Abstract
Statistical machine translation models typically learn phrase or syntactic translation rules extracted from parallel data with word alignments, but the approach suffers from a problem where some desirable rules are blocked due to word alignment mistakes. Many researchers focus on improving the translation rule extraction by correcting word alignment mistakes, while this paper presents a phrase-based forced decoding method to address this issue, and a rule-augmentation approach is proposed to improve the quality of translation based on the translation rules extracted by forced decoding method. Experiment on Chinese-English translation task demonstrates significant improvements over the baseline system.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: 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.
