Continuous Learning from Human Post-Edits for Neural Machine Translation
Autor: | Marco Turchi, Matteo Negri, Marcello Federico, M. Amin Farajian |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2017 |
Předmět: |
0301 basic medicine
Domain adaptation Artificial neural network Machine translation Computer science business.industry Deep learning 02 engineering and technology computer.software_genre 03 medical and health sciences 030104 developmental biology 0202 electrical engineering electronic engineering information engineering Computational linguistics. Natural language processing 020201 artificial intelligence & image processing Artificial intelligence P98-98.5 business computer Natural language processing |
Zdroj: | Prague Bulletin of Mathematical Linguistics, Vol 108, Iss 1, Pp 233-244 (2017) |
ISSN: | 1804-0462 |
Popis: | Improving machine translation (MT) by learning from human post-edits is a powerful solution that is still unexplored in the neural machine translation (NMT) framework. Also in this scenario, effective techniques for the continuous tuning of an existing model to a stream of manual corrections would have several advantages over current batch methods. First, they would make it possible to adapt systems at run time to new users/domains; second, this would happen at a lower computational cost compared to NMT retraining from scratch or in batch mode. To attack the problem, we explore several online learning strategies to stepwise fine-tune an existing model to the incoming post-edits. Our evaluation on data from two language pairs and different target domains shows significant improvements over the use of static models. |
Databáze: | OpenAIRE |
Externí odkaz: |