From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

TL;DR

This paper introduces an explainable AI framework for automated interpreting assessment in college classrooms, emphasizing transparency, feature relevance, and diagnostic feedback to improve evaluation quality and learner support.

Contribution

It presents a multi-dimensional, explainable modeling approach that addresses data challenges and enhances interpretability in interpreting quality assessment.

Findings

Strong predictive performance on English-Chinese interpreting data

BLEURT and CometKiwi are key features for fidelity assessment

Pause features and phraseological diversity metrics are important for fluency and language use

Abstract

Recent advancements in machine learning have spurred growing interests in automated interpreting quality assessment. Nevertheless, existing research suffers from insufficient examination of language use quality, unsatisfactory modeling effectiveness due to data scarcity and imbalance, and a lack of efforts to explain model predictions. To address these gaps, we propose a multi-dimensional modeling framework that integrates feature engineering, data augmentation, and explainable machine learning. This approach prioritizes explainability over ``black box'' predictions by utilizing only construct-relevant, transparent features and conducting Shapley Value (SHAP) analysis. Our results demonstrate strong predictive performance on a novel English-Chinese consecutive interpreting dataset, identifying BLEURT and CometKiwi scores to be the strongest predictive features for fidelity, pause-related features for fluency, and Chinese-specific phraseological diversity metrics for language use. Overall, by placing particular emphasis on explainability, we present a scalable, reliable, and transparent alternative to traditional human evaluation, facilitating the provision of detailed diagnostic feedback for learners and supporting self-regulated learning advantages not afforded by automated scores in isolation.