A Cooking Knowledge Graph and Benchmark for Question Answering Evaluation in Lifelong Learning Scenarios

Mathilde Veron , Anselmo Peã±as , Guillermo Echegoyen , Somnath Banerjee (1) , Sahar Ghannay (1) , Sophie Rosset (1)

1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur

In a long term exploitation environment, a Question Answering (QA) system should maintain or even improve its performance over time, trying to overcome the lacks made evident through the interactions with users. We claim that, in order to make progress in the QA over Knowledge Bases (KBs) research field, we must deal with two problems at the same time: the translation of Natural Language (NL) questions into formal queries, and the detection of missing knowledge that impact the way a question is answered. The research on these two challenges has not been addressed jointly until now, what motivates the main goals of this work: (i) the definition of the problem and (ii) the development of a methodology to create the evaluation resources needed to address this challenge.

Mots clés: Question Answering; Lifelong Learning; Evaluation resources

Domaines: Informatique [cs]; Informatique et langage [cs.CL]

Mathilde Veron, Anselmo Peã±as, Guillermo Echegoyen, Somnath Banerjee, Sahar Ghannay, et al.. A Cooking Knowledge Graph and Benchmark for Question Answering Evaluation in Lifelong Learning Scenarios. International Conference on Applications of Natural Language to Information Systems, Elisabeth Métais and Farid Meziane and Helmut Horacek and Philipp Cimiano, Jun 2020, Saarbrücken, Germany. ⟨hal-03006228⟩