Automatic Extraction of Commonsense LocatedNear Knowledge
This work addresses the need for automated commonsense knowledge extraction for AI systems, but it is incremental as it applies existing methods to a specific relation type.
The paper tackled the problem of automatically extracting commonsense LocatedNear knowledge by developing a sentence-level relation classifier and aggregating entity pair scores from a large corpus, resulting in the release of two benchmark datasets for evaluation.
LocatedNear relation is a kind of commonsense knowledge describing two physical objects that are typically found near each other in real life. In this paper, we study how to automatically extract such relationship through a sentence-level relation classifier and aggregating the scores of entity pairs from a large corpus. Also, we release two benchmark datasets for evaluation and future research.