tool,1-1-N03-4010,ak human language technology </term> . The <term> JAVELIN system </term> integrates a flexible , <term> planning-based
other,7-1-N03-4010,ak system </term> integrates a flexible , <term> planning-based architecture </term> with a variety of <term> language processing
tech,13-1-N03-4010,ak architecture </term> with a variety of <term> language processing modules </term> to provide an <term> open-domain question
tech,19-1-N03-4010,ak processing modules </term> to provide an <term> open-domain question answering capability </term> on <term> free text </term> . The demonstration
other,24-1-N03-4010,ak question answering capability </term> on <term> free text </term> . The demonstration will focus on
tool,6-2-N03-4010,ak The demonstration will focus on how <term> JAVELIN </term> processes <term> questions </term> and
other,8-2-N03-4010,ak on how <term> JAVELIN </term> processes <term> questions </term> and retrieves the most likely <term>
other,14-2-N03-4010,ak </term> and retrieves the most likely <term> answer candidates </term> from the given <term> text corpus </term>
lr,19-2-N03-4010,ak answer candidates </term> from the given <term> text corpus </term> . The operation of the <term> system
tech,4-3-N03-4010,ak corpus </term> . The operation of the <term> system </term> will be explained in depth through
other,13-3-N03-4010,ak explained in depth through browsing the <term> repository </term> of <term> data objects </term> created
other,15-3-N03-4010,ak browsing the <term> repository </term> of <term> data objects </term> created by the <term> system </term>
tech,20-3-N03-4010,ak <term> data objects </term> created by the <term> system </term> during each <term> question answering
other,23-3-N03-4010,ak the <term> system </term> during each <term> question answering session </term> . In this paper we present a novel
skrij podrobnosti