HULTECH at the NTCIR-11 IMine Task: Mining Intents with Continuous Vector Space Models

José G. Moreno (1) , Gaël Dias (1)

1 Equipe Hultech - Laboratoire GREYC - UMR6072

In this paper, we present our participation in the Subtopic Mining subtask of the NTCIR-11 IMine task, for the En-glish language. Our participation presents a novel strategy for intent mining given a list of candidates for a specific query topic. This strategy is based on a topic exploration through the use of continuous vector space models for each of the candidates based on classical vectorial operations. Our best run outperforms the other participants' submissions in terms of F-score and achieves a high position in the general ranking.

Domaines: Recherche d'information [cs.IR]; Interface homme-machine [cs.HC]; Apprentissage [cs.LG]; Web

José G. Moreno, Gaël Dias. HULTECH at the NTCIR-11 IMine Task: Mining Intents with Continuous Vector Space Models. IMine Subtask of the NII Testbeds and Community for Information Access Research Workshop (NTCIR-11 2014), 2014, Tokyo, Japan. ⟨hal-01150207⟩