TAILIEUCHUNG - Báo cáo khoa học: "Discriminative Training and Maximum Entropy Models for Statistical Machine Translation"

We present a framework for statistical machine translation of natural languages based on direct maximum entropy models, which contains the widely used source-channel approach as a special case. All knowledge sources are treated as feature functions, which depend on the source language sentence, the target language sentence and possible hidden variables. This approach allows a baseline machine translation system to be extended easily by adding new feature functions. We show that a baseline statistical machine translation system is significantly improved using this approach. . | Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics ACL Philadelphia July 2002 pp. 295-302. Discriminative Training and Maximum Entropy Models for Statistical Machine Translation Franz Josef Och and Hermann Ney Lehrstuhl fur Informatik VI Computer Science Department RWTH Aachen - University of Technology D-52056 Aachen Germany och ney @ Abstract We present a framework for statistical machine translation of natural languages based on direct maximum entropy models which contains the widely used source-channel approach as a special case. All knowledge sources are treated as feature functions which depend on the source language sentence the target language sentence and possible hidden variables. This approach allows a baseline machine translation system to be extended easily by adding new feature functions. We show that a baseline statistical machine translation system is significantly improved using this approach. 1 Introduction We are given a source French sentence fJ fa . fj . fj which is to be translated into a target English sentence el el . 6i . ei. Among all possible target sentences we will choose the sentence with the highest probability 1 e argmax Pr el fJ 1 fa The argmax operation denotes the search problem . the generation of the output sentence in the target language. 1The notational convention will be as follows. We use the symbol Pr to denote general probability distributions with nearly no specific assumptions. In contrast for model-based probability distributions we use the generic symbol p . . Source-Channel Model According to Bayes decision rule we can equivalently to Eq. 1 perform the following maximization el argmax Pr el Pr fJ ef 2 ei e1 This approach is referred to as source-channel approach to statistical MT. Sometimes it is also referred to as the fundamental equation of statistical MT Brown et al. 1993 . Here Pr el is the language model of the target language whereas Pr fJ el

• Báo cáo khoa học
• Discriminative Training
• Maximum Entropy Models
• Statistical Machine Translation
• báo cáo khoa học
• mô hình ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• Joint Feature Selection
• Distributed Stochastic Learning
• Large Scale Discriminative Training in SMT
• báo cáo ngôn ngữ
• ngôn ngữ tự nhiên
• Joint Processing
• Letter to Phoneme Conversion
• A Discriminative Global
• Training Algorithm
• Statistical MT
• Soft Syntactic Constraints
• Word Alignment
• Neural Network Statistical Parser
• James HENDERSON
• Vietnamese automatic speech recognition
• Transcription system
• Force alignment procedure
• State of the art Vietnamese ASR
• Bài giảng Xử lý ngôn ngữ tự nhiên
• Kỹ thuật lập trình
• Xử lý nhập nhằng ngữ nghĩa
• Xử lý ngữ nghĩa
• Xử lý ngôn ngữ
• Natural Language Processing
• Ngôn ngữ lập trình
• Nhập nhằng cấu trúc
• Tri thức về ngôn ngữ
• Mô hình n gram
• Dịch máy
• Phương pháp dịch máy
• Hiểu ngôn ngữ
• Phân tích ngữ nghĩa
• Phân loại tin tự động
• Biểu diễn vị từ
• Thuộc tính về sự kiện
• Thuộc tính về sự kiện
• Mô hình ngôn ngữ Google Book N grams
• Mô hình ngôn ngữ KenLM
• Phương pháp làm mịn
• Tách từ tiếng Việt
• Gán nhãn từ loại
• Phân tích cú pháp
• Nghĩa từ vựng
• Phân giải nhập nhằng từ
• Phân loại văn bản
• Lexical chain
• Phản hồi thông tin
• Bài toán PTCP
• Cấu trúc ngữ pháp
• Phân tích cú pháp xác suất
• CKY kết hợp xác suất
• Văn phạm phi ngữ cảnh xác suất
• Hình thái học