Abstract
While large language and vision-language models showcase impressive capabilities, they face a notable limitation: the inability to connect language with the physical world. To bridge this gap, research has focused on embodied language learning, where the language learner is situated in the world, perceives it, and interacts with it. This article explores the current standing of research in embodied language learning, highlighting opportunities and discussing common challenges. Lastly, it identifies existing gaps from the perspective of language understanding research within the embodied world and suggests potential future directions.- Anthology ID:
- 2024.findings-acl.908
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2024
- Month:
- August
- Year:
- 2024
- Address:
- Bangkok, Thailand
- Editors:
- Lun-Wei Ku, Andre Martins, Vivek Srikumar
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 15369–15379
- Language:
- URL:
- https://aclanthology.org/2024.findings-acl.908
- DOI:
- 10.18653/v1/2024.findings-acl.908
- Cite (ACL):
- Nadine Amin and Julia Rayz. 2024. Embodied Language Learning: Opportunities, Challenges, and Future Directions. In Findings of the Association for Computational Linguistics: ACL 2024, pages 15369–15379, Bangkok, Thailand. Association for Computational Linguistics.
- Cite (Informal):
- Embodied Language Learning: Opportunities, Challenges, and Future Directions (Amin & Rayz, Findings 2024)
- PDF:
- https://preview.aclanthology.org/autopr/2024.findings-acl.908.pdf