| model,6-1-H94-1014,bq | paper introduces a simple mixture <term> | language model | </term> that attempts to capture <term> long | #21217 This paper introduces a simple mixturelanguage model that attempts to capture long distance constraints in a sentence or paragraph. |
| other,12-1-H94-1014,bq | model </term> that attempts to capture <term> | long distance constraints | </term> in a <term> sentence </term> or <term> | #21223 This paper introduces a simple mixture language model that attempts to capturelong distance constraints in a sentence or paragraph. |
| other,17-1-H94-1014,bq | long distance constraints </term> in a <term> | sentence | </term> or <term> paragraph </term> . The <term> | #21228 This paper introduces a simple mixture language model that attempts to capture long distance constraints in asentence or paragraph. |
| other,19-1-H94-1014,bq | </term> in a <term> sentence </term> or <term> | paragraph | </term> . The <term> model </term> is an <term> | #21230 This paper introduces a simple mixture language model that attempts to capture long distance constraints in a sentence orparagraph. |
| model,1-2-H94-1014,bq | </term> or <term> paragraph </term> . The <term> | model | </term> is an <term> m-component mixture </term> | #21233 Themodel is an m-component mixture of trigram models. |
| other,4-2-H94-1014,bq | </term> . The <term> model </term> is an <term> | m-component mixture | </term> of <term> trigram models </term> . The | #21236 The model is anm-component mixture of trigram models. |
| model,7-2-H94-1014,bq | <term> m-component mixture </term> of <term> | trigram models | </term> . The models were constructed using | #21239 The model is an m-component mixture oftrigram models. |
| lr,7-3-H94-1014,bq | models were constructed using a 5K <term> | vocabulary | </term> and trained using a 76 million <term> | #21249 The models were constructed using a 5Kvocabulary and trained using a 76 million word Wall Street Journal text corpus. |
| other,14-3-H94-1014,bq | </term> and trained using a 76 million <term> | word | </term><term> Wall Street Journal text corpus | #21256 The models were constructed using a 5K vocabulary and trained using a 76 millionword Wall Street Journal text corpus. |
| lr-prod,15-3-H94-1014,bq | using a 76 million <term> word </term><term> | Wall Street Journal text corpus | </term> . Using the <term> BU recognition system | #21257 The models were constructed using a 5K vocabulary and trained using a 76 million wordWall Street Journal text corpus. |
| lr,2-4-H94-1014,bq | Journal text corpus </term> . Using the <term> | BU recognition system | </term> , experiments show a 7 % improvement | #21265 Using theBU recognition system, experiments show a 7% improvement in recognition accuracy with the mixture trigram models as compared to using a trigram model. |
| measure(ment),13-4-H94-1014,bq | experiments show a 7 % improvement in <term> | recognition accuracy | </term> with the <term> mixture trigram models | #21276 Using the BU recognition system, experiments show a 7% improvement inrecognition accuracy with the mixture trigram models as compared to using a trigram model. |
| model,17-4-H94-1014,bq | recognition accuracy </term> with the <term> | mixture trigram models | </term> as compared to using a <term> trigram | #21280 Using the BU recognition system, experiments show a 7% improvement in recognition accuracy with themixture trigram models as compared to using a trigram model. |
| model,25-4-H94-1014,bq | models </term> as compared to using a <term> | trigram model | </term> . This paper describes a method of | #21288 Using the BU recognition system, experiments show a 7% improvement in recognition accuracy with the mixture trigram models as compared to using atrigram model. |
