Paraphrase Lattice for Statistical Machine Translation
スポンサーリンク
概要
- 論文の詳細を見る
Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the translation of German because it can handle input ambiguities such as speech recognition ambiguities and German word segmentation ambiguities. In this paper, we show that lattice decoding is also useful for handling input variations. “Input variations” refers to the differences in input texts with the same meaning. Given an input sentence, we build a lattice which represents paraphrases of the input sentence. We call this a paraphrase lattice. Then, we give the paraphrase lattice as an input to a lattice decoder. The lattice decoder searches for the best path of the paraphrase lattice and outputs the best translation. Experimental results using the IWSLT dataset and the Europarl dataset show that our proposed method obtains significant gains in BLEU scores.
- （社）電子情報通信学会の論文
- 2011-06-01
著者
-
Sumita Eiichiro
National Inst. Communications Technol. Kyoto‐fu Jpn
-
Utiyama Masao
National Institute Of Information And Communications Technology
-
Onishi Takashi
National Institute Of Information And Communications Technology
関連論文
- A Reordering Model Using a Source-Side Parse-Tree for Statistical Machine Translation
- Splitting Input for Machine Translation Using N-gram Language Model Together with Utterance Similarity(Natural Language Processing)
- E_019 Achilles : A Chinese Morphological Analyzer
- Use of Multiple Documents as Evidence with Decreased Adding in a Japanese Question-answering System
- Imposing Constraints from the Source Tree on ITG Constraints for SMT
- Introducing a Translation Dictionary into Phrase-Based SMT
- Constraining a Generative Word Alignment Model with Discriminative Output
- Bilingual Cluster Based Models for Statistical Machine Translation
- Computer-Assisted Reading Materials Related to Coursebooks
- Exploring Sampling Methodology for Obtaining Reliable Text Coverage
- Paraphrase Lattice for Statistical Machine Translation
- An Empirical Comparison of Parsers in Constraining Reordering for E-J Patent Machine Translation
- Japanese Argument Reordering Based on Dependency Structure for Statistical Machine Translation
- An Empirical Comparison of Parsers in Constraining Reordering for E-J Patent Machine Translation
- Database of Human Evaluations of Machine Translation Systems for Patent Translation
- How to Translate Dialects: A Segmentation-Centric Pivot Translation Approach
- Joint Phrase Alignment and Extraction for Statistical Machine Translation
- Joint Phrase Alignment and Extraction for Statistical Machine Translation
- Use of Multiple Documents as Evidence with Decreased Adding in a Japanese Question-answering System
- Database of Human Evaluations of Machine Translation Systems for Patent Translation