Building Joint Spaces for Relation Extraction
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2936-2941.
Abstract
In this paper, we present a novel approach for relation extraction using only term pairs as the input without textual features. We aim to build a single joint space for each relation which is then used to produce relation specific term embeddings. The proposed method fits particularly well for domains in which similar arguments are often associated with similar relations. It can also handle the situation when the labeled data is limited. The proposed method is evaluated both theoretically with a proof for the closed-form solution and experimentally with promising results on both DBpedia and medical relations.
@inproceedings{ijcai2016p417,
title = {Building Joint Spaces for Relation Extraction},
author = {Wang, Chang and Cao, Liangliang and Fan, James},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-16}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Subbarao Kambhampati},
pages = {2936--2941},
year = {2016},
month = {7},
url = {https://ijcai.org/proceedings/2016/417},
}
TY - CPAPER TI - Building Joint Spaces for Relation Extraction AU - Wang, Chang AU - Cao, Liangliang AU - Fan, James T2 - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2016 SP - 2936 EP - 2941 UR - https://ijcai.org/proceedings/2016/417 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
