Visually-grounded planning without vision: Language models infer detailed plans from high-level instructions

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

2 Scopus citations

Abstract

The recently proposed ALFRED challenge task aims for a virtual robotic agent to complete complex multi-step everyday tasks in a virtual home environment from high-level natural language directives, such as “put a hot piece of bread on a plate”. Currently, the best-performing models are able to complete less than 5% of these tasks successfully. In this work we focus on modeling the translation problem of converting natural language directives into detailed multi-step sequences of actions that accomplish those goals in the virtual environment. We empirically demonstrate that it is possible to generate gold multi-step plans from language directives alone without any visual input in 26% of unseen cases. When a small amount of visual information is incorporated, namely the starting location in the virtual environment, our best-performing GPT-2 model successfully generates gold command sequences in 58% of cases. Our results suggest that contextualized language models may provide strong visual semantic planning modules for grounded virtual agents.

Original languageEnglish (US)
Title of host publicationFindings of the Association for Computational Linguistics Findings of ACL
Subtitle of host publicationEMNLP 2020
PublisherAssociation for Computational Linguistics (ACL)
Pages4412-4417
Number of pages6
ISBN (Electronic)9781952148903
StatePublished - 2020
EventFindings of the Association for Computational Linguistics, ACL 2020: EMNLP 2020 - Virtual, Online
Duration: Nov 16 2020Nov 20 2020

Publication series

NameFindings of the Association for Computational Linguistics Findings of ACL: EMNLP 2020

Conference

ConferenceFindings of the Association for Computational Linguistics, ACL 2020: EMNLP 2020
CityVirtual, Online
Period11/16/2011/20/20

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Visually-grounded planning without vision: Language models infer detailed plans from high-level instructions'. Together they form a unique fingerprint.

Cite this