Extracting Time Critical Information from Dynamic Text

As online chat and e-mail become more integral to critical operations, it becomes more important to recognize critical information and direct it where it is most needed. In response to these needs, we propose a novel approach to extracting domain-specific, time-critical information from dynamic text. Traditional Information Extraction (IE) approaches are unsuitable for analyzing chat streams for many reasons: the text is “dirty” (containing typos, misspellings, sparse punctuation, etc.), messages are fragmented and refer implicitly to previous messages and shared knowledge, messages from multiple topics are interleaved, etc. Our Chat-IE system will use a collection of techniques to process a chat stream that is being used in support of an ongoing activity. Exploiting the context of the ongoing activity will be crucial to extraction effectiveness, as will teasing out the individual dialogs that structure the chat stream. The IE process must also be modified in order to support extraction from those dialogs. In addition, the results of the entire process must be analyzed to determine its accuracy, criticality, completeness, and veracity. In Phase II we will build on the strong foundation established in Phase I to construct and field our new technology and proceed toward successful commercialization.