tech,17-1-H92-1095,bq spoken language understanding </term> , <term> text understanding </term> , and <term> document
tech,24-2-H94-1084,bq </term> , which creates the data for a <term> text retrieval application </term> and the <term>
tech,3-1-C04-1116,bq smaller and more robust . We present a <term> text mining method </term> for finding <term> synonymous
tech,26-3-P04-2005,bq Sense Disambiguation ( WSD ) </term> and <term> Text Summarisation </term> . Our method takes
tech,24-5-P04-2010,bq open-domain question answering </term> and <term> text summarisation </term> . In this paper , we
tech,21-3-H94-1084,bq <term> integration </term> of <term> image and text understanding </term> .
lr,26-6-P03-1050,bq affix lists </term> , and <term> human annotated text </term> , in addition to an <term> unsupervised
other,2-1-C94-1026,bq homophone errors </term> . To align <term> bilingual texts </term> becomes a crucial issue recently
other,26-4-P04-2005,bq exploits the large amount of <term> Chinese text </term> available in <term> corpora </term> and
other,7-6-C94-1026,bq experimental objects are <term> Chinese-English texts </term> , which are selected from different
other,13-1-P84-1078,bq system </term> designed to create <term> cohesive text </term> through the use of <term> lexical substitutions
lr,20-3-I05-4010,bq an authoritative and comprehensive <term> text collection </term> covering the specific
tech,6-1-P84-1078,bq describes <term> Paul </term> , a <term> computer text generation system </term> designed to create
other,27-1-P82-1035,bq newspaper stories </term> and other <term> edited texts </term> . However , a great deal of <term>
other,24-1-N03-4010,bq answering capability </term> on <term> free text </term> . The demonstration will focus on
lr,19-2-N03-4010,bq answer candidates </term> from the given <term> text corpus </term> . The operation of the <term>
tech,38-3-H01-1040,bq increased potential of <term> IE-enhanced text browsers </term> . At MIT Lincoln Laboratory
tech,15-2-N06-4001,bq researchers who are not experts in <term> text mining </term> . As evidence of its usefulness
other,10-2-A88-1001,bq heuristically-produced complete <term> sentences </term> in <term> text </term> or <term> text-to-speech form </term>
other,13-1-P82-1035,bq under the assumption that the input <term> text </term> will be in reasonably neat form ,
hide detail