Information Extraction For The Semantic Web, Solution: Integration of PDT Tools With Gate And Inductive Logic Programming

Speaker:
Jan Dedek
Abstract:
Automated semantic annotation (SA) is considered to be one of the most important elements in the evolution of the Semantic Web. Besides that, SA can provide great help in the process of data and information integration and it could be also a basis for intelligent search and navigation. We present an automated method for classical and semantic information extraction and annotation of texts, which is based on a deep linguistic analysis. The extraction method works with linguistic extraction rules. There are two ways, how to obtain these rules. The extraction rules can be either designed manually by a linguistic expert or they can be automatically learned by Inductive Logic Programming from a labelled corpus. The implementation of the method brought with it several interesting side effects: TectoMT and PDT tools were integrated with GATE (http://gate.ac.uk/) and the PML format was translated to RDF (http://www.w3.org/RDF). This makes it possible to work with the linguistic data in semantic web tools and also to run ontology reasoning tasks over it.
Length:
01:08:15
Date:
10/01/2011
views: 794

Images:
Preview of img-001.jpg
Image img-001.jpg
Preview of img-016.jpg
Image img-016.jpg
Preview of img-039.jpg
Image img-039.jpg
Attachments: (video, slides, etc.)
32M
342 downloads
68M
343 downloads
256M
354 downloads