Neural machine translation for low-resource languages without parallel corpora
| Autor: | Jon Dehdari, Josef van Genabith, Alina Karakanta |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Linguistics and Language
Machine translation business.industry Computer science Speech recognition 02 engineering and technology Transfer-based machine translation computer.software_genre Translation (geometry) Language and Linguistics Example-based machine translation Rule-based machine translation Artificial Intelligence 020204 information systems 0202 electrical engineering electronic engineering information engineering Transliteration 020201 artificial intelligence & image processing Synchronous context-free grammar Artificial intelligence Computational linguistics business computer Software Natural language processing |
| Zdroj: | Machine Translation. 32:167-189 |
| ISSN: | 1573-0573 0922-6567 |
| Popis: | The problem of a total absence of parallel data is present for a large number of language pairs and can severely detriment the quality of machine translation. We describe a language-independent method to enable machine translation between a low-resource language (LRL) and a third language, e.g. English. We deal with cases of LRLs for which there is no readily available parallel data between the low-resource language and any other language, but there is ample training data between a closely-related high-resource language (HRL) and the third language. We take advantage of the similarities between the HRL and the LRL in order to transform the HRL data into data similar to the LRL using transliteration. The transliteration models are trained on transliteration pairs extracted from Wikipedia article titles. Then, we automatically back-translate monolingual LRL data with the models trained on the transliterated HRL data and use the resulting parallel corpus to train our final models. Our method achieves significant improvements in translation quality, close to the results that can be achieved by a general purpose neural machine translation system trained on a significant amount of parallel data. Moreover, the method does not rely on the existence of any parallel data for training, but attempts to bootstrap already existing resources in a related language. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink