Domain Adaptation of Statistical Machine Translation using Web-Crawled Resources: A Case Study
|Authors:||Pavel Pecina; Antonio Toral; Vassilis Papavassiliou; Prokopis Prokopidis; Josef van Genabith|
|Book title:||Proceedings of the 16th Annual Conference of the European Association for Machine Translation|
We tackle the problem of domain adaptation of Statistical Machine Translation by exploiting domain-specific data acquired by domain-focused web-crawling. We design and evaluate a procedure for automatic acquisition of monolingual and parallel data and their exploitation for training, tuning, and testing in a phrase-based Statistical Machine Translation system. We present a strategy for using such resources depending on their availability and quantity supported by results of a large-scale evaluation on the domains of Natural Environment and Labour Legislation and two language pairs: English--French, English--Greek. The average observed increase of BLEU is substantial at 49.5% relative.