Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
| Autor: | Greg S. Corrado, Mike Schuster, Fernanda B. Viégas, Zhifeng Chen, Melvin Johnson, Nikhil Thorat, Jeffrey Dean, Quoc V. Le, Macduff Hughes, Martin Wattenberg, Yonghui Wu, Maxim Krikun |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Linguistics and Language
Interlingua Vocabulary Machine translation Computer science Speech recognition media_common.quotation_subject 02 engineering and technology computer.software_genre Bridging (programming) Rule-based machine translation Artificial Intelligence 020204 information systems 0202 electrical engineering electronic engineering information engineering media_common business.industry Communication Transfer-based machine translation language.human_language Computer Science Applications Human-Computer Interaction language Computer-assisted translation 020201 artificial intelligence & image processing Artificial intelligence business computer Natural language processing Sentence |
| Zdroj: | Transactions of the Association for Computational Linguistics. 5:339-351 |
| ISSN: | 2307-387X |
| DOI: | 10.1162/tacl_a_00065 |
| Popis: | We propose a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages. Our solution requires no changes to the model architecture from a standard NMT system but instead introduces an artificial token at the beginning of the input sentence to specify the required target language. Using a shared wordpiece vocabulary, our approach enables Multilingual NMT systems using a single model. On the WMT’14 benchmarks, a single multilingual model achieves comparable performance for English→French and surpasses state-of-theart results for English→German. Similarly, a single multilingual model surpasses state-of-the-art results for French→English and German→English on WMT’14 and WMT’15 benchmarks, respectively. On production corpora, multilingual models of up to twelve language pairs allow for better translation of many individual pairs. Our models can also learn to perform implicit bridging between language pairs never seen explicitly during training, showing that transfer learning and zero-shot translation is possible for neural translation. Finally, we show analyses that hints at a universal interlingua representation in our models and also show some interesting examples when mixing languages. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|