Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation
| Autor: | Matt Post, David Vilar |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Machine translation Process (engineering) Computer science A* search algorithm 02 engineering and technology Translation (geometry) computer.software_genre law.invention 030507 speech-language pathology & audiology 03 medical and health sciences law 0202 electrical engineering electronic engineering information engineering Beam search 020201 artificial intelligence & image processing 0305 other medical science Algorithm computer Computation and Language (cs.CL) Decoding methods Beam (structure) BLEU |
| Zdroj: | NAACL-HLT |
| Popis: | The end-to-end nature of neural machine translation (NMT) removes many ways of manually guiding the translation process that were available in older paradigms. Recent work, however, has introduced a new capability: lexically constrained or guided decoding, a modification to beam search that forces the inclusion of pre-specified words and phrases in the output. However, while theoretically sound, existing approaches have computational complexities that are either linear (Hokamp and Liu, 2017) or exponential (Anderson et al., 2017) in the number of constraints. We present a algorithm for lexically constrained decoding with a complexity of O(1) in the number of constraints. We demonstrate the algorithms remarkable ability to properly place these constraints, and use it to explore the shaky relationship between model and BLEU scores. Our implementation is available as part of Sockeye. 11 pages, 9 figures, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|