Abstract

Simultaneous interpretation, translation of the spoken word in real-time, is both highly challenging and physically demanding. Methods to predict interpreter confidence and the adequacy of the interpreted message have a number of potential applications, such as in computer-assisted interpretation interfaces or pedagogical tools. We propose the task of predicting simultaneous interpreter performance by building on existing methodology for quality estimation (QE) of machine translation output. In experiments over five settings in three language pairs, we extend a QE pipeline to estimate interpreter performance (as approximated by the METEOR evaluation metric) and propose novel features reflecting interpretation strategy and evaluation measures that further improve prediction accuracy.

Highlights

  • Simultaneous Interpretation (SI) is an inherently difficult task that carries significant cognitive and attentional burdens

  • We examine the task of estimating simultaneous interpreter performance: automatically predicting when interpreters are interpreting smoothly and when they are struggling

  • This has several immediate potential applications, one of which being in Computer-Assisted Interpretation (CAI)

Read more

Summary

Introduction

Simultaneous Interpretation (SI) is an inherently difficult task that carries significant cognitive and attentional burdens. While this might improve the quality of interpreter output, there is a danger that these systems will provide too much information and increase the cognitive load imposed upon the interpreter (Fantinouli, 2018). The system can minimize distraction by providing assistance only when an interpreter is struggling This level of support could be moderated appropriately if interpreter performance can be accurately predicted. The remainder of the paper describes methods and experiments on English-Japanese (ENJA), English-French (EN-FR), and English-Italian (EN-IT) interpretation data attempting to answer these questions

Quality Estimation
Quality Estimation for Interpretation
Interpretation-specific Features
Evaluation Metric
Data: Interpretation Corpora
Interpreter Quality Experiments
Results
Analysis
Conclusion
Full Text

Published Version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.