Loading...
Loading...

Go to the content (press return)

Coverage for character based neural machine translation

Author
Kazimi, B.; Ruiz, M.
Type of activity
Journal article
Journal
Procesamiento del lenguaje natural (SEPLN)
Date of publication
2017-09-22
Volume
59
First page
99
Last page
106
Repository
http://hdl.handle.net/2117/107805 Open in new window
URL
http://journal.sepln.org/sepln/ojs/ojs/index.php/pln/article/view/5498 Open in new window
Abstract
In recent years, Neural Machine Translation (NMT) has achieved state-of-the-art performance in translating from a language; source language, to another; target language. However, many of the proposed methods use word embedding techniques to represent a sentence in the source or target language. Character embedding techniques for this task has been suggested to represent the words in a sentence better. Moreover, recent NMT models use attention mechanism where the most relevant words in a source s...
Citation
Kazimi, B., Ruiz, M. Coverage for character based neural machine translation. "Procesamiento del lenguaje natural (SEPLN)", 22 Setembre 2017, vol. 59, p. 99-106.
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