Unsupervised Relation Extraction from Language Models using Constrained Cloze Completion
Ankur J. Goswami, Akshata Bhat, Hadar Ohana, Theodoros Rekatsinas · 2020
We show that state-of-the-art self-supervised language models can be readily used to extract relations from a corpus without the need to train a fine-tuned extractive head.We introduce RE-Flex, a simple framework that performs constrained cloze completion over pretrained language models to perform unsupervised relation extraction.RE-Flex uses contextual matching to ensure that language model predictions matches supporting evidence from the input corpus that is relevant to a target relation.We perform an extensive experimental study over multiple relation extraction benchmarks and demonstrate that RE-Flex outperforms competing unsupervised relation extraction methods based on pretrained language models by up to 27.8 F 1 points compared to the next-best method.Our results show that constrained inference queries against a language model can enable accurate unsupervised relation extraction.