Translation of Chunks and Clauses
Between words and sentences, we can identify chunks (noun phrases, verb groups) and clauses (a verb with all its arguments and adjuncts) as major syntactic units.
Translating Chunks And Clauses is the main subject of 9 publications. 9 are discussed here.
Publications
To approach the problem of the translation of sentences, one strategy is to break up the problem along syntactic lines, be it clauses
H. Kashioka and T. Maruyama and Hideki Tanaka (2003):
Building a Parallel Corpus for Monologue with Clause Alignment, Proceedings of the MT Summit IX
@inproceedings{Kashioka:2003,
author = {H. Kashioka and T. Maruyama and Hideki Tanaka},
title = { Building a Parallel Corpus for Monologue with Clause Alignment},
url = {
http://www.mt-archive.info/MTS-2003-Kashioka.pdf},
googlescholar = {12985434215675889781},
booktitle = {Proceedings of the {MT} Summit IX},
year = 2003
}
or syntactic chunks
(Koehn and Knight, 2002;
Schafer, Charles and Yarowsky, David (2003):
Statistical Machine Translation Using Coercive Two-Level Syntactic Transduction, Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing
@inproceedings{Schafer:2003,
author = {Schafer, Charles and Yarowsky, David},
title = {Statistical Machine Translation Using Coercive Two-Level Syntactic Transduction},
booktitle = {Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing},
editor = {Michael Collins and Mark Steedman},
url = {
http://www.aclweb.org/anthology/W03-1002.pdf},
pages = {9--16},
year = 2003
}
Schafer and Yarowsky, 2003;
Charles Schafer and David Yarowsky (2003):
A Two-Level Syntax-Based Approach to Arabic-English Statistical Machine Translation, MT Summit IX Workshop on Machine Translation for Semitic Languages: Issues and Approaches
@inproceedings{Schafer:2003b,
author = {Charles Schafer and David Yarowsky},
title = {A Two-Level Syntax-Based Approach to {Arabic-English} Statistical Machine Translation},
url = {
http://www.cs.cmu.edu/~alavie/Sem-MT-wshp/Schafer+Yarowsky\_paper.pdf},
googlescholar = {6647907122888764703},
booktitle = {MT Summit IX Workshop on Machine Translation for Semitic Languages: Issues and Approaches},
year = 2003
}
Schafer and Yarowsky, 2003b). This strategy also allows for special components for the translation of more basic syntactic elements such as noun phrases
Koehn, Philipp and Knight, Kevin (2003):
Feature-Rich Statistical Translation of Noun Phrases, Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics
mentioned in Translating Chunks And Clauses and Syntactic Reranking@inproceedings{Koehn:2003np,
author = {Koehn, Philipp and Knight, Kevin},
title = {Feature-Rich Statistical Translation of Noun Phrases},
booktitle = {Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics},
editor = {Erhard Hinrichs and Dan Roth},
url = {
http://www.aclweb.org/anthology/P03-1040.pdf},
pages = {311--318},
year = 2003
}
(Koehn and Knight, 2003) or noun compounds
Takaaki Tanaka and Timothy Baldwin (2003):
Translation Selection for Japanese-English Noun-Noun Compounds, Proceedings of the MT Summit IX
@inproceedings{Tanaka:2003,
author = {Takaaki Tanaka and Timothy Baldwin},
title = { Translation Selection for {Japanese-English} Noun-Noun Compounds},
url = {
http://www.mt-archive.info/MTS-2003-Tanaka.pdf},
googlescholar = {18252543100444861578},
booktitle = {Proceedings of the {MT} Summit IX},
year = 2003
}
(Tanaka and Baldwin, 2003).
Karolina Owczarzak and Bart Mellebeek and Declan Groves and Josef van Genabith and Andy Way (2006):
Wrapper Syntax for Example-based Machine Translation, 5th Conference of the Association for Machine Translation in the Americas (AMTA)
@InProceedings{Owczarzak:2006:AMTA,
author = {Karolina Owczarzak and Bart Mellebeek and Declan Groves and Josef van Genabith and Andy Way},
title = {Wrapper Syntax for Example-based Machine Translation},
url = {
http://doras.dcu.ie/15282/1/OwczarzakEtAl\_amta\_06.pdf},
googlescholar = {9798525039875720419},
booktitle = {5th Conference of the Association for Machine Translation in the Americas (AMTA)},
month = {August},
address = {Boston, Massachusetts},
year = 2006
}
Owczarzak et al. (2006);
Bart Mellebeek and Karolina Owczarzak and Declan Groves and Josef van Genabith and Andy Way (2006):
A Syntactic Skeleton for Statistical Machine Translation, Proceedings of the 11th Conference of the European Association for Machine Translation (EAMT)
@InProceedings{Mellebeek:2006:EAMT,
author = {Bart Mellebeek and Karolina Owczarzak and Declan Groves and Josef van Genabith and Andy Way},
title = {A Syntactic Skeleton for Statistical Machine Translation},
url = {
http://doras.dcu.ie/15279/1/MellebeekEtAl\_eamt\_06.pdf},
googlescholar = {1530943956457310744},
booktitle = {Proceedings of the 11th Conference of the European Association for Machine Translation (EAMT)},
month = {June},
address = {Oslo, Norway},
year = 2006
}
Mellebeek et al. (2006) break up sentence into chunks, translating the chunks separately and combine the translations into a transformed skeleton.
Hewavitharana et al. (2007) augment a phrase-based model with translations for noun phrases that are translated separately.
Benchmarks
Discussion
Related Topics
New Publications
