QAKiS: an Open Domain QA System based on Relational Patterns

Elena Cabrio 1, 2 Julien Cojan 1, 2 Alessio Palmero Aprosio 3, 4 Bernardo Magnini 4 Alberto Lavelli 4 Fabien Gandon 1, 2
1 WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics
CRISAM - Inria Sophia Antipolis - Méditerranée , Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
2 CRISAM - Inria Sophia Antipolis - Méditerranée
3 Università degli studi di Milano [Milano]
4 Human Language Technology [Trento]
FBK - Fondazione Bruno Kessler [Trento, Italy]
Abstract : We present QAKiS, a system for open domain Question Answering over linked data. It addresses the problem of question interpretation as a relation-based match, where fragments of the question are matched to binary relations of the triple store, using relational textual patterns automatically collected. For the demo, the relational patterns are automatically extracted from Wikipedia, while DBpedia is the RDF data set to be queried using a natural language interface.
Keywords : natural language processing semantic web Wikipedia NLP Question Answering System linked data Dbpedia
Document type :
Poster communications
Complete list of metadatas
https://hal.inria.fr/hal-01171115
Contributor : Fabien Gandon <>
Submitted on : Thursday, July 2, 2015 - 7:48:38 PM
Last modification on : Monday, November 5, 2018 - 3:52:09 PM
Long-term archiving on : Tuesday, April 25, 2017 - 10:20:11 PM

Files

paper_24.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01171115, version 1

Collections

UNICE | WIMMICS | INRIA | I3S | UNIV-COTEDAZUR

Citation

Elena Cabrio, Julien Cojan, Alessio Palmero Aprosio, Bernardo Magnini, Alberto Lavelli, et al.. QAKiS: an Open Domain QA System based on Relational Patterns. International Semantic Web Conference, ISWC 2012, Nov 2012, Boston, United States. ⟨http://iswc2012.semanticweb.org/⟩. ⟨hal-01171115⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

573

Files downloads

647

Contact


archive-ouverte@inria.fr