We propose novel sequence-to-sequence pre-training objectives for low-resource machine translation (NMT): Japanese-specific sequence to sequence (JASS) for language pairs involving Japanese as the source or target language, and English-specific sequence to sequence (ENSS) for language pairs involving English. JASS focuses on masking and reordering Japanese linguistic units known as bunsetsu, whereas ENSS is proposed based on phrase structure masking and reordering tasks. Experiments on ASPEC Japanese–English & Japanese–Chinese, Wikipedia Japanese–Chinese, News English–Korean corpora demonstrate that JASS and ENSS outperform MASS and other existing language-agnostic pre-training methods by up to +2.9 BLEU points for the Japanese–English tasks, up to +7.0 BLEU points for the Japanese–Chinese tasks and up to +1.3 BLEU points for English–Korean tasks. Empirical analysis, which focuses on the relationship between individual parts in JASS and ENSS, reveals the complementary nature of the subtasks of JASS and ENSS. Adequacy evaluation using LASER, human evaluation, and case studies reveals that our proposed methods significantly outperform pre-training methods without injected linguistic knowledge and they have a larger positive impact on the adequacy as compared to the fluency.
日本語、英語、中国語、韓国語、低資源機械翻訳の精度向上
| 氏名 | 専攻 | 研究室 | 役職/学年 |
|---|---|---|---|
| 毛卓遠 | 知能情報学専攻 | 黒橋研究室 | 博士1回生 |
| Chenhui Chu | 知能情報学専攻 | 黒橋研究室 | 特定准教授 |
| 黒橋禎夫 | 知能情報学専攻 | 黒橋研究室 | 教授 |
https://github.com/Mao-KU/JASS/tree/master/linguistically-driven-pretraining