tailieunhanh - Báo cáo khoa học: "Balancing User Effort and Translation Error in Interactive Machine Translation Via Confidence Measures"

This work deals with the application of confidence measures within an interactivepredictive machine translation system in order to reduce human effort. If a small loss in translation quality can be tolerated for the sake of efficiency, user effort can be saved by interactively translating only those initial translations which the confidence measure classifies as incorrect. | Balancing User Effort and Translation Error in Interactive Machine Translation Via Confidence Measures Jesus Gonzalez-Rubio Inst. Tec. de Informatica Univ. Politec. de Valencia 46021 Valencia Spain jegonzalez@ Daniel Ortiz-Martinez Dpto. de Sist Inf. y Comp. Univ. Politec. de Valencia 46021 Valencia Spain dortiz@ Francisco Casacuberta Dpto. de Sist Inf. y Comp. Univ. Politec. de Valencia 46021 Valencia Spain fcn@ Abstract This work deals with the application of confidence measures within an interactive-predictive machine translation system in order to reduce human effort. If a small loss in translation quality can be tolerated for the sake of efficiency user effort can be saved by interactively translating only those initial translations which the confidence measure classifies as incorrect. We apply confidence estimation as a way to achieve a balance between user effort savings and final translation error. Empirical results show that our proposal allows to obtain almost perfect translations while significantly reducing user effort. 1 Introduction In Statistical Machine Translation SMT the translation is modelled as a decission process. For a given source string f 1 fl. fj . f J we seek for the target string e1 e1. .ei. .ei which maximises posterior probability êl argmaxPr eI fJ . 1 I e1 Within the Interactive-predictive Machine Translation IMT framework a state-of-the-art SMT system is employed in the following way For a given source sentence the SMT system fully automatically generates an initial translation. A human translator checks this translation from left to right correcting the first error. The SMT system then proposes a new extension taking the correct prefix ei e1 . . . ei into account. These steps are repeated until the whole input sentence has been correctly translated. In the resulting decision rule we maximise over all possible extensions eI 1 of e ei i argmax Pr ei 11 ei fJ . 2 Tei 1 An implementation of the IMT .

TỪ KHÓA LIÊN QUAN
crossorigin="anonymous">
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.