| lr,12-4-C92-1055,ak | the possible variations between the <term> | training corpus | </term> and the real tasks are also taken | #22863 To make the proposed algorithm robust, the possible variations between the training corpus and the real tasks are also taken into consideration by enlarging the separation margin between the correct candidate and its competing members. | |
| model,14-2-C92-1055,ak | approximation error </term> introduced by the <term> | language model | </term> , traditional <term> statistical approaches | #22806 Owing to the problem of insufficient training data and approximation error introduced by the language model , traditional statistical approaches, which resolve ambiguities by indirectly and implicitly using maximum likelihood method, fail to achieve high performance in real applications. | |
| other,26-4-C92-1055,ak | into consideration by enlarging the <term> | separation margin | </term> between the correct <term> candidate | #22877 To make the proposed algorithm robust, the possible variations between the training corpus and the real tasks are also taken into consideration by enlarging the separation margin between the correct candidate and its competing members. | |
| other,9-2-C92-1055,ak | insufficient <term> training data </term> and <term> | approximation error | </term> introduced by the <term> language | #22801 Owing to the problem of insufficient training data and approximation error introduced by the language model, traditional statistical approaches, which resolve ambiguities by indirectly and implicitly using maximum likelihood method, fail to achieve high performance in real applications. |
