HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Answering N-Relation Natural Language Questions in the Commercial Domain

Elena Cabrio 1, 2 Catherine Faron Zucker 1, 2 Fabien Gandon 1, 2 Amine Hallili 1, 2 Andrea G. B. Tettamanzi 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 I3S - Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis
Abstract : This paper presents SynchroBot, a Natural Language Question Answering system in the Commercial Domain. It relies on an RDF dataset and an RDFS ontology that we have developed for the commercial domain of the mobile phone industry. We propose an approach to understand and interpret natural language questions, based on the use of regular expressions to identify both the properties connecting entities, and their values. These regex are automatically learned from a subset of our dataset with a genetic algorithm.
Document type :
Conference papers
Complete list of metadata

Cited literature [7 references]  Display  Hide  Download
https://hal.archives-ouvertes.fr/hal-01187413
Contributor : Catherine Faron Connect in order to contact the contributor
Submitted on : Wednesday, July 27, 2016 - 5:52:41 PM
Last modification on : Wednesday, February 2, 2022 - 2:16:06 PM

File

Vignette du document
synchrobot-WI-short.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01187413, version 1

Collections

CNRS | WIMMICS | INRIA | INRIA2 | I3S | UNIV-COTEDAZUR

Citation

Elena Cabrio, Catherine Faron Zucker, Fabien Gandon, Amine Hallili, Andrea G. B. Tettamanzi. Answering N-Relation Natural Language Questions in the Commercial Domain. The IEEE/WIC/ACM International Conference on Web Intelligence, Dec 2015, Singapore, Singapore. ⟨hal-01187413⟩

Export

BibTeX TEI DC DCterms EndNote Datacite

Share

Metrics

Record views

155

Files downloads

191