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.
Highlights
Recent advances in statistical machine translation (SMT) have improved machine translation (MT) quality to such an extent that it can be successfully used in industrial processes (e.g., Flournoy and Duran 2009)
In this paper, we tackle the problem of domain adaptation of statistical machine translation (SMT) by exploiting domain-specific data acquired by domainfocused crawling of text from the World Wide Web
From the analysis presented above, we conclude that a phrase-based SMT (PB-SMT) system tuned on data from the same domain as the training data strongly prefers to construct translations consisting of long phrases
Summary
Recent advances in statistical machine translation (SMT) have improved machine translation (MT) quality to such an extent that it can be successfully used in industrial processes (e.g., Flournoy and Duran 2009) This mostly happens only in specific domains where ample training data is available (e.g., Wu et al 2008). Tuning with and for specific domains (while using generic training data) allows the MT system to stitch together translations from smaller fragments which, in this case, leads to improved translation quality. Such tuning requires only small development sets which can be harvested automatically from the web with minimal human intervention; no manual cleaning of the development data is necessary.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.