Abstract
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.- Anthology ID:
- K17-1034
- Volume:
- Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)
- Month:
- August
- Year:
- 2017
- Address:
- Vancouver, Canada
- Venue:
- CoNLL
- SIG:
- SIGNLL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 333–342
- Language:
- URL:
- https://aclanthology.org/K17-1034
- DOI:
- 10.18653/v1/K17-1034
- Cite (ACL):
- Omer Levy, Minjoon Seo, Eunsol Choi, and Luke Zettlemoyer. 2017. Zero-Shot Relation Extraction via Reading Comprehension. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 333–342, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Zero-Shot Relation Extraction via Reading Comprehension (Levy et al., CoNLL 2017)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/K17-1034.pdf
- Code
- additional community code
- Data
- SQuAD, WikiReading