Revisiting Unsupervised Relation Extraction
This work addresses the problem of extracting relations from text without labeled data for NLP researchers, but appears incremental as it builds on prior URE methods.
The paper tackles unsupervised relation extraction by showing that using only named entities to induce relation types outperforms existing methods on two popular datasets, achieving concrete performance gains.
Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs). URE methods can be categorised into generative and discriminative approaches, which rely either on hand-crafted features or surface form. However, we demonstrate that by using only named entities to induce relation types, we can outperform existing methods on two popular datasets. We conduct a comparison and evaluation of our findings with other URE techniques, to ascertain the important features in URE. We conclude that entity types provide a strong inductive bias for URE.