Language (Re)modelling: Towards Embodied Language Understanding
This is a foundational proposal for improving NLU systems through embodied approaches, but it's conceptual without implementation results.
This position paper argues that current natural language understanding systems lack human-like efficiency, interpretability, and generalization, and proposes adopting principles from embodied cognitive linguistics to make language executable through mental simulation and metaphoric mappings.
While natural language understanding (NLU) is advancing rapidly, today's technology differs from human-like language understanding in fundamental ways, notably in its inferior efficiency, interpretability, and generalization. This work proposes an approach to representation and learning based on the tenets of embodied cognitive linguistics (ECL). According to ECL, natural language is inherently executable (like programming languages), driven by mental simulation and metaphoric mappings over hierarchical compositions of structures and schemata learned through embodied interaction. This position paper argues that the use of grounding by metaphoric inference and simulation will greatly benefit NLU systems, and proposes a system architecture along with a roadmap towards realizing this vision.