"Semantic Textual Similarity based on Deep Learning: Can it improve matching and retrieval for Translation Memory tools?"

by Tharindu Ranasinghe, University of Wolverhampton

Update: the event has now finished (Jan 20th 2021).

Abstract

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 talk, we talk about our research [1,2] on sentence encoders to improve the matching and retrieving process in Translation Memories systems - an effective and efficient solution to replace edit distance-based algorithms.

References:

  • Ranasinghe, T. Mitkov, R., Orasan, C. and Caro, R., 2020, May. Semantic Textual Similarity based on Deep Learning: Can it improve matching and retrieval for Translation Memory tools?. In Parallel Corpora: Creation and Applications. John Benjamins.
  • Ranasinghe, T. Orasan, C. and Mitkov, R., 2020, May. Intelligent Translation Memory Matching and Retrieval with Sentence Encoders. In Proceedings of the 22nd Annual Conference of the European Association for Machine Translation (pp. 175–184).

CONTACT DETAILS


RGCL
University of Wolverhampton
Wulfruna Street
Wolverhampton, WV1 1LY
United Kingdom