1 / 9

Build ontologies from texts and using them for IR

Build ontologies from texts and using them for IR. Josiane MOTHE Institut de Recherche en Informatique de Toulouse (IRIT). Ontology. Ontology: description at a conceptual level Concepts and their labels Semantic relationships Rules (inferences) Domain ontology In order to help

weim
Download Presentation

Build ontologies from texts and using them for IR

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Providing Intelligent Content - Pinar SENKUL - METU CENG Build ontologies from texts and using them for IR Josiane MOTHE Institut de Recherche en Informatique de Toulouse (IRIT)

  2. Providing Intelligent Content - Pinar SENKUL - METU CENG Ontology • Ontology: description at a conceptual level • Concepts and their labels • Semantic relationships • Rules (inferences) • Domain ontology • In order to help • Structuration • Access (direct or advanced information) to heterogeneous data • Issues • Build ontologies • Use them in applications Ontologies, text and IR , mothe@irit.fr

  3. Providing Intelligent Content - Pinar SENKUL - METU CENG Building ontologies • From texts • Term extraction • Relationship extraction (NLP-based) • Formalisation : OWL-Lite [w3c] • Enrich thesaurus when exist ISO 2788 - ANSI Z39 • used for ; more generic / more specific ; is-related to => disambiguate them • Add terms / labels Ontologies, text and IR , mothe@irit.fr

  4. Providing Intelligent Content - Pinar SENKUL - METU CENG existing concept in the hierarchy head Color Ultraviolet Color Intrinsic color Building ontologies – from thesaurus • Concepts and labels from terms Term1 USE Term2 Term3 USED FOR Term2 • IS a relation Term1 Broader Term Term2 Term3 Narrower Term Term4 • Hierachical levels Concept INTRINSIC COLORS Label intrinsic color Concept ULTRAVIOLET COLORS Label ultraviolet color Ontologies, text and IR , mothe@irit.fr

  5. Providing Intelligent Content - Pinar SENKUL - METU CENG Building ontologies – from corpus • Abstract level • Syntatic analysis • Terms and their category • Context of usage • Extraction of terms and the semantic of their relationships « is a property of » between « radial velocity » and « intensity » Ontologies, text and IR , mothe@irit.fr

  6. Providing Intelligent Content - Pinar SENKUL - METU CENG Using ontologies in IR Visualization of the instances of the task ontology Ontologies, text and IR , mothe@irit.fr

  7. Providing Intelligent Content - Pinar SENKUL - METU CENG Using ontologies in IR Visualization of the knowledge learnt for an instance researcher of the task ontology Ontologies, text and IR , mothe@irit.fr

  8. Providing Intelligent Content - Pinar SENKUL - METU CENG Using ontologies in IR Visualization of the knowledge learnt for an instance Article of the task ontology Ontologies, text and IR , mothe@irit.fr

  9. Providing Intelligent Content - Pinar SENKUL - METU CENG More • www.irit.fr/~Josiane.Mothe • mothe@irit.fr Ontologies, text and IR , mothe@irit.fr

More Related