| tech,0-1-C04-1103,bq | <term> referring expressions </term> . <term> | Machine transliteration/back-transliteration | </term> plays an important role in many <term> | #5729 The evaluation using another 23 subjects showed that the proposed method could effectively generate proper referring expressions.Machine transliteration/back-transliteration plays an important role in many multilingual speech and language applications. |
| other,8-1-C04-1103,bq | </term> plays an important role in many <term> | multilingual speech and language applications | </term> . In this paper , a novel framework | #5737 Machine transliteration/back-transliteration plays an important role in manymultilingual speech and language applications. |
| tech,8-2-C04-1103,bq | this paper , a novel framework for <term> | machine transliteration/back transliteration | </term> that allows us to carry out <term> | #5751 In this paper, a novel framework formachine transliteration/back transliteration that allows us to carry out direct orthographical mapping (DOM) between two different languages is presented. |
| other,17-2-C04-1103,bq | </term> that allows us to carry out <term> | direct orthographical mapping ( DOM ) | </term> between two different <term> languages | #5760 In this paper, a novel framework for machine transliteration/back transliteration that allows us to carry outdirect orthographical mapping ( DOM ) between two different languages is presented. |
| other,26-2-C04-1103,bq | DOM ) </term> between two different <term> | languages | </term> is presented . Under this framework | #5769 In this paper, a novel framework for machine transliteration/back transliteration that allows us to carry out direct orthographical mapping (DOM) between two differentlanguages is presented. |
| model,5-3-C04-1103,bq | presented . Under this framework , a <term> | joint source-channel transliteration model | </term> , also called <term> n-gram transliteration | #5778 Under this framework, ajoint source-channel transliteration model, also called n-gram transliteration model (ngram TM), is further proposed to model the transliteration process. |
| model,12-3-C04-1103,bq | transliteration model </term> , also called <term> | n-gram transliteration model ( ngram TM ) | </term> , is further proposed to model the | #5785 Under this framework, a joint source-channel transliteration model, also calledn-gram transliteration model ( ngram TM ), is further proposed to model the transliteration process. |
| tech,26-3-C04-1103,bq | , is further proposed to model the <term> | transliteration process | </term> . We evaluate the proposed methods | #5799 Under this framework, a joint source-channel transliteration model, also called n-gram transliteration model (ngram TM), is further proposed to model thetransliteration process. |
| tech,7-4-C04-1103,bq | the proposed methods through several <term> | transliteration/back transliteration | </term> experiments for <term> English/Chinese | #5809 We evaluate the proposed methods through severaltransliteration/back transliteration experiments for English/Chinese and English/Japanese language pairs. |
| other,11-4-C04-1103,bq | transliteration </term> experiments for <term> | English/Chinese and English/Japanese language pairs | </term> . Our study reveals that the proposed | #5813 We evaluate the proposed methods through several transliteration/back transliteration experiments forEnglish/Chinese and English/Japanese language pairs. |
| measure(ment),19-5-C04-1103,bq | development effort but also improves the <term> | transliteration accuracy | </term> significantly . The reality of <term> | #5838 Our study reveals that the proposed method not only reduces an extensive system development effort but also improves thetransliteration accuracy significantly. |
