Ecole d'ingénieur et centre de recherche en Sciences du numérique

QALM: a benchmark for question answering over linked merchant websites data

Hallili, Amine; Cabrio, Elena; Faron Zucker, Catherine

ISWC 2014, 13th International Semantic Web Conference, October 21-23, 2014, Riva del Garda, Italy

This paper presents a benchmark for training and evaluating Question Answering Systems aiming at mediating between a user, expressing his or her information needs in natural language, and semantic data in the commercial domain of the mobile phones industry. We rst describe the RDF dataset we extracted through the APIs of merchant websites, and the schemas on which it relies. We then present the methodology we applied to create a set of natural language questions expressing possible user needs in the above mentioned domain. Such question set has then been further annotated both with the correspond- ing SPARQL queries, and with the correct answers retrieved from the dataset.

Document Bibtex

Titre:QALM: a benchmark for question answering over linked merchant websites data
Type:Poster / Demo
Langue:English
Ville:Riva del Garda
Pays:ITALIE
Date:
Département:Data Science
Eurecom ref:4454
Copyright: CEUR
Bibtex: @poster / demo{EURECOM+4454, year = {2014}, title = {{QALM}: a benchmark for question answering over linked merchant websites data}, author = {{H}allili, {A}mine and {C}abrio, {E}lena and {F}aron {Z}ucker, {C}atherine}, number = {EURECOM+4454}, month = {10}, institution = {Eurecom} address = {{R}iva del {G}arda, {ITALIE}}, url = {http://www.eurecom.fr/publication/4454} }
Voir aussi: