Extracting parallel phrases from comparable data for machine translation

Mining parallel data from comparable corpora is a promising approach for overcoming the data sparseness in statistical machine translation and other natural language processing applications. In this paper, we address the task of detecting parallel phrase pairs embedded in comparable sentence pairs....

Full description

Saved in:
Bibliographic Details
Published in:Natural language engineering Vol. 22; no. 4; pp. 549 - 573
Main Authors: HEWAVITHARANA, SANJIKA, VOGEL, STEPHAN
Format: Journal Article
Language:English
Published: Cambridge, UK Cambridge University Press 01.07.2016
Subjects:
Algorithms
Alignment
Arabic language
Bilingualism
Candidates
Computational linguistics
Data mining
Data processing
English language
Extraction
Hindi language
International conferences
Language
Linguistics
Machine translation
Natural language processing
Parallel corpora
Sentences
Similarity measures
Translation
Translation systems
Translations
Urdu language
United States > US
Qatar
Japan
ISSN:1351-3249, 1469-8110
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Mining parallel data from comparable corpora is a promising approach for overcoming the data sparseness in statistical machine translation and other natural language processing applications. In this paper, we address the task of detecting parallel phrase pairs embedded in comparable sentence pairs. We present a novel phrase alignment approach that is designed to only align parallel sections bypassing non-parallel sections of the sentence. We compare the proposed approach with two other alignment methods: (1) the standard phrase extraction algorithm, which relies on the Viterbi path of the word alignment, (2) a binary classifier to detect parallel phrase pairs when presented with a large collection of phrase pair candidates. We evaluate the accuracy of these approaches using a manually aligned data set, and show that the proposed approach outperforms the other two approaches. Finally, we demonstrate the effectiveness of the extracted phrase pairs by using them in Arabic–English and Urdu–English translation systems, which resulted in improvements upto 1.2 Bleu over the baseline. The main contributions of this paper are two-fold: (1) novel phrase alignment algorithms to extract parallel phrase pairs from comparable sentences, (2) evaluating the utility of the extracted phrases by using them directly in the MT decoder.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1351-3249
1469-8110
DOI:10.1017/S1351324916000139