Mining Commonsense Facts from the Physical World

TL;DR

This paper introduces a new method for automatically extracting commonsense facts about the physical world from raw text, enhancing knowledge base coverage by combining textual and existing knowledge sources.

Contribution

The paper proposes a novel model that fuses sequence text and knowledge base information, along with creating large datasets for commonsense knowledge base completion.

Findings

Model significantly outperforms baselines

Creates two large annotated datasets

Improves coverage of commonsense knowledge bases

Abstract

Textual descriptions of the physical world implicitly mention commonsense facts, while the commonsense knowledge bases explicitly represent such facts as triples. Compared to dramatically increased text data, the coverage of existing knowledge bases is far away from completion. Most of the prior studies on populating knowledge bases mainly focus on Freebase. To automatically complete commonsense knowledge bases to improve their coverage is under-explored. In this paper, we propose a new task of mining commonsense facts from the raw text that describes the physical world. We build an effective new model that fuses information from both sequence text and existing knowledge base resource. Then we create two large annotated datasets each with approximate 200k instances for commonsense knowledge base completion. Empirical results demonstrate that our model significantly outperforms baselines.