MT model space: statistical versus compositional versus example-based machine translation
D. Wu. Machine Translation, 19 (3):
213--227(2005)
Abstract
Abstract We offer a perspective on EBMT from a statistical MT standpoint, by developing a three-dimensional MT model space based on three pairs of definitions: (1) logical versus statistical MT, (2) schema-based versus example-based MT, and (3) lexical versus compositional MT. Within this space we consider the interplay of three key ideas in the evolution of transfer, example-based, and statistical approaches to MT. We depict how all translation models face these issues in one way or another, regardless of the school of thought, and suggest where the real questions for the future may lie.
%0 Journal Article
%1 Wu2005
%A Wu, Dekai
%D 2005
%J Machine Translation
%K Estad{\'{\i}}stica,Modelos,Traduccion autom{\'{a}}tica
%N 3
%P 213--227
%T MT model space: statistical versus compositional versus example-based machine translation
%U http://dx.doi.org/10.1007/s10590-006-9009-3
%V 19
%X Abstract We offer a perspective on EBMT from a statistical MT standpoint, by developing a three-dimensional MT model space based on three pairs of definitions: (1) logical versus statistical MT, (2) schema-based versus example-based MT, and (3) lexical versus compositional MT. Within this space we consider the interplay of three key ideas in the evolution of transfer, example-based, and statistical approaches to MT. We depict how all translation models face these issues in one way or another, regardless of the school of thought, and suggest where the real questions for the future may lie.
%Z Language: eng
@article{Wu2005,
abstract = {Abstract We offer a perspective on EBMT from a statistical MT standpoint, by developing a three-dimensional MT model space based on three pairs of definitions: (1) logical versus statistical MT, (2) schema-based versus example-based MT, and (3) lexical versus compositional MT. Within this space we consider the interplay of three key ideas in the evolution of transfer, example-based, and statistical approaches to MT. We depict how all translation models face these issues in one way or another, regardless of the school of thought, and suggest where the real questions for the future may lie.},
added-at = {2015-12-01T11:35:13.000+0100},
annote = {Language: eng},
author = {Wu, Dekai},
biburl = {https://www.bibsonomy.org/bibtex/24dd9a6bb747c91a147c7dd0d0423b38d/sofiagruiz92},
interhash = {67738a72fd675daaa7d92368bbc22fa5},
intrahash = {4dd9a6bb747c91a147c7dd0d0423b38d},
journal = {Machine Translation},
keywords = {Estad{\'{\i}}stica,Modelos,Traduccion autom{\'{a}}tica},
number = 3,
pages = {213--227},
timestamp = {2015-12-01T11:35:13.000+0100},
title = {{MT model space: statistical versus compositional versus example-based machine translation}},
url = {http://dx.doi.org/10.1007/s10590-006-9009-3},
volume = 19,
year = 2005
}