TW200630825A - Method to automatically summarize chinese digital documents - Google Patents

Method to automatically summarize chinese digital documents

Info

Publication number
TW200630825A
TW200630825A TW094105191A TW94105191A TW200630825A TW 200630825 A TW200630825 A TW 200630825A TW 094105191 A TW094105191 A TW 094105191A TW 94105191 A TW94105191 A TW 94105191A TW 200630825 A TW200630825 A TW 200630825A
Authority
TW
Taiwan
Prior art keywords
document
digital documents
similarity
importance
words
Prior art date
Application number
TW094105191A
Other languages
Chinese (zh)
Other versions
TWI288335B (en
Inventor
Yuen-Hsien Tseng
Original Assignee
Webgenie Information Ltd
Yuen-Hsien Tseng
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Webgenie Information Ltd, Yuen-Hsien Tseng filed Critical Webgenie Information Ltd
Priority to TW94105191A priority Critical patent/TWI288335B/en
Publication of TW200630825A publication Critical patent/TW200630825A/en
Application granted granted Critical
Publication of TWI288335B publication Critical patent/TWI288335B/en

Links

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Document Processing Apparatus (AREA)

Abstract

A method is developed to automatically summarize Chinese digital documents. It evaluates the importance of each sentence in the digital document, finds out the similarity between the document title and each of its sentences, and combines the title with the reduced sentence to become a summary candidate with its number of characters below an assigned limit. Finally, according to the ratio of the number of characters and the similarity, it sorts those summary candidates and provides the result for the user to select. This invention simultaneously considers factors including the number of words after summarization, the importance covered by the content, the readability, and the coherence of the meaning. It effectively represents the key points of original document within limited number of words and greatly reduces the human labor burden.
TW94105191A 2005-02-22 2005-02-22 Method to automatically summarize Chinese digital documents TWI288335B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
TW94105191A TWI288335B (en) 2005-02-22 2005-02-22 Method to automatically summarize Chinese digital documents

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW94105191A TWI288335B (en) 2005-02-22 2005-02-22 Method to automatically summarize Chinese digital documents

Publications (2)

Publication Number Publication Date
TW200630825A true TW200630825A (en) 2006-09-01
TWI288335B TWI288335B (en) 2007-10-11

Family

ID=39202987

Family Applications (1)

Application Number Title Priority Date Filing Date
TW94105191A TWI288335B (en) 2005-02-22 2005-02-22 Method to automatically summarize Chinese digital documents

Country Status (1)

Country Link
TW (1) TWI288335B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI493364B (en) * 2013-05-23 2015-07-21 Loremaster Tech Inc Management methods for subjective comments of articles, and related devices and computer program products
CN110837556A (en) * 2019-10-30 2020-02-25 深圳价值在线信息科技股份有限公司 Abstract generation method and device, terminal equipment and storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI493364B (en) * 2013-05-23 2015-07-21 Loremaster Tech Inc Management methods for subjective comments of articles, and related devices and computer program products
CN110837556A (en) * 2019-10-30 2020-02-25 深圳价值在线信息科技股份有限公司 Abstract generation method and device, terminal equipment and storage medium

Also Published As

Publication number Publication date
TWI288335B (en) 2007-10-11

Similar Documents

Publication Publication Date Title
Piotrowski Natural language processing for historical texts
CN106407236B (en) A kind of emotion tendency detection method towards comment data
Topkara et al. Information hiding through errors: a confusing approach
CN106407235B (en) A kind of semantic dictionary construction method based on comment data
ATE381053T1 (en) DATA ENTRY METHOD AND SYSTEM FOR PERSONAL COMPUTER, AND CORRESPONDING COMPUTER-READABLE MEDIUM
EP1887451A3 (en) Data entry method and system for personal computer, and corresponding computer readable medium
Diemer Corpus linguistics with Google
CN101038508A (en) GB phoneticize input method
Winters F. Scott Fitzgerald's Die Schönen und Verdammten: A corpus-based study of loan words and code switches as features of translators' style
TW200630825A (en) Method to automatically summarize chinese digital documents
Coleman et al. Historical dictionaries and historical dictionary research: papers from the International Conference on Historical Lexicography and Lexicology, at the University of Leicester, 2002
CN103020046A (en) Name transliteration method on the basis of classification of name origin
Yadav et al. Indus script: A study of its sign design
Downey et al. Lexomic analysis of medieval Latin texts
JP2009230561A (en) Example-set-based translation device, method and program, and phrase translation device including the translation device
Cook Lexical coinages in Mandarin Chinese and the problem of classification.
Bollmann Spelling normalization of historical German with sparse training data
Church Dedication to William A. Gale
US20040021641A1 (en) Method for inputting a chinese character with phonetic symbols
Fragoulaki History-(A.) Rengakos and (A.) Tsakmakis Eds. Brill's Companion to Thucydides.(Brill's Companions in Classical Studies). Leiden: Brill, 2006. Pp. xix+ 947.€ 249. 9789004136830.
Molina et al. Evaluation of unambiguous virtual keyboards with character prediction
Stewart A HISTORY OF THE HELLENISTIC PELOPONNESE-(I.) Kralli The Hellenistic Peloponnese: Interstate Relations. A Narrative and Analytic History, from the Fourth Century to 146 bc. Pp. xxxiv+ 556, maps. Swansea: The Classical Press of Wales, 2017. Cased,£ 75. ISBN: 978-1-910589-60-1.
Ngonyani Sentential negation and verb movement in Bantu languages
McNamara Multilingualism in Medieval Britain (c. 1066-1520): Sources and Analysis ed. by Judith A. Jefferson and Ad Putter
Everson Proposal to encode the Wancho script in the UCS