tech,4-1-I05-5009,ak This paper presents an <term> evaluation method </term> employing a <term> latent variable model </term> for <term> paraphrases </term> with their <term> contexts </term> .
model,8-1-I05-5009,ak This paper presents an <term> evaluation method </term> employing a <term> latent variable model </term> for <term> paraphrases </term> with their <term> contexts </term> .
other,12-1-I05-5009,ak This paper presents an <term> evaluation method </term> employing a <term> latent variable model </term> for <term> paraphrases </term> with their <term> contexts </term> .
other,15-1-I05-5009,ak This paper presents an <term> evaluation method </term> employing a <term> latent variable model </term> for <term> paraphrases </term> with their <term> contexts </term> .
other,4-2-I05-5009,ak We assume that the <term> context </term> of a <term> sentence </term> is indicated by a <term> latent variable </term> of the <term> model </term> as a <term> topic </term> and that the <term> likelihood </term> of each <term> variable </term> can be inferred .
other,7-2-I05-5009,ak We assume that the <term> context </term> of a <term> sentence </term> is indicated by a <term> latent variable </term> of the <term> model </term> as a <term> topic </term> and that the <term> likelihood </term> of each <term> variable </term> can be inferred .
other,12-2-I05-5009,ak We assume that the <term> context </term> of a <term> sentence </term> is indicated by a <term> latent variable </term> of the <term> model </term> as a <term> topic </term> and that the <term> likelihood </term> of each <term> variable </term> can be inferred .
model,16-2-I05-5009,ak We assume that the <term> context </term> of a <term> sentence </term> is indicated by a <term> latent variable </term> of the <term> model </term> as a <term> topic </term> and that the <term> likelihood </term> of each <term> variable </term> can be inferred .
other,19-2-I05-5009,ak We assume that the <term> context </term> of a <term> sentence </term> is indicated by a <term> latent variable </term> of the <term> model </term> as a <term> topic </term> and that the <term> likelihood </term> of each <term> variable </term> can be inferred .
measure(ment),23-2-I05-5009,ak We assume that the <term> context </term> of a <term> sentence </term> is indicated by a <term> latent variable </term> of the <term> model </term> as a <term> topic </term> and that the <term> likelihood </term> of each <term> variable </term> can be inferred .
other,26-2-I05-5009,ak We assume that the <term> context </term> of a <term> sentence </term> is indicated by a <term> latent variable </term> of the <term> model </term> as a <term> topic </term> and that the <term> likelihood </term> of each <term> variable </term> can be inferred .
other,1-3-I05-5009,ak A <term> paraphrase </term> is evaluated for whether its <term> sentences </term> are used in the same <term> context </term> .
other,7-3-I05-5009,ak A <term> paraphrase </term> is evaluated for whether its <term> sentences </term> are used in the same <term> context </term> .
other,13-3-I05-5009,ak A <term> paraphrase </term> is evaluated for whether its <term> sentences </term> are used in the same <term> context </term> .
measure(ment),11-4-I05-5009,ak Experimental results showed that the proposed method achieves almost 60 % <term> accuracy </term> and that there is not a large performance difference between the two <term> models </term> .
model,24-4-I05-5009,ak Experimental results showed that the proposed method achieves almost 60 % <term> accuracy </term> and that there is not a large performance difference between the two <term> models </term> .
measure(ment),5-5-I05-5009,ak The results also revealed an <term> upper bound </term> of <term> accuracy </term> of 77 % with the method when using only <term> topic information </term> .
measure(ment),8-5-I05-5009,ak The results also revealed an <term> upper bound </term> of <term> accuracy </term> of 77 % with the method when using only <term> topic information </term> .
other,18-5-I05-5009,ak The results also revealed an <term> upper bound </term> of <term> accuracy </term> of 77 % with the method when using only <term> topic information </term> .
hide detail