TAILIEUCHUNG - Báo cáo khoa học: "Hidden Markov Tree Model in Dependency-based Machine Translation∗"

We would like to draw attention to Hidden Markov Tree Models (HMTM), which are to our knowledge still unexploited in the field of Computational Linguistics, in spite of highly successful Hidden Markov (Chain) Models. In dependency trees, the independence assumptions made by HMTM correspond to the intuition of linguistic dependency. Therefore we suggest to use HMTM and tree-modified Viterbi algorithm for tasks interpretable as labeling nodes of dependency trees. In particular, we show that the transfer phase in a Machine Translation system based on tectogrammatical dependency trees can be seen as a task suitable for HMTM. . | Hidden Markov Tree Model in Dependency-based Machine Translation Zdenek Zabokrtsky Charles University in Prague Institute of Formal and Applied Linguistics zabokrtsky@ Martin Popel Charles University in Prague Institute of Formal and Applied Linguistics popel@ Abstract We would like to draw attention to Hidden Markov Tree Models HMTM which are to our knowledge still unexploited in the field of Computational Linguistics in spite of highly successful Hidden Markov Chain Models. In dependency trees the independence assumptions made by HMTM correspond to the intuition of linguistic dependency. Therefore we suggest to use HMTM and tree-modified Viterbi algorithm for tasks interpretable as labeling nodes of dependency trees. In particular we show that the transfer phase in a Machine Translation system based on tectogrammatical dependency trees can be seen as a task suitable for HMTM. When using the HMTM approach for the English-Czech translation we reach a moderate improvement over the baseline. 1 Introduction Hidden Markov Tree Models HMTM were introduced in Crouse et al. 1998 and used in applications such as image segmentation signal classification denoising and image document categorization see Durand et al. 2004 for references. Although Hidden Markov Models belong to the most successful techniques in Computational Linguistics CL the HMTM modification remains to the best of our knowledge unknown in the field. The first novel claim made in this paper is that the independence assumptions made by Markov Tree Models can be useful for modeling syntactic trees. Especially they fit dependency trees well because these models assume conditional dependence in the probabilistic sense only along tree The work on this project was supported by the grants MSM 0021620838 GaAv Cr 1ET101120503 and MSMT Cr LC536. We thank Jan Hajic and three anonymous reviewers for many useful comments. edges which corresponds to intuition behind dependency relations in the .

• Báo cáo khoa học
• Hidden Markov Tree Model
• Dependency based Machine Translation
• Long Papers
• báo cáo khoa học
• báo cáo ngôn ngữ
• xử lý ngôn ngữ tự nhiên
• BMC Bioinformatics
• Differential expression
• Directed acyclic graph
• Expectation maximization
• Expression quantitative trait loci
• False discovery rate
• Bài giảng Xử lý ngôn ngữ tự nhiên
• 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 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