This paper presents a method to effectively introduce a translation dictionary into phrase-based SMT. Though SMT systems can be built with only a parallel corpus, translation dictionaries are more widely available and have many more entries than parallel corpora. A simple and low-cost method to introduce a translation dictionary is to attach a dictionary entry into a phrase table. This, however, does not work well. Target word order and even whole target sentences are often incorrect. To solve this problem, the proposed method uses high-frequency words in the training corpus. The high-frequency words may already be trained well; in other words, they may appear in the phrase table and therefore be translated with correct word order. Experimental results show the proposed method as far superior to simply attaching dictionary entries into phrase tables.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hideo OKUMA, Hirofumi YAMAMOTO, Eiichiro SUMITA, "Introducing a Translation Dictionary into Phrase-Based SMT" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 7, pp. 2051-2057, July 2008, doi: 10.1093/ietisy/e91-d.7.2051.
Abstract: This paper presents a method to effectively introduce a translation dictionary into phrase-based SMT. Though SMT systems can be built with only a parallel corpus, translation dictionaries are more widely available and have many more entries than parallel corpora. A simple and low-cost method to introduce a translation dictionary is to attach a dictionary entry into a phrase table. This, however, does not work well. Target word order and even whole target sentences are often incorrect. To solve this problem, the proposed method uses high-frequency words in the training corpus. The high-frequency words may already be trained well; in other words, they may appear in the phrase table and therefore be translated with correct word order. Experimental results show the proposed method as far superior to simply attaching dictionary entries into phrase tables.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.7.2051/_p
Copy
@ARTICLE{e91-d_7_2051,
author={Hideo OKUMA, Hirofumi YAMAMOTO, Eiichiro SUMITA, },
journal={IEICE TRANSACTIONS on Information},
title={Introducing a Translation Dictionary into Phrase-Based SMT},
year={2008},
volume={E91-D},
number={7},
pages={2051-2057},
abstract={This paper presents a method to effectively introduce a translation dictionary into phrase-based SMT. Though SMT systems can be built with only a parallel corpus, translation dictionaries are more widely available and have many more entries than parallel corpora. A simple and low-cost method to introduce a translation dictionary is to attach a dictionary entry into a phrase table. This, however, does not work well. Target word order and even whole target sentences are often incorrect. To solve this problem, the proposed method uses high-frequency words in the training corpus. The high-frequency words may already be trained well; in other words, they may appear in the phrase table and therefore be translated with correct word order. Experimental results show the proposed method as far superior to simply attaching dictionary entries into phrase tables.},
keywords={},
doi={10.1093/ietisy/e91-d.7.2051},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Introducing a Translation Dictionary into Phrase-Based SMT
T2 - IEICE TRANSACTIONS on Information
SP - 2051
EP - 2057
AU - Hideo OKUMA
AU - Hirofumi YAMAMOTO
AU - Eiichiro SUMITA
PY - 2008
DO - 10.1093/ietisy/e91-d.7.2051
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2008
AB - This paper presents a method to effectively introduce a translation dictionary into phrase-based SMT. Though SMT systems can be built with only a parallel corpus, translation dictionaries are more widely available and have many more entries than parallel corpora. A simple and low-cost method to introduce a translation dictionary is to attach a dictionary entry into a phrase table. This, however, does not work well. Target word order and even whole target sentences are often incorrect. To solve this problem, the proposed method uses high-frequency words in the training corpus. The high-frequency words may already be trained well; in other words, they may appear in the phrase table and therefore be translated with correct word order. Experimental results show the proposed method as far superior to simply attaching dictionary entries into phrase tables.
ER -