Abstract
We demonstrate a system for understanding natural language utterances for structure description and placement in a situated blocks world context. By relying on a rich, domain-specific adaptation of a generic ontology and a logical form structure produced by a semantic parser, we obviate the need for an intermediate, domain-specific representation and can produce a reasoner that grounds and reasons over concepts and constraints with real-valued data. This linguistic base enables more flexibility in interpreting natural language expressions invoking intrinsic concepts and features of structures and space. We demonstrate some of the capabilities of a system grounded in deep language understanding and present initial results in a structure learning task.- Anthology ID:
- W18-1402
- Volume:
- Proceedings of the First International Workshop on Spatial Language Understanding
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans
- Venue:
- SpLU
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12–20
- Language:
- URL:
- https://aclanthology.org/W18-1402
- DOI:
- 10.18653/v1/W18-1402
- Cite (ACL):
- Ian Perera, James Allen, Choh Man Teng, and Lucian Galescu. 2018. Building and Learning Structures in a Situated Blocks World Through Deep Language Understanding. In Proceedings of the First International Workshop on Spatial Language Understanding, pages 12–20, New Orleans. Association for Computational Linguistics.
- Cite (Informal):
- Building and Learning Structures in a Situated Blocks World Through Deep Language Understanding (Perera et al., SpLU 2018)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/W18-1402.pdf