Loading...
Loading...

Go to the content (press return)

Why Catalan-Spanish Neural Machine Translation? Analysis, comparison and combination with standard Rule and Phrase-based technologies

Author
Ruiz, M.
Type of activity
Presentation of work at congresses
Name of edition
4th Workshop on NLP for Similar Languages, Varieties and Dialects
Date of publication
2017
Presentation's date
2017-04-03
Book of congress proceedings
Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)
First page
55
Last page
62
Repository
http://hdl.handle.net/2117/102886 Open in new window
URL
http://web.science.mq.edu.au/~smalmasi/vardial4/pdf/VarDial07.pdf Open in new window
Abstract
Catalan and Spanish are two related languages given that both derive from Latin. They share similarities in several linguistic levels including morphology, syntax and semantics. This makes them particularly interesting for the MT task. Given the recent appearance and popularity of neural MT, this paper analyzes the performance of this new approach compared to the well-established rule-based and phrase-based MT systems. Experiments are reported on a large database of 180 million words. Results, i...
Citation
Ruiz, M. Why Catalan-Spanish Neural Machine Translation? Analysis, comparison and combination with standard Rule and Phrase-based technologies. A: Workshop on NLP for Similar Languages, Varieties and Dialects. "Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)". 2017, p. 55-62.
Keywords
Machine translation
Group of research
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
TALP - Centre for Language and Speech Technologies and Applications
VEU - Speech Processing Group

Participants

Attachments