Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors

TL;DR

This paper introduces a multi-task probabilistic model using a VAE for distantly supervised relation extraction, enhancing performance and interpretability by aligning sentence representations with Knowledge Base priors.

Contribution

It presents a novel joint VAE-based framework that incorporates Knowledge Base priors to improve relation extraction and interpretability.

Findings

Multi-task learning improves relation extraction performance.

Knowledge Base priors help align sentence representations with KB entities.

The approach enhances interpretability of sentence embeddings.

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.