We present an approach to minimally supervised relation extraction that combines the benefits of learned representations and structured learning, and accurately predicts sentence-level relation mentions given only proposition-level supervision from a KB. By explicitly reasoning about missing data during learning, our approach enables large-scale training of 1D convolutional neural networks while mitigating the issue of label noise inherent in distant supervision. Our approach achieves state-of-the-art results on minimally supervised sentential relation extraction, outperforming a number of baselines, including a competitive approach that uses the attention layer of a purely neural model.
@article{arxiv.1904.00118,
title = {Structured Minimally Supervised Learning for Neural Relation Extraction},
author = {Fan Bai and Alan Ritter},
journal= {arXiv preprint arXiv:1904.00118},
year = {2019}
}
Comments
Accepted to NAACL 2019. This version improves the model description(present original "Bag-Size Adaptive Learning Rate" as "Bag-Size Weighting Function"). No result/conclusion change