activity
20162024
most citedNeural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision (Short Version)

7 citations · 8 across the 7 of their papers we have counts for

collaborators

7 papers

cs.AI2024

Knowledge Management in the Companion Cognitive Architecture

Constantine Nakos, Kenneth D. Forbus

One of the fundamental aspects of cognitive architectures is their ability to encode and manipulate knowledge. Without a consistent, well-designed, and scalable knowledge managemen…

cs.AI2024

Interactively Diagnosing Errors in a Semantic Parser

Constantine Nakos, Kenneth D. Forbus

Hand-curated natural language systems provide an inspectable, correctable alternative to language systems based on machine learning, but maintaining them requires considerable effo…

cs.AI2024

Qualitative Event Perception: Leveraging Spatiotemporal Episodic Memory for Learning Combat in a Strategy Game

Will Hancock, Kenneth D. Forbus

Event perception refers to people's ability to carve up continuous experience into meaningful discrete events. We speak of finishing our morning coffee, mowing the lawn, leaving wo…

cs.AI20241 cited

A Defeasible Deontic Calculus for Resolving Norm Conflicts

Taylor Olson, Roberto Salas-Damian, Kenneth D. Forbus

When deciding how to act, we must consider other agents' norms and values. However, our norms are ever-evolving. We often add exceptions or change our minds, and thus norms can con…

cs.CV2024

Hybrid Primal Sketch: Combining Analogy, Qualitative Representations, and Computer Vision for Scene Understanding

Kenneth D. Forbus, Kezhen Chen, Wangcheng Xu +1

One of the purposes of perception is to bridge between sensors and conceptual understanding. Marr's Primal Sketch combined initial edge-finding with multiple downstream processes t…

cs.CL2023

Towards Zero-Shot Frame Semantic Parsing with Task Agnostic Ontologies and Simple Labels

Danilo Ribeiro, Omid Abdar, Jack Goetz +4

Frame semantic parsing is an important component of task-oriented dialogue systems. Current models rely on a significant amount training data to successfully identify the intent an…