QAnswer: A Question Answering prototype bridging the gap between a considerable part of the LOD cloud and end-users

Dennis Diefenbach (1) , Pedro Henrique Migliatti (2) , Omar Qawasmeh (3, 1) , Vincent Lully (4) , Kamal Singh (1) , Pierre Maret (1)

1 LHC - Laboratoire Hubert Curien
2 UFSCar - Universidade Federal de São Carlos [São Carlos]
3 UJM - Université Jean Monnet - Saint-Étienne
4 SU - Sorbonne Université

We present QAnswer, a Question Answering system which queries at the same time 3 core datasets of the Semantic Web, that are relevant for end-users. These datasets are Wikidata with Lexemes, LinkedGeodata and Musicbrainz. Additionally, it is possible to query these datasets in English, German, French, Italian, Spanish, Pour-tuguese, Arabic and Chinese. Moreover, QAnswer includes a fall-back option to the search engine Qwant when the answer to a question cannot be found in the datasets mentioned above. These features make QAnswer as the first prototype of a Question Answering System over a considerable part of the LOD cloud.

Mots clés: Semantic Web; Multilingual; Multi-Knowledge; Question Answering

Domaines: Recherche d'information [cs.IR]

Dennis Diefenbach, Pedro Henrique Migliatti, Omar Qawasmeh, Vincent Lully, Kamal Singh, et al.. QAnswer: A Question Answering prototype bridging the gap between a considerable part of the LOD cloud and end-users. The Web Conference, May 2019, San Francisco, United States. ⟨10.1145/3308558.3314124⟩. ⟨hal-02121400⟩