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
본 논문에서는 기존의 구문 기반 통계기계번역(SMT) 시스템을 사용하여 번역할 수 없는 OOV(Out of Vocabulary) 단어를 처리하는 방법을 제안합니다. 특정 OOV 단어에 대해 어휘 근사 기술을 사용하여 훈련 데이터에서 발생하는 철자 및 굴절 단어 변형을 식별합니다. 그러면 소스 문장의 모든 OOV 단어가 훈련 코퍼스에서 찾은 적절한 단어 변형으로 대체되어 입력의 OOV 단어 수가 줄어듭니다. 또한, 이러한 단어 번역의 적용 범위를 늘리기 위해 원래 구문 테이블에 단일 단어 항목이 없지만 문맥에만 나타나는 모든 소스 언어 단어에 대해 새로운 구문 번역을 추가하여 SMT 번역 모델을 확장합니다. 더 큰 문구. 힌디어를 영어, 중국어, 일본어로 번역하기 위해 제안된 방법의 효율성을 조사합니다.
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.
부
Michael PAUL, Karunesh ARORA, Eiichiro SUMITA, "Translation of Untranslatable Words -- Integration of Lexical Approximation and Phrase-Table Extension Techniques into Statistical Machine Translation" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 12, pp. 2378-2385, December 2009, doi: 10.1587/transinf.E92.D.2378.
Abstract: This paper proposes a method for handling out-of-vocabulary (OOV) words that cannot be translated using conventional phrase-based statistical machine translation (SMT) systems. For a given OOV word, lexical approximation techniques are utilized to identify spelling and inflectional word variants that occur in the training data. All OOV words in the source sentence are then replaced with appropriate word variants found in the training corpus, thus reducing the number of OOV words in the input. Moreover, in order to increase the coverage of such word translations, the SMT translation model is extended by adding new phrase translations for all source language words that do not have a single-word entry in the original phrase-table but only appear in the context of larger phrases. The effectiveness of the proposed methods is investigated for the translation of Hindi to English, Chinese, and Japanese.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.2378/_p
부
@ARTICLE{e92-d_12_2378,
author={Michael PAUL, Karunesh ARORA, Eiichiro SUMITA, },
journal={IEICE TRANSACTIONS on Information},
title={Translation of Untranslatable Words -- Integration of Lexical Approximation and Phrase-Table Extension Techniques into Statistical Machine Translation},
year={2009},
volume={E92-D},
number={12},
pages={2378-2385},
abstract={This paper proposes a method for handling out-of-vocabulary (OOV) words that cannot be translated using conventional phrase-based statistical machine translation (SMT) systems. For a given OOV word, lexical approximation techniques are utilized to identify spelling and inflectional word variants that occur in the training data. All OOV words in the source sentence are then replaced with appropriate word variants found in the training corpus, thus reducing the number of OOV words in the input. Moreover, in order to increase the coverage of such word translations, the SMT translation model is extended by adding new phrase translations for all source language words that do not have a single-word entry in the original phrase-table but only appear in the context of larger phrases. The effectiveness of the proposed methods is investigated for the translation of Hindi to English, Chinese, and Japanese.},
keywords={},
doi={10.1587/transinf.E92.D.2378},
ISSN={1745-1361},
month={December},}
부
TY - JOUR
TI - Translation of Untranslatable Words -- Integration of Lexical Approximation and Phrase-Table Extension Techniques into Statistical Machine Translation
T2 - IEICE TRANSACTIONS on Information
SP - 2378
EP - 2385
AU - Michael PAUL
AU - Karunesh ARORA
AU - Eiichiro SUMITA
PY - 2009
DO - 10.1587/transinf.E92.D.2378
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2009
AB - This paper proposes a method for handling out-of-vocabulary (OOV) words that cannot be translated using conventional phrase-based statistical machine translation (SMT) systems. For a given OOV word, lexical approximation techniques are utilized to identify spelling and inflectional word variants that occur in the training data. All OOV words in the source sentence are then replaced with appropriate word variants found in the training corpus, thus reducing the number of OOV words in the input. Moreover, in order to increase the coverage of such word translations, the SMT translation model is extended by adding new phrase translations for all source language words that do not have a single-word entry in the original phrase-table but only appear in the context of larger phrases. The effectiveness of the proposed methods is investigated for the translation of Hindi to English, Chinese, and Japanese.
ER -