TR #: 96-41

TR title: Retrieval of Passages for Information Reduction

Author (s): Jody J. Daniels

Address  (Computer Science Department
          Lederle Graduate Research Center
          University of Massachusetts
          Amherst, MA  01003-4601

Date: 19 July 1996

Keywords: Information Retrieval, Passage Retrieval, Case-Based Reasoning

                                 ABSTRACT 


Information Retrieval (IR) typically retrieves entire documents in
response to a user's information need.  However, many times a user
would prefer to examine smaller portions of a document.  One example
of this is when building a frame-based representation of a text.  The
user would like to read all and only those portions of the text that
are about predefined important features.  

This research addresses the problem of automatically locating text
about these features, where the important features are those defined
for use by a case-based reasoning (CBR) system in the form of slots
and fillers.

We propose to use a small set of ``annotations'', textual segments,
that we saved when creating our original case-base to generate queries
and retrieve relevant passages.  Annotations are associated with the
slot about which they provide information.  Using a case-base of
annotations for each slot we generate and pose a query to an IR system
that is aimed at the retrieval of passages within a relevant document.
By locating passages for display to the user, we winnow a text down to
sets of several sentences, greatly reducing the time and effort
expended searching through each text for important features.