Home Linguistics & Semiotics Chapter 4. Semantic textual similarity based on deep learning
Chapter
Licensed
Unlicensed Requires Authentication

Chapter 4. Semantic textual similarity based on deep learning

Can it improve matching and retrieval for Translation Memory tools?
  • Tharindu Ranasinghe , Ruslan Mitkov , Constantin Orăsan and Rocío Caro Quintana
View more publications by John Benjamins Publishing Company
To Publisher Page
Corpora in Translation and Contrastive Research in the Digital Age
This chapter is in the book Corpora in Translation and Contrastive Research in the Digital Age

Abstract

This study proposes an original methodology to underpin the operation of new generation Translation Memory (TM) systems where the translations to be retrieved from the TM database are matched not on the basis of Levenshtein (edit) distance but by employing innovative Natural Language Processing (NLP) and Deep Learning (DL) techniques. Three DL sentence encoders were experimented with to retrieve TM matches in English-Spanish sentence pairs from the DGT TM dataset. Each sentence encoder was compared with Okapi which uses edit distance to retrieve the best match.1 The automatic evaluation shows the benefit of the DL technology for TM matching and holds promise for the implementation of the TM tool itself, which is our next project.

Abstract

This study proposes an original methodology to underpin the operation of new generation Translation Memory (TM) systems where the translations to be retrieved from the TM database are matched not on the basis of Levenshtein (edit) distance but by employing innovative Natural Language Processing (NLP) and Deep Learning (DL) techniques. Three DL sentence encoders were experimented with to retrieve TM matches in English-Spanish sentence pairs from the DGT TM dataset. Each sentence encoder was compared with Okapi which uses edit distance to retrieve the best match.1 The automatic evaluation shows the benefit of the DL technology for TM matching and holds promise for the implementation of the TM tool itself, which is our next project.

Chapters in this book

  1. Prelim pages i
  2. Table of contents v
  3. Corpus resources and tools 1
  4. Part I. Corpus resources and tools
  5. Chapter 1. Now what ? 23
  6. Chapter 2. ZHEN 49
  7. Chapter 3. Word alignment in a parallel corpus of Old English prose 75
  8. Chapter 4. Semantic textual similarity based on deep learning 101
  9. Chapter 5. TAligner 3.0 125
  10. Chapter 6. Developing a corpus-informed tool for Spanish professionals writing specialised texts in English 147
  11. Part II. Corpus-based studies and explorations
  12. Chapter 7. English and Spanish discourse markers in translation 177
  13. Chapter 8. The discourse markers well and so and their equivalents in the Portuguese and Turkish subparts of the TED-MDB corpus 209
  14. Chapter 9. Variation of evidential values in discourse domains 233
  15. Chapter 10. The translation for dubbing of Westerns in Spain 257
  16. Chapter 11. Generic analysis of mobile application reviews in English and Spanish 283
  17. Chapter 12. Exploring variation in translation with probabilistic language models 307
  18. Chapter 13. Binomial adverbs in Germanic and Romance Languages 325
  19. Index 343
https://doi.org/10.1075/btl.158.04ran

Chapters in this book

  1. Prelim pages i
  2. Table of contents v
  3. Corpus resources and tools 1
  4. Part I. Corpus resources and tools
  5. Chapter 1. Now what ? 23
  6. Chapter 2. ZHEN 49
  7. Chapter 3. Word alignment in a parallel corpus of Old English prose 75
  8. Chapter 4. Semantic textual similarity based on deep learning 101
  9. Chapter 5. TAligner 3.0 125
  10. Chapter 6. Developing a corpus-informed tool for Spanish professionals writing specialised texts in English 147
  11. Part II. Corpus-based studies and explorations
  12. Chapter 7. English and Spanish discourse markers in translation 177
  13. Chapter 8. The discourse markers well and so and their equivalents in the Portuguese and Turkish subparts of the TED-MDB corpus 209
  14. Chapter 9. Variation of evidential values in discourse domains 233
  15. Chapter 10. The translation for dubbing of Westerns in Spain 257
  16. Chapter 11. Generic analysis of mobile application reviews in English and Spanish 283
  17. Chapter 12. Exploring variation in translation with probabilistic language models 307
  18. Chapter 13. Binomial adverbs in Germanic and Romance Languages 325
  19. Index 343
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 29.12.2025 from https://www.degruyterbrill.com/document/doi/10.1075/btl.158.04ran/html
Scroll to top button