| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Training phrase-based SMT without explicit word aligment
Abstract : The machine translation systems usually build an initial
word-to-word alignment, before training the phrase translation pairs.
This approach requires a lot of matching between different single words of
both considered languages. In this paper, we propose a new approach for
phrase-based machine translation which does not require any word alignment.
This method is based on inter-lingual triggers retrieved by Multivariate
Mutual Information. This algorithm segments sentences into
phrases and fnds their alignments simultaneously. The main objective
of this work is to build directly valid alignments between source and
target phrases. The achieved results, in terms of performance are satisfactory
and the obtained translation table is smaller than the reference
one; this approach could be considered as an alternative to the classical
methods.
Cited literature [15 references]
https://hal.inria.fr/hal-01067051
Contributor : Kamel Smaïli <>
Submitted on : Monday, September 22, 2014 - 6:06:40 PM
Last modification on : Wednesday, October 28, 2020 - 2:20:03 PM
Contributor : Kamel Smaïli <>
Submitted on : Monday, September 22, 2014 - 6:06:40 PM
Last modification on : Wednesday, October 28, 2020 - 2:20:03 PM
File
CICLING2014Nasri.pdf
Files produced by the author(s)