Intelligent Translation Memory Matching and Retrieval with Sentence Encoders
This work addresses a bottleneck in translation technology for linguists and translators, but it is incremental as it applies an existing method (sentence encoders) to a new domain.
The paper tackled the problem of matching and retrieving translated segments in Translation Memory systems, which traditionally rely on edit distance algorithms, by introducing sentence encoders as a more effective and efficient solution.
Matching and retrieving previously translated segments from a Translation Memory is the key functionality in Translation Memories systems. However this matching and retrieving process is still limited to algorithms based on edit distance which we have identified as a major drawback in Translation Memories systems. In this paper we introduce sentence encoders to improve the matching and retrieving process in Translation Memories systems - an effective and efficient solution to replace edit distance based algorithms.