Neurosymbolic AI for Situated Language Understanding
This work is significant for researchers in natural language processing and AI who are struggling with the generalization and transferability issues of current data-intensive models, offering an incremental approach by reincorporating classic AI ideas.
This paper proposes a neurosymbolic AI model for situated language understanding that addresses the limitations of data-intensive deep neural networks in transferring skills to novel situations. It achieves this by creating situational representations that act as formal models of salient phenomena and provide rich, task-appropriate data for training flexible computational models.
In recent years, data-intensive AI, particularly the domain of natural language processing and understanding, has seen significant progress driven by the advent of large datasets and deep neural networks that have sidelined more classic AI approaches to the field. These systems can apparently demonstrate sophisticated linguistic understanding or generation capabilities, but often fail to transfer their skills to situations they have not encountered before. We argue that computational situated grounding provides a solution to some of these learning challenges by creating situational representations that both serve as a formal model of the salient phenomena, and contain rich amounts of exploitable, task-appropriate data for training new, flexible computational models. Our model reincorporates some ideas of classic AI into a framework of neurosymbolic intelligence, using multimodal contextual modeling of interactive situations, events, and object properties. We discuss how situated grounding provides diverse data and multiple levels of modeling for a variety of AI learning challenges, including learning how to interact with object affordances, learning semantics for novel structures and configurations, and transferring such learned knowledge to new objects and situations.