Commonsense Properties from Query Logs and Question Answering Forums - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Commonsense Properties from Query Logs and Question Answering Forums

Résumé

Commonsense knowledge about object properties, human behavior and general concepts is crucial for robust AI applications. However, automatic acquisition of this knowledge is challenging because of sparseness and bias in online sources. This paper presents Quasi-modo, a methodology and tool suite for distilling commonsense properties from non-standard web sources. We devise novel ways of tapping into search-engine query logs and QA forums, and combining the resulting candidate assertions with statistical cues from encyclopedias, books and image tags in a corroboration step. Unlike prior work on commonsense knowledge bases, Quasimodo focuses on salient properties that are typically associated with certain objects or concepts. Extensive evaluations, including extrinsic use-case studies, show that Quasimodo provides better coverage than state-of-the-art baselines with comparable quality.
Fichier principal
Vignette du fichier
Quasimodo (1).pdf (832.74 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02158602 , version 1 (18-06-2019)
hal-02158602 , version 2 (08-09-2019)

Identifiants

Citer

Julien Romero, Simon Razniewski, Koninika Pal, Jeff Pan, Archit Sakhadeo, et al.. Commonsense Properties from Query Logs and Question Answering Forums. 28th ACM International Conference on Information and Knowledge Management (CIKM 2019), ACM, Nov 2019, Pékin, China. ⟨10.1145/3357384.3357955⟩. ⟨hal-02158602v2⟩
199 Consultations
387 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More