Reading the Manual: Event Extraction as Definition Comprehension
Computation and Language
2020-10-26 v2
Abstract
We ask whether text understanding has progressed to where we may extract event information through incremental refinement of bleached statements derived from annotation manuals. Such a capability would allow for the trivial construction and extension of an extraction framework by intended end-users through declarations such as, "Some person was born in some location at some time." We introduce an example of a model that employs such statements, with experiments illustrating we can extract events under closed ontologies and generalize to unseen event types simply by reading new definitions.
Keywords
Cite
@article{arxiv.1912.01586,
title = {Reading the Manual: Event Extraction as Definition Comprehension},
author = {Yunmo Chen and Tongfei Chen and Seth Ebner and Aaron Steven White and Benjamin Van Durme},
journal= {arXiv preprint arXiv:1912.01586},
year = {2020}
}
Comments
Accepted at the EMNLP 2020 Workshop on Structured Prediction for NLP