
Lexicalized statistical parsing for Vietnamese : Luận văn ThS. Công nghệ thông tin / Phạm, Thị Minh Thu; Lê, Anh Cường
Tác giả : Phạm, Thị Minh Thu; Lê, Anh Cường
Nhà xuất bản : Trường Đại học Công nghệ
Năm xuất bản : 2010
Mô tả vật lý : 49 p. + CD-ROM
Chủ đề : 1. Cú pháp. 2. Phân tích thống kê. 3. Tiếng Việt. 4. Tin học. 5. Từ vựng. 6. Thesis.
Thông tin chi tiết
Tóm tắt : | Luận văn ThS. Công nghệ thông tin -- Trường Đại học Công nghệ. Đại học Quốc gia Hà Nội, 2010Electronic ResourcesFor a long time, human being have always dreamed of an intelligent machine which can listen to, understand and implement humans' requirements. Many scientists have tried to make that dream and devoted many achievements for the science of artificial intelligence. In artificial intelligence, natural language processing (NLP) is a field which studies on how to understand and generate automatically human language. NLP has many practical applications such as machine translation, information extraction, discourse analysis, text summarization. These applications have the same basic problems such as lexical analysis, syntactic parsing and semantic analysis. In which, syntactic parsing is the central role and it is also the goal of this thesis. Chapter 2 introduces basic parsing approaches from classical methods such as topdown or bottom-up strategy to statistic based methods like probabilistic context-free grammar (PCFG) and lexicalized probabilistic context-free grammar (LPCFG). In this chapter, we also introduce the important parsing algorithms including CYK, Earley and Chart parsing. Chapter 3 represents Vietnamese parsing and our approach. Characteristics of Vietnamese and Viet Treebank will be introduced in the comparison with Penn Treebank. Chapter 4 describes our experiments and discussions. After the introduction of the Bikel parsing tool, we will describe the process of applying and developing it for the Vietnamese: from adapting the tool for Vietnamese and investigating it in order to find out the best configuration, and finally handling several grammatical errors to reduce error rate and enhance the parser performance. Chapter 6 summarizes the obtained results, gives some conclutions of our work, and shows our plan for the future work. |
Thông tin dữ liệu nguồn
Thư viện | Ký hiệu xếp giá | Dữ liệu nguồn |
---|---|---|
![]() |
|
https://repository.vnu.edu.vn/handle/VNU_123/41962 |