Multiple Translation-Engine-based Hypotheses and Edit-Distance-based Rescoring for a Greedy Decoder for Statistical Machine Translation

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 enginesare 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.

著者

• 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

• 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
• 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

スポンサーリンク