Lexical impoverishment in neural machine translation: automatic and human study of Spanish-English noun translation
The information required to translate a word in the machine translation of isolated sentences is often missing or unobtainable. We show that the diversity in the training-set distribution of Spanish equivalents of English nouns is reduced in translation. A translator survey reveals this is often due to lack of source context.
Authors
- Mikel L. Forcada (ORCID: https://orcid.org/0000-0003-0843-6442)
- M. Giménez
Institutions
- University of Alicante (ES)
Publication Details
- Journal
- Tradumàtica tecnologies de la traducció
- Published
- 2024-12-31
- DOI
- https://doi.org/10.5565/rev/tradumatica.428
- Primary Topic
- Natural Language Processing Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00