| other,46-2-I05-5008,ak | <term> meaning equivalence </term> or <term> | entailment | </term> ; and , ( iii ) the amount of internal | #7636 We measured the quality of the paraphrases produced in an experiment, i.e., (i) their grammaticality: at least 99% correct sentences; (ii) their equivalence in meaning: at least 96% correct paraphrases either by meaning equivalence orentailment; and, (iii) the amount of internal lexical and syntactical variation in a set of paraphrases: slightly superior to that of hand-produced sets. | |
| other,18-2-I05-5008,ak | an experiment , i.e. , ( i ) their <term> | grammaticality | </term> : at least 99 % correct sentences | #7608 We measured the quality of the paraphrases produced in an experiment, i.e., (i) theirgrammaticality: at least 99% correct sentences; (ii) their equivalence in meaning: at least 96% correct paraphrases either by meaning equivalence or entailment; and, (iii) the amount of internal lexical and syntactical variation in a set of paraphrases: slightly superior to that of hand-produced sets. | |
| other,33-2-I05-5008,ak | ) their <term> equivalence </term> in <term> | meaning | </term> : at least 96 % correct <term> paraphrases | #7623 We measured the quality of the paraphrases produced in an experiment, i.e., (i) their grammaticality: at least 99% correct sentences; (ii) their equivalence inmeaning: at least 96% correct paraphrases either by meaning equivalence or entailment; and, (iii) the amount of internal lexical and syntactical variation in a set of paraphrases: slightly superior to that of hand-produced sets. | |
| other,65-2-I05-5008,ak | syntactical variation </term> in a set of <term> | paraphrases | </term> : slightly superior to that of hand-produced | #7655 We measured the quality of the paraphrases produced in an experiment, i.e., (i) their grammaticality: at least 99% correct sentences; (ii) their equivalence in meaning: at least 96% correct paraphrases either by meaning equivalence or entailment; and, (iii) the amount of internal lexical and syntactical variation in a set ofparaphrases: slightly superior to that of hand-produced sets. | |
| measure(ment),17-3-I05-5008,ak | reference sets </term> to be used for <term> | MT evaluation | </term> . This paper presents an <term> evaluation | #7682 The paraphrase sets produced by this method thus seem adequate as reference sets to be used forMT evaluation. | |
| measure(ment),27-1-I05-5008,ak | measures </term> like <term> BLEU </term> and <term> | NIST | </term> . We measured the quality of the <term> | #7588 We propose a method that automatically generates paraphrase sets from seed sentences to be used as reference sets in objective machine translation evaluation measures like BLEU andNIST. | |
| measure(ment),25-1-I05-5008,ak | translation evaluation measures </term> like <term> | BLEU | </term> and <term> NIST </term> . We measured | #7586 We propose a method that automatically generates paraphrase sets from seed sentences to be used as reference sets in objective machine translation evaluation measures likeBLEU and NIST. | |
| other,40-2-I05-5008,ak | meaning </term> : at least 96 % correct <term> | paraphrases | </term> either by <term> meaning equivalence | #7630 We measured the quality of the paraphrases produced in an experiment, i.e., (i) their grammaticality: at least 99% correct sentences; (ii) their equivalence in meaning: at least 96% correctparaphrases either by meaning equivalence or entailment; and, (iii) the amount of internal lexical and syntactical variation in a set of paraphrases: slightly superior to that of hand-produced sets. | |
| other,7-1-I05-5008,ak | method that automatically generates <term> | paraphrase sets | </term> from <term> seed sentences </term> to | #7568 We propose a method that automatically generatesparaphrase sets from seed sentences to be used as reference sets in objective machine translation evaluation measures like BLEU and NIST. | |
| other,57-2-I05-5008,ak | and , ( iii ) the amount of internal <term> | lexical and syntactical variation | </term> in a set of <term> paraphrases </term> | #7647 We measured the quality of the paraphrases produced in an experiment, i.e., (i) their grammaticality: at least 99% correct sentences; (ii) their equivalence in meaning: at least 96% correct paraphrases either by meaning equivalence or entailment; and, (iii) the amount of internallexical and syntactical variation in a set of paraphrases: slightly superior to that of hand-produced sets. | |
| other,31-2-I05-5008,ak | % correct sentences ; ( ii ) their <term> | equivalence | </term> in <term> meaning </term> : at least | #7621 We measured the quality of the paraphrases produced in an experiment, i.e., (i) their grammaticality: at least 99% correct sentences; (ii) theirequivalence in meaning: at least 96% correct paraphrases either by meaning equivalence or entailment; and, (iii) the amount of internal lexical and syntactical variation in a set of paraphrases: slightly superior to that of hand-produced sets. | |
| other,16-1-I05-5008,ak | seed sentences </term> to be used as <term> | reference sets | </term> in <term> objective machine translation | #7577 We propose a method that automatically generates paraphrase sets from seed sentences to be used asreference sets in objective machine translation evaluation measures like BLEU and NIST. | |
| measure(ment),19-1-I05-5008,ak | used as <term> reference sets </term> in <term> | objective machine translation evaluation measures | </term> like <term> BLEU </term> and <term> NIST | #7580 We propose a method that automatically generates paraphrase sets from seed sentences to be used as reference sets inobjective machine translation evaluation measures like BLEU and NIST. | |
| other,43-2-I05-5008,ak | correct <term> paraphrases </term> either by <term> | meaning equivalence | </term> or <term> entailment </term> ; and , | #7633 We measured the quality of the paraphrases produced in an experiment, i.e., (i) their grammaticality: at least 99% correct sentences; (ii) their equivalence in meaning: at least 96% correct paraphrases either bymeaning equivalence or entailment; and, (iii) the amount of internal lexical and syntactical variation in a set of paraphrases: slightly superior to that of hand-produced sets. | |
| other,1-3-I05-5008,ak | to that of hand-produced sets . The <term> | paraphrase sets | </term> produced by this method thus seem | #7666 Theparaphrase sets produced by this method thus seem adequate as reference sets to be used for MT evaluation. | |
| other,6-2-I05-5008,ak | </term> . We measured the quality of the <term> | paraphrases | </term> produced in an experiment , i.e. | #7596 We measured the quality of theparaphrases produced in an experiment, i.e., (i) their grammaticality: at least 99% correct sentences; (ii) their equivalence in meaning: at least 96% correct paraphrases either by meaning equivalence or entailment; and, (iii) the amount of internal lexical and syntactical variation in a set of paraphrases: slightly superior to that of hand-produced sets. | |
| other,10-1-I05-5008,ak | generates <term> paraphrase sets </term> from <term> | seed sentences | </term> to be used as <term> reference sets | #7571 We propose a method that automatically generates paraphrase sets fromseed sentences to be used as reference sets in objective machine translation evaluation measures like BLEU and NIST. | |
| other,11-3-I05-5008,ak | this method thus seem adequate as <term> | reference sets | </term> to be used for <term> MT evaluation | #7676 The paraphrase sets produced by this method thus seem adequate asreference sets to be used for MT evaluation. |
