Back to search

Georgia Institute of Technology

ZERO-SHOT COMPOSITIONAL EVENT DETECTION VIA GRAPH MODULAR NETWORK

Abstract

dc:description.abstract

Humans are known to have the capability of understanding events by composing different atomic concepts, even for event types that have never been seen before. However, event detection has been so far treated as a sequence tagging problem in literature. Despite the increasing accuracy obtained on benchmarks such as ACE, current supervised sequence tagging models lack the compositional generalization ability. We present a model that is able to achieve zero-shot compositional generalization for event detection. Our model, named compositional graph modular network (CGMN), proposes two separate graph neural networks to obtain compositional semantic representations for sentences and events respectively. Meanwhile, it ties graph-based event representations with the weight parameters of an event matching layer, so that the semantic representations for sentences and events can be connected with each other, thereby achieving zero-shot recognition of new events using only their constituent atomic concepts. Our experiments on the ACE 2005 dataset as well as our collected Twitter event dataset show that, CGMN significantly outperforms state-of-the-art event detection methods on unseen classes and demonstrate strong zero-shot compositional generalization capabilities.

Degree

thesis:*
Level thesis:degree_level
Masters
Department dc:contributor.department
Electrical and Computer Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2021

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zhuang, Yuchen
Advisor dc:contributor.advisor
  • Bloch, Matthieu R.
Committee members dc:contributor.committeemember
  • Lee, Chin-Hui
  • Juang, Biing Hwang
  • Davenport, Mark

Subjects

dc:subject × 1

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1853/64680

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Zhuang, Yuchen. ZERO-SHOT COMPOSITIONAL EVENT DETECTION VIA GRAPH MODULAR NETWORK. Masters thesis, Georgia Institute of Technology, 2021. http://hdl.handle.net/1853/64680