English

Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors

Computation and Language 2021-04-19 v1

Abstract

We propose a multi-task, probabilistic approach to facilitate distantly supervised relation extraction by bringing closer the representations of sentences that contain the same Knowledge Base pairs. To achieve this, we bias the latent space of sentences via a Variational Autoencoder (VAE) that is trained jointly with a relation classifier. The latent code guides the pair representations and influences sentence reconstruction. Experimental results on two datasets created via distant supervision indicate that multi-task learning results in performance benefits. Additional exploration of employing Knowledge Base priors into the VAE reveals that the sentence space can be shifted towards that of the Knowledge Base, offering interpretability and further improving results.

Keywords

Cite

@article{arxiv.2104.08225,
  title  = {Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors},
  author = {Fenia Christopoulou and Makoto Miwa and Sophia Ananiadou},
  journal= {arXiv preprint arXiv:2104.08225},
  year   = {2021}
}

Comments

16 pages, 9 figures, Accepted as a long paper at NAACL 2021

R2 v1 2026-06-24T01:15:09.479Z