This paper proposes a new methodology to improve the <term> accuracy </term> of a <term> term aggregation system </term> using each author 's text as a coherent <term> corpus </term> .
In this paper , we report a system <term> FROFF </term> which can make a fair copy of not only texts but also graphs and tables indispensable to our papers .
In order to meet the needs of a publication of papers in English , many systems to run off texts have been developed .
lr,0-4-P03-1050,bq <term> Monolingual , unannotated text </term> can be used to further improve the <term> stemmer </term> by allowing it to adapt to a desired <term> domain </term> or <term> genre </term> .
lr,1-3-P03-1050,bq No <term> parallel text </term> is needed after the <term> training phase </term> .
lr,11-4-P04-2010,bq Furthermore , we present a standalone system that resolves <term> pronouns </term> in <term> unannotated text </term> by using a fully automatic sequence of <term> preprocessing modules </term> that mimics the manual <term> annotation process </term> .
lr,19-2-N03-4010,bq The demonstration will focus on how <term> JAVELIN </term> processes <term> questions </term> and retrieves the most likely <term> answer candidates </term> from the given <term> text corpus </term> .
lr,20-3-I05-4010,bq The resultant <term> bilingual corpus </term> , 10.4 M <term> English words </term> and 18.3 M <term> Chinese characters </term> , is an authoritative and comprehensive <term> text collection </term> covering the specific and special domain of HK laws .
lr,26-6-P03-1050,bq Our <term> resource-frugal approach </term> results in 87.5 % <term> agreement </term> with a state of the art , proprietary <term> Arabic stemmer </term> built using <term> rules </term> , <term> affix lists </term> , and <term> human annotated text </term> , in addition to an <term> unsupervised component </term> .
lr-prod,15-3-H94-1014,bq The models were constructed using a 5K <term> vocabulary </term> and trained using a 76 million <term> word </term><term> Wall Street Journal text corpus </term> .
other,0-1-A94-1026,bq <term> Japanese texts </term> frequently suffer from the <term> homophone errors </term> caused by the <term> KANA-KANJI conversion </term> needed to input the <term> text </term> .
other,10-2-A88-1001,bq <term> Multimedia answers </term> include <term> videodisc images </term> and heuristically-produced complete <term> sentences </term> in <term> text </term> or <term> text-to-speech form </term> .
other,10-5-P82-1035,bq This method of using <term> expectations </term> to aid the understanding of <term> scruffy texts </term> has been incorporated into a working <term> computer program </term> called <term> NOMAD </term> , which understands <term> scruffy texts </term> in the domain of Navy messages .
other,11-7-H01-1042,bq Subjects were given a set of up to six extracts of <term> translated newswire text </term> .
other,12-3-C92-4207,bq It is done by an experimental <term> computer program </term><term> SPRINT </term> , which takes <term> natural language texts </term> and produces a <term> model </term> of the described <term> world </term> .
other,12-4-P06-1013,bq Our <term> combination methods </term> rely on <term> predominant senses </term> which are derived automatically from <term> raw text </term> .
other,13-1-P82-1035,bq Most large <term> text-understanding systems </term> have been designed under the assumption that the input <term> text </term> will be in reasonably neat form , e.g. , <term> newspaper stories </term> and other <term> edited texts </term> .
other,13-1-P84-1078,bq This report describes <term> Paul </term> , a <term> computer text generation system </term> designed to create <term> cohesive text </term> through the use of <term> lexical substitutions </term> .
other,13-2-N03-2003,bq In this paper , we show how <term> training data </term> can be supplemented with <term> text </term> from the <term> web </term> filtered to match the <term> style </term> and/or <term> topic </term> of the target <term> recognition task </term> , but also that it is possible to get bigger performance gains from the <term> data </term> by using <term> class-dependent interpolation </term> of <term> N-grams </term> .
other,14-4-C92-4207,bq To reconstruct the <term> model </term> , the authors extract the <term> qualitative spatial constraints </term> from the <term> text </term> , and represent them as the <term> numerical constraints </term> on the <term> spatial attributes </term> of the <term> entities </term> .
hide detail