Sökning: id:"swepub:oai:DiVA.org:kth-302955" >
The lazy encoder :
The lazy encoder : A fine-grained analysis of the role of morphology in neural machine translation
-
Bisazza, A. (författare)
-
- Tump, Clara (författare)
- KTH,Skolan för elektroteknik och datavetenskap (EECS)
-
(creator_code:org_t)
- Stroudsburg, PA, USA : Association for Computational Linguistics, 2020
- 2020
- Engelska.
-
Ingår i: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018. - Stroudsburg, PA, USA : Association for Computational Linguistics. ; , s. 2871-2876
- Relaterad länk:
-
https://www.aclweb.o...
-
visa fler...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Neural sequence-to-sequence models have proven very effective for machine translation, but at the expense of model interpretability. To shed more light into the role played by linguistic structure in the process of neural machine translation, we perform a fine-grained analysis of how various source-side morphological features are captured at different levels of the NMT encoder while varying the target language. Differently from previous work, we find no correlation between the accuracy of source morphology encoding and translation quality. We do find that morphological features are only captured in context and only to the extent that they are directly transferable to the target words.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Language Technology (hsv//eng)
Nyckelord
- Computational linguistics
- Computer aided language translation
- Morphology
- Natural language processing systems
- Fine-grained analysis
- Interpretability
- Linguistic structure
- Machine translations
- Morphological features
- Sequence models
- Target language
- Translation quality
- Signal encoding
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)