# Matching the Blanks: Distributional Similarity for Relation Learning

## TL;DR

This paper introduces a novel approach for relation learning that leverages distributional similarity and BERT-based text representations to create task-agnostic relation embeddings, outperforming previous methods in various relation extraction tasks.

## Contribution

The authors develop a new method for relation representation using distributional hypotheses and BERT, enabling better generalization without task-specific training data.

## Key findings

- Outperforms previous relation extraction methods on FewRel without task-specific training.
- Significantly improves results on SemEval 2010, KBP37, and TACRED datasets after fine-tuning.
- Demonstrates the effectiveness of distributional similarity and BERT in relation learning.

## Abstract

General purpose relation extractors, which can model arbitrary relations, are a core aspiration in information extraction. Efforts have been made to build general purpose extractors that represent relations with their surface forms, or which jointly embed surface forms with relations from an existing knowledge graph. However, both of these approaches are limited in their ability to generalize. In this paper, we build on extensions of Harris' distributional hypothesis to relations, as well as recent advances in learning text representations (specifically, BERT), to build task agnostic relation representations solely from entity-linked text. We show that these representations significantly outperform previous work on exemplar based relation extraction (FewRel) even without using any of that task's training data. We also show that models initialized with our task agnostic representations, and then tuned on supervised relation extraction datasets, significantly outperform the previous methods on SemEval 2010 Task 8, KBP37, and TACRED.