The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este artigo apresenta um método para introduzir efetivamente um dicionário de tradução em SMT baseado em frases. Embora os sistemas SMT possam ser construídos apenas com um corpus paralelo, os dicionários de tradução estão mais amplamente disponíveis e têm muito mais entradas do que os corpora paralelos. Um método simples e de baixo custo para introduzir um dicionário de tradução é anexar uma entrada de dicionário a uma tabela de frases. Isso, no entanto, não funciona bem. A ordem das palavras-alvo e até mesmo frases-alvo inteiras costumam estar incorretas. Para resolver este problema, o método proposto utiliza palavras de alta frequência no corpus de treinamento. As palavras de alta frequência podem já estar bem treinadas; em outras palavras, elas podem aparecer na tabela de frases e, portanto, ser traduzidas na ordem correta das palavras. Resultados experimentais mostram que o método proposto é muito superior à simples anexação de entradas de dicionário em tabelas de frases.
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.
Copiar
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
Copiar
@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},}
Copiar
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 -