Method and device of automatically generating a summary for document set
A technology of automatic generation and document collection, applied in the fields of instrumentation, computing, electrical digital data processing, etc., can solve the problems of insufficiency, generation of new abstracts, huge amount of calculation, etc., to achieve the effect of improving efficiency and adapting to the speed of information update
Active Publication Date: 2009-06-03
PEKING UNIV +2
View PDF0 Cites 26 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
If the existing multi-document summarization method is used to summarize frequently updated document sets, every time a new document is added to the document set, the weights of all sentences in the document set need to be recalculated. The collection quickly generates new summaries, which leads to the problem of low efficiency of generating summaries, and cannot meet the needs of large-scale Internet applications (such as news topic detection, hot spot analysis, etc.)
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0027] In order to solve the problem of slow and inefficient generation of summaries due to the need to recalculate the weight of each sentence of all documents in the document set when generating summaries for document sets in the prior art, the present invention provides a method for automatically generating summaries for document sets Methods, the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.
[0028] Such as figure 1 As shown, the method for automatically generating a summary for a document set provided by the present invention is used to automatically generate a summary for a document set after adding a new document to the document set, including the following steps:
[0029] Step 101, calculating the vector of the new document and the vector of each sentence in the new document;
[0030] The specific steps are:
[0031] to the new document d new Carry out clauses to obtain the sentence set S new , S...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method and a device of automatically generating a summary for a document set, relates to the language and word processing field, and aims at solving the problems of slow speed and low efficiency of the summary generation due to weight recomputation of each sentence in all documents of the document set when the summary is generated for the document set in the prior art. The method comprises the following steps: computing the weight of each sentence in a new document; updating the weight of the sentence in the existing summary of the document set; acquiring a weight order of all nonrepetitive sentences in the existing summary of the new document and the document set; and generating a new summary of the document set. The method and the device are applicable to the automatic summary generation of a plurality of documents.
Description
technical field [0001] The invention relates to the fields of language and word processing and information retrieval, in particular to a method and device for automatically generating abstracts for document collections. Background technique [0002] Automatically generating summaries for a document collection refers to: a computer system automatically extracts the essence or key points of a document collection from each document in a document collection; Refine, to provide users with a concise content description of the documentation set. With the continuous popularization and application of computer technology and Internet technology, the technology of automatically generating summaries for document sets has been widely used in text / web site (Web) content retrieval and other aspects. For example, the news services provided by search engines such as Google and Baidu are to collect various news information on the Internet, form multiple news topics (news document collections...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/27
Inventor 万小军余军杨建武吴於茜
Owner PEKING UNIV