tech,1-1-C04-1128,bq our approach is successful . While <term> sentence extraction </term> as an approach to <term> summarization
tech,7-1-C04-1128,bq extraction </term> as an approach to <term> summarization </term> has been shown to work in <term> documents
other,14-1-C04-1128,bq summarization </term> has been shown to work in <term> documents </term> of certain <term> genres </term> , because
other,17-1-C04-1128,bq in <term> documents </term> of certain <term> genres </term> , because of the conversational nature
other,25-1-C04-1128,bq because of the conversational nature of <term> email communication </term> where <term> utterances </term> are made
other,28-1-C04-1128,bq <term> email communication </term> where <term> utterances </term> are made in relation to one made
tech,38-1-C04-1128,bq relation to one made previously , <term> sentence extraction </term> may not capture the necessary <term>
other,45-1-C04-1128,bq </term> may not capture the necessary <term> segments </term> of <term> dialogue </term> that would
other,47-1-C04-1128,bq the necessary <term> segments </term> of <term> dialogue </term> that would make a <term> summary </term>
other,52-1-C04-1128,bq <term> dialogue </term> that would make a <term> summary </term> coherent . In this paper , we present
other,12-2-C04-1128,bq present our work on the detection of <term> question-answer pairs </term> in an <term> email conversation </term>
other,16-2-C04-1128,bq <term> question-answer pairs </term> in an <term> email conversation </term> for the task of <term> email summarization
tech,22-2-C04-1128,bq conversation </term> for the task of <term> email summarization </term> . We show that various <term> features
other,4-3-C04-1128,bq summarization </term> . We show that various <term> features </term> based on the structure of <term> email-threads
other,10-3-C04-1128,bq features </term> based on the structure of <term> email-threads </term> can be used to improve upon <term>
other,17-3-C04-1128,bq </term> can be used to improve upon <term> lexical similarity </term> of <term> discourse segments </term>
other,20-3-C04-1128,bq upon <term> lexical similarity </term> of <term> discourse segments </term> for <term> question-answer pairing </term>
tech,23-3-C04-1128,bq <term> discourse segments </term> for <term> question-answer pairing </term> . We present a framework for the
skrij podrobnosti