2024/06/07 by Pavan Holur, Holur, Pavan, Shreyas Rajesh +5 · 1 citation
Business, Management and Accounting · Computer Science · #AI-based Problem Solving and Planning #Artificial Intelligence (cs.AI) #Business Process Modeling and Analysis #Computation and Language (cs.CL) #FOS: Computer and information sciences #Semantic Web and Ontologies
paper · pdf · doi:10.48550/arxiv.2406.04555
openalex publication_date 2024/06/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
An experienced human Observer reading a document -- such as a crime report -- creates a succinct plot-like ``Working Memory'' comprising different actors, their prototypical roles and states at any point, their evolution over time based on their interactions, and even a map of missing Semantic parts anticipating them in the future. An equivalent AI Observer currently does not exist. We introduce the [G]enerative [S]emantic [W]orkspace (GSW) -- comprising an ``Operator'' and a ``Reconciler'' -- that leverages advancements in LLMs to create a generative-style Semantic framework, as opposed to a traditionally predefined set of lexicon labels. Given a text segment Cn that describes an ongoing situation, the Operator instantiates actor-centric Semantic maps (termed ``Workspace instance'' Wn). The Reconciler resolves differences between Wn and a ``Working memory'' Mn^* to generate the updated Mn+1^*. GSW outperforms well-known baselines on several tasks (∼ 94% vs. FST, GLEN, BertSRL - multi-sentence Semantics extraction, ∼ 15% vs. NLI-BERT, ∼ 35% vs. QA). By mirroring the real Observer, GSW provides the first step towards Spatial Computing assistants capable of understanding individual intentions and predicting future behavior.