| tech,24-2-A94-1011,bq | </term> are to be successfully applied in <term> | IR | </term> . A novel method for adding <term> | #19943 This perplexing fact needs both an explanation and a solution if the power of recently developed NLP techniques are to be successfully applied inIR. |
| other,36-7-A94-1011,bq | improved performance for sophisticated <term> | representations | </term> . It therefore shows that <term> statistical | #20132 We then proceed to repeat results which show that standard statistical models are not particularly suitable for exploiting linguistically sophisticated representations, and show that a statistically fitted rule-based model provides significantly improved performance for sophisticatedrepresentations. |
| other,45-3-A94-1011,bq | inherently extensible to more sophisticated <term> | annotation | </term> , and does not require a <term> pre-tagged | #19990 A novel method for adding linguistic annotation to corpora is presented which involves using a statistical POS tagger in conjunction with unsupervised structure finding methods to derive notions of noun group, verb group, and so on which is inherently extensible to more sophisticatedannotation, and does not require a pre-tagged corpus to fit. |
| other,23-4-A94-1011,bq | representation </term> of them is that <term> | linguistically sophisticated units | </term> are more frequently individually | #20025 One of the distinguishing features of a more linguistically sophisticated representation of documents over a word set based representation of them is thatlinguistically sophisticated units are more frequently individually good predictors of document descriptors (keywords) than single words are. |
| other,25-6-A94-1011,bq | theory about these probably-correct <term> | rules | </term> . We then proceed to repeat results | #20094 We investigate how sets of individually high-precision rules can result in a low precision when used together, and develop some theory about these probably-correctrules. |
| other,26-9-A94-1011,bq | based tool </term> to be used in the <term> | technical abstracting industry | </term> . This paper proposes a model using | #20189 This paper reports on work done for the LRE project SmTA double check, which is creating a PC based tool to be used in thetechnical abstracting industry. |
| other,40-4-A94-1011,bq | descriptors ( keywords ) </term> than single <term> | words | </term> are . This leads us to consider the | #20042 One of the distinguishing features of a more linguistically sophisticated representation of documents over a word set based representation of them is that linguistically sophisticated units are more frequently individually good predictors of document descriptors (keywords) than singlewords are. |
| tech,4-8-A94-1011,bq | representations </term> . It therefore shows that <term> | statistical systems | </term> can exploit <term> sophisticated representations | #20138 It therefore shows thatstatistical systems can exploit sophisticated representations of documents, and lends some support to the use of more linguistically sophisticated representations for document classification. |
| other,18-7-A94-1011,bq | particularly suitable for exploiting <term> | linguistically sophisticated representations | </term> , and show that a <term> statistically | #20114 We then proceed to repeat results which show that standard statistical models are not particularly suitable for exploitinglinguistically sophisticated representations, and show that a statistically fitted rule-based model provides significantly improved performance for sophisticated representations. |
| other,22-8-A94-1011,bq | lends some support to the use of more <term> | linguistically sophisticated representations | </term> for <term> document classification </term> | #20156 It therefore shows that statistical systems can exploit sophisticated representations of documents, and lends some support to the use of morelinguistically sophisticated representations for document classification. |
| other,8-9-A94-1011,bq | paper reports on work done for the <term> | LRE project SmTA double check | </term> , which is creating a <term> PC based | #20171 This paper reports on work done for theLRE project SmTA double check, which is creating a PC based tool to be used in the technical abstracting industry. |
| other,7-6-A94-1011,bq | sets of individually high-precision <term> | rules | </term> can result in a <term> low precision | #20076 We investigate how sets of individually high-precisionrules can result in a low precision when used together, and develop some theory about these probably-correct rules. |
| other,11-5-A94-1011,bq | <term> descriptors </term> from individual <term> | phrases | </term> rather than from the <term> weighted | #20056 This leads us to consider the assignment of descriptors from individualphrases rather than from the weighted sum of a word set representation. |
| tech,18-1-A94-1011,bq | in performance within the standard <term> | term weighting statistical assignment paradigm | </term> ( Fagan 1987 ; Lewis , 1992bc ; Buckley | #19901 The use of NLP techniques for document classification has not produced significant improvements in performance within the standardterm weighting statistical assignment paradigm (Fagan 1987; Lewis, 1992bc; Buckley, 1993). |
| tech,3-1-A94-1011,bq | translation </term> use . The use of <term> | NLP techniques | </term> for <term> document classification </term> | #19886 The use ofNLP techniques for document classification has not produced significant improvements in performance within the standard term weighting statistical assignment paradigm (Fagan 1987; Lewis, 1992bc; Buckley, 1993). |
| measure(ment),12-6-A94-1011,bq | high-precision <term> rules </term> can result in a <term> | low precision | </term> when used together , and develop | #20081 We investigate how sets of individually high-precision rules can result in alow precision when used together, and develop some theory about these probably-correct rules. |
| tech,10-7-A94-1011,bq | repeat results which show that standard <term> | statistical models | </term> are not particularly suitable for | #20106 We then proceed to repeat results which show that standardstatistical models are not particularly suitable for exploiting linguistically sophisticated representations, and show that a statistically fitted rule-based model provides significantly improved performance for sophisticated representations. |
| other,8-5-A94-1011,bq | leads us to consider the assignment of <term> | descriptors | </term> from individual <term> phrases </term> | #20053 This leads us to consider the assignment ofdescriptors from individual phrases rather than from the weighted sum of a word set representation. |
| tech,26-8-A94-1011,bq | sophisticated representations </term> for <term> | document classification | </term> . This paper reports on work done | #20160 It therefore shows that statistical systems can exploit sophisticated representations of documents, and lends some support to the use of more linguistically sophisticated representations fordocument classification. |
| tech,21-3-A94-1011,bq | POS tagger </term> in conjunction with <term> | unsupervised structure finding methods | </term> to derive notions of <term> noun group | #19966 A novel method for adding linguistic annotation to corpora is presented which involves using a statistical POS tagger in conjunction withunsupervised structure finding methods to derive notions of noun group, verb group, and so on which is inherently extensible to more sophisticated annotation, and does not require a pre-tagged corpus to fit. |
