TAILIEUCHUNG - Báo cáo khoa học: "Prefix Probabilities from Stochastic Tree Adjoining Grammars*"

Language models for speech recognition typically use a probability model of the form Pr(an[al,a2,.,an-i). Stochastic grammars, on the other hand, are typically used to assign structure to utterances, A language model of the above form is constructed from such grammars by computing the prefix probability ~we~* Pr(), where w represents all possible terminations of the prefix . The main result in this paper is an algorithm to compute such prefix probabilities given a stochastic Tree Adjoining Grammar (TAG). The algorithm achieves the required computation in O(n 6) time. . | Prefix Probabilities from Stochastic Tree Adjoining Grammars Mark-Jan Nederhof DFKI Stuhlsatzenhausweg 3 D-66123 Saarbriicken Germany nederhof Anoop Sarkar Dept of Computer and Info. Sc. Univ of Pennsylvania 200 South 33rd Street Philadelphia PA 19104 USA Giorgio Satta Dip. di Elettr. e Inf. Univ di Padova via Gradenigo 6 A 35131 Padova Italy Abstract Language models for speech recognition typically use a probability model of the form Pr an ai a2 . an-i . Stochastic grammars on the other hand are typically used to assign structure to utterances. A language model of the above form is constructed from such grammars by computing the prefix probability Pr ai anw where U represents all possible terminations of the prefix O1 an. The main result in this paper is an algorithm to compute such prefix probabilities given a stochastic Tree Adjoining Grammar TAG . The algorithm achieves the required computation in ỡ n6 time. The probability of subderivations that do not derive any words in the prefix but contribute structurally to its derivation are precomputed to achieve termination. This algorithm enables existing corpus-based estimation techniques for stochastic TAGs to be used for language modelling. 1 Introduction Given some word sequence ai an_i speech recognition language models are used to hypothesize the next word an which could be any word from the vocabulary E. This is typically done using a probability model Pr an ai . an-i . Based on the assumption that modelling the hidden structure of nat Part of this research was done while the first and the third authors were visiting the Institute for Research in Cognitive Science University of Pennsylvania. The first author was supported by the German Federal Ministry of Education Science Research and Technology BMBF in the framework of the Verbmobil Project under Grant 01 IV 701 VO and by the Priority Programme Language and Speech Technology which is sponsored by NWO Dutch

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.