The client is provided with a natural language WWW interface to the department's online expertise. Suppose the client is the CS student from our example who enters the following question: What is a good first book on Scheme?
CIE first finds the relevant topics. When a topic is found, CIE checks if it has any information accounts. For each information account, the system checks for a match among the nonrelevant questions. If such a match is found, the information account is no longer considered. Otherwise, the system iterates through its Q&A collection, computing a similarity score between each Q&A and the submitted question. The Q&A with the highest score is presented to the client. Figure 3 shows one such pair. The left side of the interface contains information on the expert from whose information account the Q&A is retrieved. The client can evaluate the quality of retrieval, request to continue the search, view the expert's expertise, or e-mail the expert. Thus, the client not only receives an answer to his question, but also is introduced to an expert for future reference.
Figure 3: Receiving an Answer from CIE
When the question is related to several topics, the system initiates a dialog with the client. Suppose the next question submitted by the student is: What is the difference between Scheme and Common Lisp? Figure 4 presents the resulting CIE-generated interface for the client to indicate his or her preferences. The client can search each retrieved topic separately, search all the topics, or tell the system that none of the retrieved topics is relevant.
Figure 4: Resolving Ambiguity through a Simple Dialog