Knowledge Engineering in the Long Game of Artificial Intelligence: The Case of Speech Acts
This addresses the problem of creating adaptable, lifelong learning agents for AI researchers, but it appears incremental as it builds on existing knowledge-centric architectures.
The paper tackles the challenge of developing holistic language-endowed intelligent agents by proposing knowledge engineering principles, using dialog act modeling as an example, and highlights limitations of past isolated approaches.
This paper describes principles and practices of knowledge engineering that enable the development of holistic language-endowed intelligent agents that can function across domains and applications, as well as expand their ontological and lexical knowledge through lifelong learning. For illustration, we focus on dialog act modeling, a task that has been widely pursued in linguistics, cognitive modeling, and statistical natural language processing. We describe an integrative approach grounded in the OntoAgent knowledge-centric cognitive architecture and highlight the limitations of past approaches that isolate dialog from other agent functionalities.