Effective Piecewise CNN with Attention Mechanism for Distant Supervision on Relation Extraction Task

Yuming Li, Pin Ni, Gangmin Li, Victor Chang

2020

Abstract

Relation Extraction is an important sub-task in the field of information extraction. Its goal is to identify entities from text and extract semantic relationships between entities. However, the current Relationship Extraction task based on deep learning methods generally have practical problems such as insufficient amount of manually labeled data, so training under weak supervision has become a big challenge. Distant Supervision is a novel idea that can automatically annotate a large number of unlabeled data based on a small amount of labeled data. Based on this idea, this paper proposes a method combining the Piecewise Convolutional Neural Networks and Attention mechanism for automatically annotating the data of Relation Extraction task. The experiments proved that the proposed method achieved the highest precision is 76.24% on NYT-FB (New York Times - Freebase) dataset (top 100 relation categories). The results show that the proposed method performed better than CNN-based models in most cases.

Download


Paper Citation


in Harvard Style

Li Y., Ni P., Li G. and Chang V. (2020). Effective Piecewise CNN with Attention Mechanism for Distant Supervision on Relation Extraction Task.In Proceedings of the 5th International Conference on Complexity, Future Information Systems and Risk - Volume 1: COMPLEXIS, ISBN 978-989-758-427-5, pages 53-60. DOI: 10.5220/0009582700530060


in Bibtex Style

@conference{complexis20,
author={Yuming Li and Pin Ni and Gangmin Li and Victor Chang},
title={Effective Piecewise CNN with Attention Mechanism for Distant Supervision on Relation Extraction Task},
booktitle={Proceedings of the 5th International Conference on Complexity, Future Information Systems and Risk - Volume 1: COMPLEXIS,},
year={2020},
pages={53-60},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009582700530060},
isbn={978-989-758-427-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 5th International Conference on Complexity, Future Information Systems and Risk - Volume 1: COMPLEXIS,
TI - Effective Piecewise CNN with Attention Mechanism for Distant Supervision on Relation Extraction Task
SN - 978-989-758-427-5
AU - Li Y.
AU - Ni P.
AU - Li G.
AU - Chang V.
PY - 2020
SP - 53
EP - 60
DO - 10.5220/0009582700530060