loading

The theory and practice of discourse parsing and summarization / Daniel Marcu

Tác giả : Daniel Marcu

Nhà xuất bản : MIT Press

Năm xuất bản : c2000

Nơi xuất bản : Cambridge, Mass.

Mô tả vật lý : xviii, 248 p. ; 24 cm

ISBN : 9780262133725

Số phân loại : 401.410285

Chủ đề : 1. Lý thuyết tự động. 2. Lý thuyết -- Xử lý dữ liệu. 3. Phân tích cú pháp ( ngữ pháp máy tính). 4. Phân tích ngôn ngữ -- Xử lý dữ kiện. 5. Abstracts -- Data processing. 6. Automatic abstracting. 7. Discourse analysis -- Data processing. 8. Parsing (Computer grammar). 9. Dữ kiện tin học. 10. Ngôn ngữ.

Thông tin chi tiết

Tóm tắt :

Until now, most discourse researchers have assumed that full semantic understanding is necessary to derive the discourse structure of texts. This book documents the first serious attempt to construct automatically and use nonsemantic computational structures for text summarization. Daniel Marcu develops a semantics-free theoretical framework that is both general enough to be applicable to naturally occurring texts and concise enough to facilitate an algorithmic approach to discourse analysis. He presents and evaluates two discourse parsing methods: one uses manually written rules that reflect common patterns of usage of cue phrases such as "however" and "in addition to"; the other uses rules that are learned automatically from a corpus of discourse structures. By means of a psycholinguistic experiment, Marcu demonstrates how a discourse-based summarizer identifies the most important parts of texts at levels of performance that are close to those of humans. Marcu also discusses how the automatic derivation of discourse structures may be used to improve the performance of current natural language generation, machine translation, summarization, question answering, and information retrieval systems.

 Thông tin dữ liệu nguồn

 Thư viện  Ký hiệu xếp giá  Dữ liệu nguồn
Thư viện đại học Cần Thơ
https://lrcopac.ctu.edu.vn/pages/opac/wpid-detailbib-id-153231.html