We show that relation extraction can be reduced to answering simple reading comprehension questions, by associating one or more natural-language questions with each relation slot. This reduction has several advantages: we can (1) learn relation-extraction models by extending recent neural reading-comprehension techniques, (2) build very large training sets for those models by combining relation-specific crowd-sourced questions with distant supervision, and even (3) do zero-shot learning by extracting new relation types that are only specified at test-time, for which we have no labeled training examples. Experiments on a Wikipedia slot-filling task demonstrate that the approach can generalize to new questions for known relation types with high accuracy, and that zero-shot generalization to unseen relation types is possible, at lower accuracy levels, setting the bar for future work on this task.
@article{arxiv.1706.04115,
title = {Zero-Shot Relation Extraction via Reading Comprehension},
author = {Omer Levy and Minjoon Seo and Eunsol Choi and Luke Zettlemoyer},
journal= {arXiv preprint arXiv:1706.04115},
year = {2017}
}