Multiple Translation-Engine-based Hypotheses and Edit-Distance-based Rescoring for a Greedy Decoder for Statistical Machine Translation(Natural-Language Processing)
スポンサーリンク
概要
- 論文の詳細を見る
This paper extends a greedy decoder for statistical machine translation (SMT), which searches for an optimal translation by using SMT models starting from a decoder seed, i.e., the source language input paired with an initial translation hypothesis. First, the outputs generated by multiple translation engines are utilized as the initial translation hypotheses, whereby their variations reduce local optima problems inherent in the search. Second, a rescoring method based on the edit-distance between the initial translation hypothesis and the outputs of the decoder is used to compensate for problems of conventional greedy decoding solely based on statistical models. Our approach is evaluated for the translation of dialogues in the travel domain, and the results show that it drastically improves translation quality.
- 一般社団法人情報処理学会の論文
- 2005-11-15
著者
-
SUMITA Eiichiro
NICT
-
SUMITA Eiichiro
ATR Spoken Language Translation Research Laboratories
-
Paul Michael
Atr Spoken Language Communication Research Laboratories:graduate School Of Science And Technology Ko
-
YAMAMOTO Seiichi
ATR Spoken Language Translation Research Laboratories
-
Sumita Eiichiro
Nict Kyoto‐shi Jpn
-
Yamamoto Seiichi
Atr Spoken Language Communication Research Laboratories:department Of Information Systems Design Dos
-
Paul Michael
ATR Spoken Language Communication Research Laboratories
-
Sumita Eiichiro
ATR Spoken Language Communication Research Laboratories
関連論文
- Class-Dependent Modeling for Dialog Translation
- Class-Dependent Modeling for Dialog Translation
- Splitting Input for Machine Translation Using N-gram Language Model Together with Utterance Similarity(Natural Language Processing)
- An Objective Method for Evaluating Speech Translation System : Using a Second Language Learner's Corpus(Speech Corpora and Related Topics, Corpus-Based Speech Technologies)
- Introducing a Translation Dictionary into Phrase-Based SMT
- Proposal of an Evaluation Set Selection Method for a Corpus-Based Speech Translation Technology
- Training Set Selection for Building Compact and Efficient Language Models
- Translation of Untranslatable Words-Integration of Lexical Approximation and Phrase-Table Extension Techniques into Statistical Machine Translation
- A trainable method for pronominal anaphora resolution using shallow information
- Multiple Translation-Engine-based Hypotheses and Edit-Distance-based Rescoring for a Greedy Decoder for Statistical Machine Translation(Natural-Language Processing)
- Multiple Translation-Engine-based Hypotheses and Edit-Distance-based Rescoring for a Greedy Decoder for Statistical Machine Translation
- A Bayesian Model of Transliteration and Its Human Evaluation When Integrated into a Machine Translation System