Towards an Indexical Model of Situated Language Comprehension for Cognitive Agents in Physical Worlds
This work addresses language understanding for agents in physical worlds, but it appears incremental as it builds on existing theories like the Indexical Hypothesis.
The authors tackled the problem of situated language comprehension for cognitive agents by proposing an Indexical Model that translates linguistic symbols to modal representations using multiple information sources, showing it can alleviate ambiguities from underspecific referring expressions and unexpressed verb arguments.
We propose a computational model of situated language comprehension based on the Indexical Hypothesis that generates meaning representations by translating amodal linguistic symbols to modal representations of beliefs, knowledge, and experience external to the linguistic system. This Indexical Model incorporates multiple information sources, including perceptions, domain knowledge, and short-term and long-term experiences during comprehension. We show that exploiting diverse information sources can alleviate ambiguities that arise from contextual use of underspecific referring expressions and unexpressed argument alternations of verbs. The model is being used to support linguistic interactions in Rosie, an agent implemented in Soar that learns from instruction.