Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting
This addresses terminology accuracy in machine translation for downstream applications, representing an incremental improvement over existing constraint-based methods.
The paper tackles the problem of ensuring terminology correctness in machine translation by proposing a translate-then-refine approach that trains a terminology-aware model and uses post-processing methods like constrained decoding and large language model prompting. Results show effective terminology incorporation and improved recall, with specific gains reported in the WMT 2023 task.
Terminology correctness is important in the downstream application of machine translation, and a prevalent way to ensure this is to inject terminology constraints into a translation system. In our submission to the WMT 2023 terminology translation task, we adopt a translate-then-refine approach which can be domain-independent and requires minimal manual efforts. We annotate random source words with pseudo-terminology translations obtained from word alignment to first train a terminology-aware model. Further, we explore two post-processing methods. First, we use an alignment process to discover whether a terminology constraint has been violated, and if so, we re-decode with the violating word negatively constrained. Alternatively, we leverage a large language model to refine a hypothesis by providing it with terminology constraints. Results show that our terminology-aware model learns to incorporate terminologies effectively, and the large language model refinement process can further improve terminology recall.