Locating knowledge sources through keyphrase extraction

There are a large number of tasks for which keyphrases can be useful. Manually identifying keyphrases can be a tedious and time consuming process that requires expertise, but if automated could save time and aid in creating metadata that could be used to locate knowledge sources. In this paper, the authors present an automated process for keyphrase extraction from email messages. The process enables users to find other people who might hold the knowledge they require from information communicated via the email system. The effectiveness of the extraction system is tested and compared against other extraction systems and the overall value of extracting information from email explored.