Commonsense Properties from Query Logs and Question Answering Forums
This addresses the problem of sparse and biased commonsense knowledge for AI applications, though it appears incremental as it builds on prior work on commonsense knowledge bases.
The paper tackles the challenge of automatically acquiring commonsense knowledge about object properties by introducing Quasimodo, a methodology that distills such knowledge from non-standard web sources like search-engine query logs and QA forums, achieving better coverage than state-of-the-art baselines with comparable quality.
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 Quasimodo, 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.