Abstract
This paper proposes a multi-classifier combination strategy to improve translation error detection performance for statistical machine translation (SMT). Specifically, two different classifiers – Maximum Entropy (MaxEnt) and Support Vector Machine (SVM) – over different features perform a binary classification and export classification probabilities for either class. Then a probability product rule based multi-classifier combination strategy is employed to fuse these two classifiers to decrease the classification error rate (CER). Three typical word posterior probabilities (WPP) and three linguistic features as well as their combinations are used in the experiments conducted on Chinese-to-English NIST data sets. Experimental results show that the combination of multiple classifiers reduce the CER by relative 0.15%, 0.94%, and 1.52% compared to the SVM classifier, and relative 1.73%, 1.72%, 2.02% compared to the MaxEnt classifier over three different feature combinations.
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.
