Extracting Commonsense Properties from Embeddings with Limited Human Guidance

Code

• github.com/yangyiben/PCE
  OfficialIn paperpytorch★ 0

Abstract

Intelligent systems require common sense, but automatically extracting this knowledge from text can be difficult. We propose and assess methods for extracting one type of commonsense knowledge, object-property comparisons, from pre-trained embeddings. In experiments, we show that our approach exceeds the accuracy of previous work but requires substantially less hand-annotated knowledge. Further, we show that an active learning approach that synthesizes common-sense queries can boost accuracy.

Tasks

Reproductions