Automatic Extraction of Commonsense LocatedNear Knowledge
Computation and Language
2018-05-15 v3 Artificial Intelligence
Abstract
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.
Keywords
Cite
@article{arxiv.1711.04204,
title = {Automatic Extraction of Commonsense LocatedNear Knowledge},
author = {Frank F. Xu and Bill Yuchen Lin and Kenny Q. Zhu},
journal= {arXiv preprint arXiv:1711.04204},
year = {2018}
}
Comments
Accepted by ACL 2018. A preliminary version is presented on AKBC@NIPS'17