End-to-End Evaluation in Simultaneous Translation
نویسندگان
چکیده
This paper presents the end-to-end evaluation of an automatic simultaneous translation system, built with state-of-the-art components. It shows whether, and for which situations, such a system might be advantageous when compared to a human interpreter. Using speeches in English translated into Spanish, we present the evaluation procedure and we discuss the results both for the recognition and translation components as well as for the overall system. Even if the translation process remains the Achilles’ heel of the system, the results show that the system can keep at least half of the information, becoming potentially useful for final users.
منابع مشابه
Reflecting on Backward Design for Knowledge Translation; Comment on “A Call for a Backward Design to Knowledge Translation”
In a recent Editorial for this journal, El-Jardali and Fadlallah proposed a new framework for Knowledge Translation (KT) in healthcare. Many such frameworks already exist; thus, new entrants to the field must be scrutinized in regard to their unique contributions to advancing understanding and practice. The El-Jardali and Fadlallah framework focuses on policy-level discussions, a relatively und...
متن کاملThe Effect of EQ and Gender on Oral Cloze Performance of Simultaneous Interpreting Students
This research sought to investigate the relationship between simultaneous interpreters’ oral cloze performance, their emotional intelligence, and gender. In other words, the study tried to predict the variability in performance on simultaneous interpreting (SI) oral cloze test based on the variability in gender, emotional quotient (EQ) and its subscales. To this end, a number of seventy partici...
متن کاملUnsupervised Vocabulary Selection for Domain-Independent Simultaneous Lecture Translation
In this work, we investigate methods to automatically adapt our simultaneous lecture translation systems to the diverse topics that occur in educational lectures. Utilizing materials that are available before the lecture begins, such as lecture slides, our proposed framework iteratively searches for related documents on the World Wide Web and generates lecture-specific models and vocabularies b...
متن کاملSpeed or accuracy? a study in evaluation of simultaneous speech translation
Simultaneous speech translation is a technology that attempts to reduce the delay inherent in speech translation by beginning translation before the end of explicit sentence boundaries. Despite best efforts, there is still often a trade-off between speed and accuracy in these systems, with systems with less delay also achieving lower accuracy. However, somewhat surprisingly, there is no previou...
متن کاملEnd-to-end evaluation in ATR-MATRIX: speech translation system between English and Japanese
ATR Interpreting Telecommunications Research Laboratories developed ATR-MATRIX speech translation system, which translates both ways between English and Japanese, enough to hold natural on-line real-time conversations. Using this system we started an end-to-end evaluation of a speech translation system through a dialog test with naive speakers who are not involved in system development and not ...
متن کامل