aggregation system </term> using each author 's text as a coherent <term> corpus </term> . Our approach
lr,0-4-P03-1050,bq </term> . <term> Monolingual , unannotated text </term> can be used to further improve the
lr,1-3-P03-1050,bq training resources </term> . No <term> parallel text </term> is needed after the <term> training
lr,11-4-P04-2010,bq <term> pronouns </term> in <term> unannotated text </term> by using a fully automatic sequence
lr,19-2-N03-4010,bq answer candidates </term> from the given <term> text corpus </term> . The operation of the <term>
lr,20-3-I05-4010,bq an authoritative and comprehensive <term> text collection </term> covering the specific
lr,26-6-P03-1050,bq lists </term> , and <term> human annotated text </term> , in addition to an <term> unsupervised
lr-prod,15-3-H94-1014,bq <term> word </term><term> Wall Street Journal text corpus </term> . Using the <term> BU recognition
other,10-2-A88-1001,bq complete <term> sentences </term> in <term> text </term> or <term> text-to-speech form </term>
other,11-7-H01-1042,bq six extracts of <term> translated newswire text </term> . Some of the extracts were <term>
other,12-4-P06-1013,bq are derived automatically from <term> raw text </term> . Experiments using the <term> SemCor
other,13-1-P82-1035,bq under the assumption that the input <term> text </term> will be in reasonably neat form
other,13-1-P84-1078,bq </term> designed to create <term> cohesive text </term> through the use of <term> lexical
other,13-2-N03-2003,bq data </term> can be supplemented with <term> text </term> from the <term> web </term> filtered
other,14-4-C92-4207,bq spatial constraints </term> from the <term> text </term> , and represent them as the <term>
other,16-7-P03-1050,bq average precision </term> over <term> unstemmed text </term> , and 96 % of the performance of
other,17-1-A94-1026,bq conversion </term> needed to input the <term> text </term> . It is critical , therefore , for
other,20-2-P01-1008,bq translations </term> of the same <term> source text </term> . Our approach yields <term> phrasal
other,24-1-N03-4010,bq answering capability </term> on <term> free text </term> . The demonstration will focus on
other,26-4-P04-2005,bq exploits the large amount of <term> Chinese text </term> available in <term> corpora </term>
hide detail