Towards content-oriented patent document processing: Intelligent patent analysis and summarization. (March 2015)

• Record Type: Journal Article
• Authors: Brügmann, Sören; Bouayad-Agha, Nadjet; Burga, Alicia; Carrascosa, Serguei; Ciaramella, Alberto; Ciaramella, Marco; Codina-Filba, Joan; Escorsa, Enric; Judea, Alex; Mille, Simon; Müller, Andreas; Saggion, Horacio; Ziering, Patrick; Schütze, Hinrich; Wanner, Leo
• Is Part Of: World patent information. Volume 40(2015)
• Page Start: 30
• Page End: 42
• Publication Date: 2015-03
• Subjects: Entity recognition -- Segmentation -- Lexical chain identification -- Claim description alignment -- Summarization -- TOPAS -- Patent analysis -- Document processing; Patent literature -- Periodicals; Information storage and retrieval systems -- Patent documentation -- Periodicals; 608.05
• DOI: 10.1016/j.wpi.2014.10.003
• Languages: English
• ISSNs: 0172-2190

Abstract

Abstract: In this article, we present an operational prototype of a workbench for intelligent patent document analysis and summarization that has been developed in the context of the R&D project TOPAS, partially funded by the European Commission. The workbench uses the GATE environment as infrastructure for document representation and algorithm integration. It contains, apart from several preprocessing tools, five modules for the individual aspects of patent analysis (entity recognition, lexical chain identification, invention composition derivation, segmentation, and claim – description alignment) and a module for patent summarization. The workbench, which has been tested in different application settings, can be used as a standalone engine or as component within a more global patent processing line. Most of its modules can be also used separately. Highlights: Further development of content-oriented patent document processing. Workbench for intelligent document analysis and summarisation provided. Modules for entity recognition, lexical chain identification, segmentation, claim-description alignment, and summarization. Potential for further development and practical use outlined.