Automatic Estimation of Simultaneous Interpreter Performance

TL;DR

This paper introduces a method to automatically predict the performance of simultaneous interpreters by adapting quality estimation techniques from machine translation, incorporating new features for better accuracy across multiple languages.

Contribution

It extends existing quality estimation methods to evaluate interpreter performance, adding novel features related to interpretation strategy and evaluation metrics.

Findings

Improved prediction accuracy of interpreter performance

Effective adaptation of machine translation quality estimation techniques

Validated across multiple language pairs and settings

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.