2020
EMNLP
EMNLP 2020
Reading the Manual: Event Extraction as Definition Comprehension
Abstract
AbstractWe 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, βSome person was born in some location at some time.β 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.
π
Interdisciplinary Bridge
β Artificial Intelligence and Deep Learning and Machine Learning and Natural Language Processing
π§
Keyword Pioneer
β closed ontology
π£
Hot Topic Early Bird
β event extraction
π
Cross-Pollinator
β Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio