1.   Discovering Coherence and Justification Clusters in Digital Transcripts Using Epistemic


    (Poster Presented in ICAIL 2011)   

  1. Cameron Hughes, Ctest Laboratories

  2. Tracey Hughes, Ctest Laboratories


We are investigating the potential use of courtroom transcripts as sources of social knowledge for Epistemic agents. But we are immediately faced with the reality that not all transcripts are equal. Part of the quality of the transcripts will be directly related to knowledge, consistency and integrity of the individuals that testify during the course of the trial, and part of the quality will rely on the nature and sophistication of the questions asked and answers given. The nature of the knowledge discovered in any given transcript can and will vary widely. Before we can determine whether a transcript will be useful as a knowledge source for an Epistemic agent, we have to identify the nature, consistency, pedigree, integrity and quality of the knowledge present in the transcript. In this paper we show how coherence and justification clusters can be used as part of an epistemic metric that can determine the quality of knowledge present in a transcript. Interrogative domains are domains where the primary activity consists of one or more people asking questions and one or more people giving answers. A civil or criminal trial is one example of an interrogative domain.  Attorney's present questions to defendants, plaintiffs or witnesses, and the witnesses, plaintiffs, or defendants are charged with providing answers to the questions given. Other examples of an interrogative domain are congressional hearings, interviews and surveys.  The question and answer sets taken from an interrogative domain are potential sources of knowledge.  This potential is a result of the fact that given each question & answer pair entails at least one proposition. That proposition asserts something about the world that is either true or false. The agent(s), those individuals who are charged with making a determination or taking an action based on entailed propositions of the question and answer sets are candidate knowers in the interrogative domain. In other words based on the entailed propositions from the question and answer sets of the interrogative domains, what can the agent be said to know?