Building an Event Extractor with Only a Few Examples

Pengfei Yu, Zixuan Zhang, Clare Voss, Jonathan May, Heng Ji

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Supervised event extraction models require a substantial amount of training data to perform well. However, event annotation requires a lot of human effort and costs much time, which limits the application of existing supervised approaches to new event types. In order to reduce manual labor and shorten the time to build an event extraction system for an arbitrary event ontology, we present a new framework to train such systems much more efficiently without large annotations. Our event trigger labeling model uses a weak supervision approach, which only requires a set of keywords, a small number of examples and an unlabeled corpus, on which our approach automatically collects weakly supervised annotations. Our argument role labeling component performs zero-shot learning, which only requires the names of the argument roles of new event types. The source codes of our event trigger detection and event argument extraction models are publicly available for research purposes. We also release a dockerized system connecting the two models into an unified event extraction pipeline.

Original languageEnglish (US)
Title of host publicationDeepLo 2022 - 3rd Workshop on Deep Learning Approaches for Low-Resource NLP, Proceedings of the DeepLo Workshop
EditorsColin Cherry, Angela Fan, George Foster, Gholamreza Haffari, Shahram Khadivi, Nanyun Peng, Xiang Ren, Ehsan Shareghi, Swabha Swayamdipta
PublisherAssociation for Computational Linguistics (ACL)
Pages102-109
Number of pages8
ISBN (Electronic)9781955917971
StatePublished - 2022
Event3rd Workshop on Deep Learning Approaches for Low-Resource NLP, DeepLo 2022 - Seattle, United States
Duration: Jul 14 2022 → …

Publication series

NameDeepLo 2022 - 3rd Workshop on Deep Learning Approaches for Low-Resource NLP, Proceedings of the DeepLo Workshop

Conference

Conference3rd Workshop on Deep Learning Approaches for Low-Resource NLP, DeepLo 2022
Country/TerritoryUnited States
CitySeattle
Period7/14/22 → …

ASJC Scopus subject areas

  • Language and Linguistics
  • Software
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Building an Event Extractor with Only a Few Examples'. Together they form a unique fingerprint.

Cite this