Chinese–Spanish neural machine translation enhanced with character and word bitmap fonts
Visualitza/Obre
Cita com:
hdl:2117/104271
Tipus de documentArticle
Data publicació2017-04-06
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya
Abstract
Recently, machine translation systems based on neural networks have reached state-of-the-art results for some pairs of languages (e.g., German–English). In this paper, we are investigating the performance of neural machine translation in Chinese–Spanish, which is a challenging language pair. Given that the meaning of a Chinese word can be related to its graphical representation, this work aims to enhance neural machine translation by using as input a combination of: words or characters and their corresponding bitmap fonts. The fact of performing the interpretation of every word or character as a bitmap font generates more informed vectorial representations. Best results are obtained when using words plus their bitmap fonts obtaining an improvement (over a competitive neural MT baseline system) of almost six BLEU, five METEOR points and ranked coherently better in the human evaluation.
CitacióRuiz, M., Aldón, D., Fonollosa, J. A. R. Chinese–Spanish neural machine translation enhanced with character and word bitmap fonts. "Machine translation", 6 Abril 2017, p. 1-13.
ISSN0922-6567
Versió de l'editorhttps://link.springer.com/article/10.1007%2Fs10590-017-9196-0
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
bitmap-mt.pdf | 850,9Kb | Visualitza/Obre |