| other,13-3-I05-5009,ak | sentences </term> are used in the same <term> | context | </term> . Experimental results showed that | #7746 A paraphrase is evaluated for whether its sentences are used in the samecontext. | |
| model,24-4-I05-5009,ak | performance difference between the two <term> | models | </term> . The results also revealed an <term> | #7772 Experimental results showed that the proposed method achieves almost 60% accuracy and that there is not a large performance difference between the twomodels. | |
| other,18-5-I05-5009,ak | % with the method when using only <term> | topic information | </term> . This article is devoted to the | #7792 The results also revealed an upper bound of accuracy of 77% with the method when using onlytopic information. | |
| other,15-1-I05-5009,ak | <term> paraphrases </term> with their <term> | contexts | </term> . We assume that the <term> context | #7700 This paper presents an evaluation method employing a latent variable model for paraphrases with theircontexts. | |
| other,19-2-I05-5009,ak | </term> of the <term> model </term> as a <term> | topic | </term> and that the <term> likelihood </term> | #7721 We assume that the context of a sentence is indicated by a latent variable of the model as atopic and that the likelihood of each variable can be inferred. | |
| measure(ment),11-4-I05-5009,ak | proposed method achieves almost 60 % <term> | accuracy | </term> and that there is not a large performance | #7759 Experimental results showed that the proposed method achieves almost 60%accuracy and that there is not a large performance difference between the two models. | |
| other,7-3-I05-5009,ak | </term> is evaluated for whether its <term> | sentences | </term> are used in the same <term> context | #7740 A paraphrase is evaluated for whether itssentences are used in the same context. | |
| model,16-2-I05-5009,ak | <term> latent variable </term> of the <term> | model | </term> as a <term> topic </term> and that the | #7718 We assume that the context of a sentence is indicated by a latent variable of themodel as a topic and that the likelihood of each variable can be inferred. | |
| other,26-2-I05-5009,ak | the <term> likelihood </term> of each <term> | variable | </term> can be inferred . A <term> paraphrase | #7728 We assume that the context of a sentence is indicated by a latent variable of the model as a topic and that the likelihood of eachvariable can be inferred. | |
| tech,4-1-I05-5009,ak | evaluation </term> . This paper presents an <term> | evaluation method | </term> employing a <term> latent variable | #7689 This paper presents anevaluation method employing a latent variable model for paraphrases with their contexts. | |
| model,8-1-I05-5009,ak | evaluation method </term> employing a <term> | latent variable model | </term> for <term> paraphrases </term> with their | #7693 This paper presents an evaluation method employing alatent variable model for paraphrases with their contexts. | |
| other,1-3-I05-5009,ak | variable </term> can be inferred . A <term> | paraphrase | </term> is evaluated for whether its <term> | #7734 Aparaphrase is evaluated for whether its sentences are used in the same context. | |
| other,7-2-I05-5009,ak | assume that the <term> context </term> of a <term> | sentence | </term> is indicated by a <term> latent variable | #7709 We assume that the context of asentence is indicated by a latent variable of the model as a topic and that the likelihood of each variable can be inferred. | |
| measure(ment),8-5-I05-5009,ak | revealed an <term> upper bound </term> of <term> | accuracy | </term> of 77 % with the method when using | #7782 The results also revealed an upper bound ofaccuracy of 77% with the method when using only topic information. | |
| other,4-2-I05-5009,ak | contexts </term> . We assume that the <term> | context | </term> of a <term> sentence </term> is indicated | #7706 We assume that thecontext of a sentence is indicated by a latent variable of the model as a topic and that the likelihood of each variable can be inferred. | |
| measure(ment),5-5-I05-5009,ak | </term> . The results also revealed an <term> | upper bound | </term> of <term> accuracy </term> of 77 % with | #7779 The results also revealed anupper bound of accuracy of 77% with the method when using only topic information. | |
| measure(ment),23-2-I05-5009,ak | as a <term> topic </term> and that the <term> | likelihood | </term> of each <term> variable </term> can be | #7725 We assume that the context of a sentence is indicated by a latent variable of the model as a topic and that thelikelihood of each variable can be inferred. | |
| other,12-2-I05-5009,ak | <term> sentence </term> is indicated by a <term> | latent variable | </term> of the <term> model </term> as a <term> | #7714 We assume that the context of a sentence is indicated by alatent variable of the model as a topic and that the likelihood of each variable can be inferred. | |
| other,12-1-I05-5009,ak | <term> latent variable model </term> for <term> | paraphrases | </term> with their <term> contexts </term> . | #7697 This paper presents an evaluation method employing a latent variable model forparaphrases with their contexts. |
