Paper Info
Title
Domain adaptation of statistical machine translation with domain-focused web crawling
Abstract
In this paper, we tackle the problem of domain adaptation of statistical machine translation (SMT) by exploiting domain-specific data acquired by domain-focused crawling of text from the World Wide Web. We design and empirically evaluate a procedure for automatic acquisition of monolingual and parallel text and their exploitation for system training, tuning, and testing in a phrase-based SMT framework. We present a strategy for using such resources depending on their availability and quantity supported by results of a large-scale evaluation carried out for the domains of environment and labour legislation, two language pairs (English---French and English---Greek) and in both directions: into and from English. In general, machine translation systems trained and tuned on a general domain perform poorly on specific domains and we show that such systems can be adapted successfully by retuning model parameters using small amounts of parallel in-domain data, and may be further improved by using additional monolingual and parallel training data for adaptation of language and translation models. The average observed improvement in BLEU achieved is substantial at 15.30 points absolute.
Year
DOI
Venue
2015
10.1007/s10579-014-9282-3
Language Resources and Evaluation
Keywords
Field
DocType
Domain adaptation,Optimisation,Statistical machine translation,Web crawling
Training set,Crawling,Domain adaptation,Computer science,Evaluation of machine translation,Machine translation,Phrase,Natural language processing,Transfer-based machine translation,Artificial intelligence,Web crawler
Journal
Volume
Issue
ISSN
49
1
1574-020X
Citations 
PageRank 
References 
3
0.39
58
Authors
7
Name
Order
Citations
PageRank
Pavel Pecina155852.31
Antonio Toral24710.43
Vassilis Papavassiliou312010.74
Prokopis411410.95
Aleš Tamchyna511514.76
Andy Way6881126.78
Josef van Genabith71037105.64