Aligning Translation-Specific Understanding to General Understanding in Large Language Models

Anonymous

Abstract: Although large language models (LLMs) have shown surprising language understanding and generation capabilities, they have yet to gain a revolutionary advancement in the field of machine translation. One potential cause of the limited performance is the misalignment between the translation-specific understanding and general understanding inside LLMs. To align the translation-specific understanding to the general one, we propose a novel translation process \textsc{xIoD} (\textbf{Cross-Lingual} \textbf{I}nterpretation \textbf{o}f \textbf{D}ifficult words), explicitly incorporating the general understanding on the content incurring inconsistent understanding to guide the translation.= Specifically, \textsc{xIoD} performs the cross-lingual interpretation for the difficult-to-translate words and enhances the translation with the generated interpretations. Furthermore, we reframe the external tools of QE to tackle the challenges of \textsc{xIoD} in the detection of difficult words and the generation of helpful interpretations. We conduct experiments on the self-constructed benchmark Challenge-MT, which includes cases in which multiple SOTA translation systems consistently underperform. Experimental results show the effectiveness of our \textsc{xIoD}, which improves up to +3.85 COMET. Human evaluation reveals that the translation generated by \textsc{xIoD} accords more with the sense-for-sense translation.

Paper Type: long

Research Area: Machine Translation

Contribution Types: NLP engineering experiment

Languages Studied: English,Chinese,Estonian,Islandic