LCS:一种用于零样本神经机器翻译的语言转换器策略
LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation
AI总结:
本文提出语言转换器策略(LCS),通过在编码器顶层引入目标语言嵌入,解决零样本神经机器翻译中的偏离目标语言问题,并在多个数据集上显著提升语言准确率和BLEU分数。
摘要:
多语言神经机器翻译模型通常通过在源句或目标句前添加语言标签(LT)来区分翻译方向。然而,当前的LT策略在零样本翻译中无法按预期指示所需的目标语言,即存在偏离目标语言(off-target)问题。我们的分析表明,目标语言的指示对目标LT的放置位置非常敏感。例如,当将目标LT放在解码器端时,指示会随着解码步骤的推进而迅速退化;而当将目标LT放在编码器端时,则会导致复制或改写源输入。为解决上述问题,我们提出了一种简单而有效的策略,称为语言转换器策略(LCS)。通过在顶部编码器层中引入目标语言嵌入,LCS缓解了编码器中的混淆,并确保为解码器提供稳定的语言指示。在MultiUN、TED和OPUS-100数据集上的实验结果表明,LCS能够显著缓解偏离目标语言问题,语言准确率分别达到95.28%、96.21%和85.35%,同时在零样本翻译上的BLEU分数分别比普通LT策略高出3.07、3.3和7.93。
英文摘要:
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 degrade along with decoding steps, while placing the target LT on the encoder side would lead to copying or paraphrasing the source input. To address the above issues, we propose a simple yet effective strategy named Language Converter Strategy (LCS). By introducing the target language embedding into the top encoder layers, LCS mitigates confusion in the encoder and ensures stable language indication for the decoder. Experimental results on MultiUN, TED, and OPUS-100 datasets demonstrate that LCS could significantly mitigate the off-target issue, with language accuracy up to 95.28%, 96.21%, and 85.35% meanwhile outperforming the vanilla LT strategy by 3.07, 3,3, and 7.93 BLEU scores on zero-shot translation, respectively.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。