PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World

Rowan Zellers, Ari Holtzman, Matthew Peters, Roozbeh Mottaghi, Aniruddha Kembhavi, Ali Farhadi, Yejin Choi


Abstract
We propose PIGLeT: a model that learns physical commonsense knowledge through interaction, and then uses this knowledge to ground language. We factorize PIGLeT into a physical dynamics model, and a separate language model. Our dynamics model learns not just what objects are but also what they do: glass cups break when thrown, plastic ones don’t. We then use it as the interface to our language model, giving us a unified model of linguistic form and grounded meaning. PIGLeT can read a sentence, simulate neurally what might happen next, and then communicate that result through a literal symbolic representation, or natural language. Experimental results show that our model effectively learns world dynamics, along with how to communicate them. It is able to correctly forecast what happens next given an English sentence over 80% of the time, outperforming a 100x larger, text-to-text approach by over 10%. Likewise, its natural language summaries of physical interactions are also judged by humans as more accurate than LM alternatives. We present comprehensive analysis showing room for future work.
Anthology ID:
2021.acl-long.159
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2040–2050
Language:
URL:
https://aclanthology.org/2021.acl-long.159
DOI:
10.18653/v1/2021.acl-long.159
Bibkey:
Cite (ACL):
Rowan Zellers, Ari Holtzman, Matthew Peters, Roozbeh Mottaghi, Aniruddha Kembhavi, Ali Farhadi, and Yejin Choi. 2021. PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2040–2050, Online. Association for Computational Linguistics.
Cite (Informal):
PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World (Zellers et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2021.acl-long.159.pdf
Optional supplementary material:
 2021.acl-long.159.OptionalSupplementaryMaterial.zip
Video:
 https://preview.aclanthology.org/nschneid-patch-2/2021.acl-long.159.mp4
Data
VCR