A Systematic Survey of Text Worlds as Embodied Natural Language Environments

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

5 Scopus citations

Abstract

Text Worlds are virtual environments for embodied agents that, unlike 2D or 3D environments, are rendered exclusively using textual descriptions. These environments offer an alternative to higher-fidelity 3D environments due to their low barrier to entry, providing the ability to study semantics, compositional inference, and other high-level tasks with rich action spaces while controlling for perceptual input. This systematic survey outlines recent developments in tooling, environments, and agent modeling for Text Worlds, while examining recent trends in knowledge graphs, common sense reasoning, transfer learning of Text World performance to higher-fidelity environments, as well as near-term development targets that, once achieved, make Text Worlds an attractive general research paradigm for natural language processing.

Original languageEnglish (US)
Title of host publicationWordplay 2022 - 3rd Wordplay
Subtitle of host publicationWhen Language Meets Games Workshop, Proceedings of the Workshop
EditorsMarc-Alexandre Cote, Xingdi Yuan, Prithviraj Ammanabrolu
PublisherAssociation for Computational Linguistics (ACL)
Pages1-15
Number of pages15
ISBN (Electronic)9781955917810
StatePublished - 2022
Event3rd Wordplay: When Language Meets Games Workshop, Wordplay 2022 - Seattle, United States
Duration: Jul 14 2022 → …

Publication series

NameWordplay 2022 - 3rd Wordplay: When Language Meets Games Workshop, Proceedings of the Workshop

Conference

Conference3rd Wordplay: When Language Meets Games Workshop, Wordplay 2022
Country/TerritoryUnited States
CitySeattle
Period7/14/22 → …

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'A Systematic Survey of Text Worlds as Embodied Natural Language Environments'. Together they form a unique fingerprint.

Cite this