Cognitive conversation language - CCL

Abstract

Enhancements in ways a conversational agent can participate in human-computer dialog tasks, as well as in the ability of such agents in answering questions has been explored in different research areas in the last years. But some limitations are still present in most of the current conversational agents’ models. In this paper we present a new formal language, named Cognitive Conversation Language (CCL), designed to give support to conversational agents. CCL can be used to help such agents in a variety of tasks, including questions understanding and answer generation. Empirical results of the use of CCL are provided based on experiments using the knowledge base of a well-know never-ending learning system, called NELL (Never-Ending Language Learner). Results obtained in the experiments are empirical evidence that CCL can contribute in improving the quality of a question & answer task.