A method of generating translations of unseen n-grams by using proportional analogy

Juan Luo, Yves Lepage

Research output: Contribution to journalArticle

Abstract

In recent years, statistical machine translation has gained much attention. The phrase-based statistical machine translation model has made significant advancement in translation quality over the word-based model. In this paper, we attempt to apply the technique of proportional analogy to statistical machine translation systems. We propose a novel approach to apply proportional analogy to generate translations of unseen n-grams from the phrase table for phrase-based statistical machine translation. Experiments are conducted with two datasets of different sizes. We also investigate two methods to integrate n-grams translations produced by proportional analogy into the state-of-the-art statistical machine translation system, Moses.1 The experimental results show that unseen n-grams translations generated using the technique of proportional analogy are rewarding for statistical machine translation systems with small datasets.

Original languageEnglish
JournalIEEJ Transactions on Electrical and Electronic Engineering
DOIs
Publication statusAccepted/In press - 2016

Fingerprint

Experiments

Keywords

  • Phrase table
  • Proportional analogy
  • Statistical machine translation
  • Unseen n-grams

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

@article{1bfb3ad9ba1e4ea0b03fc19f68630004,
title = "A method of generating translations of unseen n-grams by using proportional analogy",
abstract = "In recent years, statistical machine translation has gained much attention. The phrase-based statistical machine translation model has made significant advancement in translation quality over the word-based model. In this paper, we attempt to apply the technique of proportional analogy to statistical machine translation systems. We propose a novel approach to apply proportional analogy to generate translations of unseen n-grams from the phrase table for phrase-based statistical machine translation. Experiments are conducted with two datasets of different sizes. We also investigate two methods to integrate n-grams translations produced by proportional analogy into the state-of-the-art statistical machine translation system, Moses.1 The experimental results show that unseen n-grams translations generated using the technique of proportional analogy are rewarding for statistical machine translation systems with small datasets.",
keywords = "Phrase table, Proportional analogy, Statistical machine translation, Unseen n-grams",
author = "Juan Luo and Yves Lepage",
year = "2016",
doi = "10.1002/tee.22221",
language = "English",
journal = "IEEJ Transactions on Electrical and Electronic Engineering",
issn = "1931-4973",
publisher = "John Wiley and Sons Inc.",

}

TY - JOUR

T1 - A method of generating translations of unseen n-grams by using proportional analogy

AU - Luo, Juan

AU - Lepage, Yves

PY - 2016

Y1 - 2016

N2 - In recent years, statistical machine translation has gained much attention. The phrase-based statistical machine translation model has made significant advancement in translation quality over the word-based model. In this paper, we attempt to apply the technique of proportional analogy to statistical machine translation systems. We propose a novel approach to apply proportional analogy to generate translations of unseen n-grams from the phrase table for phrase-based statistical machine translation. Experiments are conducted with two datasets of different sizes. We also investigate two methods to integrate n-grams translations produced by proportional analogy into the state-of-the-art statistical machine translation system, Moses.1 The experimental results show that unseen n-grams translations generated using the technique of proportional analogy are rewarding for statistical machine translation systems with small datasets.

AB - In recent years, statistical machine translation has gained much attention. The phrase-based statistical machine translation model has made significant advancement in translation quality over the word-based model. In this paper, we attempt to apply the technique of proportional analogy to statistical machine translation systems. We propose a novel approach to apply proportional analogy to generate translations of unseen n-grams from the phrase table for phrase-based statistical machine translation. Experiments are conducted with two datasets of different sizes. We also investigate two methods to integrate n-grams translations produced by proportional analogy into the state-of-the-art statistical machine translation system, Moses.1 The experimental results show that unseen n-grams translations generated using the technique of proportional analogy are rewarding for statistical machine translation systems with small datasets.

KW - Phrase table

KW - Proportional analogy

KW - Statistical machine translation

KW - Unseen n-grams

UR - http://www.scopus.com/inward/record.url?scp=84976243103&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976243103&partnerID=8YFLogxK

U2 - 10.1002/tee.22221

DO - 10.1002/tee.22221

M3 - Article

JO - IEEJ Transactions on Electrical and Electronic Engineering

JF - IEEJ Transactions on Electrical and Electronic Engineering

SN - 1931-4973

ER -