Pragmatics and Agent Communication Languages

With an eye to increased efficiency, agent communication language (ACL) designers have heeded the analogy with natural language and introduced elements from natural language pragmatics (NLP) into their designs. However, ACL pragmatics has not availed itself of NLP advances to the extent that it could. While a few aspects of pragmatics are incorporated, most notably speech acts, their inclusion ultimately results in a misrepresentation of what pragmatics is and what it can offer to agent communication. There have been positive steps in bringing pragmatics into the agent communication fold, such as work on conversation policies, but even these projects are relatively preliminary. Continued work in ACL pragmatics (ACLP) is hampered by the lack of systematicity in NLP, making it difficult to apply the analogy in a principled way. We develop an informal model of the structure of NLP that (a) systematizes the disparate topics in NLP, and (b) can serve as an interface connecting problems in ACLP with their counterparts in NLP.