of training models for each language for developers of natural language processing applications, pre-trained multilingual sentence encoders are promising.
However, since training corpora for such multilingual sentence encoders contain only a small amount of text in languages other than English, they suffer from performance degradation for non-English languages.
To improve the performance of pre-trained multilingual sentence encoders for non-English languages, we propose a method of machine translating a source sentence into English and then inputting it together with the source sentence in a multi-source manner.
Experimental results on sentiment analysis and topic classification tasks in Japanese revealed the effectiveness of the proposed method.