Abstract
We present a novel method for using agent experiences gathered through an embodied simulation to ground contextualized word vectors to object representations. We use similarity learning to make comparisons between different object types based on their properties when interacted with, and to extract common features pertaining to the objects’ behavior. We then use an affine transformation to calculate a projection matrix that transforms contextualized word vectors from different transformer-based language models into this learned space, and evaluate whether new test instances of transformed token vectors identify the correct concept in the object embedding space. Our results expose properties of the embedding spaces of four different transformer models and show that grounding object token vectors is usually more helpful to grounding verb and attribute token vectors than the reverse, which reflects earlier conclusions in the analogical reasoning and psycholinguistic literature.- Anthology ID:
- 2023.iwcs-1.32
- Volume:
- Proceedings of the 15th International Conference on Computational Semantics
- Month:
- June
- Year:
- 2023
- Address:
- Nancy, France
- Editors:
- Maxime Amblard, Ellen Breitholtz
- Venue:
- IWCS
- SIG:
- SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 305–317
- Language:
- URL:
- https://aclanthology.org/2023.iwcs-1.32
- DOI:
- Cite (ACL):
- Sadaf Ghaffari and Nikhil Krishnaswamy. 2023. Grounding and Distinguishing Conceptual Vocabulary Through Similarity Learning in Embodied Simulations. In Proceedings of the 15th International Conference on Computational Semantics, pages 305–317, Nancy, France. Association for Computational Linguistics.
- Cite (Informal):
- Grounding and Distinguishing Conceptual Vocabulary Through Similarity Learning in Embodied Simulations (Ghaffari & Krishnaswamy, IWCS 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.iwcs-1.32.pdf