LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation

arXiv:2406.02876v1 Announce Type: new
Abstract: Multilingual neural machine translation models generally distinguish translation directions by the language tag (LT) in front of the source or target sentences. However, current LT strategies cannot indicate the desired target language as expected on zero-shot translation, i.e., the off-target issue. Our analysis reveals that the indication of the target language is sensitive to the placement of the target LT. For example, when placing the target LT on the decoder side, the indication would rapidly …

abstract analysis arxiv converter cs.ai cs.cl current front however issue language machine machine translation multilingual neural machine translation strategies strategy tag translation type zero-shot