Multiple-document summarization using document clustering
A document clustering and document technology, applied in the field of systems that generate multi-document summaries, can solve problems such as incompleteness and achieve high-quality results
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0016] figure 1 The framework structure of an exemplary multi-document summarization system is shown. First, a number of documents are received (10). The document is preprocessed (20) by removing formatting characters and stopping words. Then, a unigram language model is used to obtain documents by terms and sentences by term matrices. If the task is query-related generalization, the sentences obtained through the term matrix are projected into a subspace where each candidate sentence is related to the query. Afterwards, given the two matrices, the system performs nonnegative factorization on the document and simultaneously clusters documents and sentences into latent topics (30). Sentences with high probabilities in topics are used to form summaries (40).
[0017] figure 2 An exemplary process for summarizing multiple documents is shown. exist figure 1 In B, a number of documents are provided as input in box 101 . In block 102, the process obtains a language model fo...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com