# Commonsense Properties from Query Logs and Question Answering Forums

## TL;DR

Quasimodo is a novel method that extracts salient commonsense properties from web query logs and QA forums, improving coverage over existing approaches by combining multiple data sources and statistical cues.

## Contribution

The paper introduces Quasimodo, a new tool suite for distilling commonsense knowledge from web sources, focusing on salient object properties and integrating diverse data for better coverage.

## Key findings

- Quasimodo outperforms state-of-the-art baselines in coverage.
- It effectively combines query logs, QA forums, and statistical cues.
- The approach is validated through extensive evaluations and case studies.

## Abstract

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.