Optimizing example selection for retrieval-augmented machine translation with translation memories
This work addresses the challenge of efficient example retrieval for machine translation systems, which is an incremental improvement in a domain-specific area.
The paper tackled the problem of selecting examples from a translation memory to improve retrieval-augmented machine translation by optimizing coverage of the source sentence using submodular functions, resulting in performance gains evaluated on the translation task.
Retrieval-augmented machine translation leverages examples from a translation memory by retrieving similar instances. These examples are used to condition the predictions of a neural decoder. We aim to improve the upstream retrieval step and consider a fixed downstream edit-based model: the multi-Levenshtein Transformer. The task consists of finding a set of examples that maximizes the overall coverage of the source sentence. To this end, we rely on the theory of submodular functions and explore new algorithms to optimize this coverage. We evaluate the resulting performance gains for the machine translation task.