Building Joint Spaces for Relation Extraction
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. PDF
Cite
Text
Wang et al. "Building Joint Spaces for Relation Extraction." International Joint Conference on Artificial Intelligence, 2016.Markdown
[Wang et al. "Building Joint Spaces for Relation Extraction." International Joint Conference on Artificial Intelligence, 2016.](https://mlanthology.org/ijcai/2016/wang2016ijcai-building/)BibTeX
@inproceedings{wang2016ijcai-building,
title = {{Building Joint Spaces for Relation Extraction}},
author = {Wang, Chang and Cao, Liangliang and Fan, James},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2016},
pages = {2936-2942},
url = {https://mlanthology.org/ijcai/2016/wang2016ijcai-building/}
}