TAILIEUCHUNG - Báo cáo khoa học: "Improving the IBM Alignment Models Using Variational Bayes"

Bayesian approaches have been shown to reduce the amount of overfitting that occurs when running the EM algorithm, by placing prior probabilities on the model parameters. We apply one such Bayesian technique, variational Bayes, to the IBM models of word alignment for statistical machine translation. | Improving the IBM Alignment Models Using Variational Bayes Darcey Riley and Daniel Gildea Computer Science Dept. University of Rochester Rochester NY 14627 Abstract Bayesian approaches have been shown to reduce the amount of overfitting that occurs when running the EM algorithm by placing prior probabilities on the model parameters. We apply one such Bayesian technique variational Bayes to the IBM models of word alignment for statistical machine translation. We show that using variational Bayes improves the performance of the widely used GIZA software as well as improving the overall performance of the Moses machine translation system in terms of BLEU score. 1 Introduction The IBM Models of word alignment Brown et al. 1993 along with the Hidden Markov Model HMM Vogel et al. 1996 serve as the starting point for most current state-of-the-art machine translation systems both phrase-based and syntax-based Koehn et al. 2007 Chiang 2005 Galley et al. 2004 . Both the IBM Models and the HMM are trained using the EM algorithm Dempster et al. 1977 . Recently Bayesian techniques have become widespread in applications of EM to natural language processing tasks as a very general method of controlling overfitting. For instance Johnson 2007 showed the benefits of such techniques when applied to HMMs for unsupervised part of speech tagging. In machine translation Blunsom et al. 2008 and DeNero et al. 2008 use Bayesian techniques to learn bilingual phrase pairs. In this setting which involves finding a segmentation of the input sentences into phrasal units it is particularly important to control the tendency of EM to choose longer phrases 306 which explain the training data well but are unlikely to generalize. However most state-of-the-art machine translation systems today are built on the basis of wordlevel alignments of the type generated by GIZA from the IBM Models and the HMM. Overfitting is also a problem in this context and improving these word alignment systems could be of .

TỪ KHÓA LIÊN QUAN
TAILIEUCHUNG - Chia sẻ tài liệu không giới hạn
Địa chỉ : 444 Hoang Hoa Tham, Hanoi, Viet Nam
Website : tailieuchung.com
Email : tailieuchung20@gmail.com
Tailieuchung.com là thư viện tài liệu trực tuyến, nơi chia sẽ trao đổi hàng triệu tài liệu như luận văn đồ án, sách, giáo trình, đề thi.
Chúng tôi không chịu trách nhiệm liên quan đến các vấn đề bản quyền nội dung tài liệu được thành viên tự nguyện đăng tải lên, nếu phát hiện thấy tài liệu xấu hoặc tài liệu có bản quyền xin hãy email cho chúng tôi.
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.