A method of generating translations of unseen n‐grams by using proportional analogy. Issue 3 (15th February 2016)

• Record Type: Journal Article
• Authors: Luo, Juan; Lepage, Yves
• Is Part Of: IEEJ transactions on electrical and electronic engineering. Volume 11:Issue 3(2016:May)
• Page Start: 325
• Page End: 330
• Publication Date: 2016-02-15
• Subjects: statistical machine translation -- proportional analogy -- unseen n‐grams -- phrase table; Electrical engineering -- Periodicals; Electronics -- Periodicals; 621.3
• DOI: 10.1002/tee.22221
• Languages: English
• ISSNs: 1931-4973

Abstract

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. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.