Type

Journal Article

Authors

Josef van Genabith
Andy Way
Aleš Tamchyna
Prokopis Prokopidis
Vassilis Papavassiliou
Antonio Toral
Pavel Pecina

Subjects

Linguistics

Topics
english language world wide web domain adaptation statistical machine translation language pairs machine translation systems phrase based smt large scale

Domain adaptation of statistical machine translation with domain-focused web crawling. (2015)

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.
Collections Ireland -> Dublin City University -> PubMed

Full list of authors on original publication

Josef van Genabith, Andy Way, Aleš Tamchyna, Prokopis Prokopidis, Vassilis Papavassiliou, Antonio Toral, Pavel Pecina

Experts in our system

1
Josef van Genabith
Dublin City University
Total Publications: 115
 
2
Andy Way
Dublin City University
Total Publications: 229
 
3
Antonio Toral
Dublin City University
Total Publications: 18
 
4
Pavel Pecina
Dublin City University
Total Publications: 12