Lexically Constrained Neural Machine Translation with Levenshtein Transformer
| Autor: | Shamil Chollampatt, Raymond Hendy Susanto, Liling Tan |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Machine translation Computer science Inference 02 engineering and technology 010501 environmental sciences computer.software_genre 01 natural sciences Terminology 0202 electrical engineering electronic engineering information engineering Beam search 020201 artificial intelligence & image processing Computation and Language (cs.CL) Algorithm computer Decoding methods 0105 earth and related environmental sciences Transformer (machine learning model) |
| Zdroj: | ACL |
| DOI: | 10.18653/v1/2020.acl-main.325 |
| Popis: | This paper proposes a simple and effective algorithm for incorporating lexical constraints in neural machine translation. Previous work either required re-training existing models with the lexical constraints or incorporating them during beam search decoding with significantly higher computational overheads. Leveraging the flexibility and speed of a recently proposed Levenshtein Transformer model (Gu et al., 2019), our method injects terminology constraints at inference time without any impact on decoding speed. Our method does not require any modification to the training procedure and can be easily applied at runtime with custom dictionaries. Experiments on English-German WMT datasets show that our approach improves an unconstrained baseline and previous approaches. 8 pages, In Proceedings of ACL 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|