Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors
This work addresses relation extraction for natural language processing applications, but it is incremental as it builds on existing methods with multi-task learning and prior integration.
The paper tackles the problem of distantly supervised relation extraction by proposing a multi-task, probabilistic approach that uses a Variational Autoencoder to align sentence representations with Knowledge Base pairs, resulting in improved performance on two datasets.
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.