Advancing Automated Speaking Assessment Leveraging Multifaceted Relevance and Grammar Information

TL;DR

This paper introduces a hybrid automated speaking assessment model that enhances content relevance evaluation by integrating multimodal cues and detailed grammar error analysis, leading to improved assessment accuracy.

Contribution

It proposes a novel relevance module combining question, image, exemplar, and response data, along with fine-grained grammar error features derived from advanced correction techniques.

Findings

Significant improvement in content relevance evaluation.

Enhanced detection of detailed grammar errors.

Overall better performance in speaking assessment tasks.

Abstract

Current automated speaking assessment (ASA) systems for use in multi-aspect evaluations often fail to make full use of content relevance, overlooking image or exemplar cues, and employ superficial grammar analysis that lacks detailed error types. This paper ameliorates these deficiencies by introducing two novel enhancements to construct a hybrid scoring model. First, a multifaceted relevance module integrates question and the associated image content, exemplar, and spoken response of an L2 speaker for a comprehensive assessment of content relevance. Second, fine-grained grammar error features are derived using advanced grammar error correction (GEC) and detailed annotation to identify specific error categories. Experiments and ablation studies demonstrate that these components significantly improve the evaluation of content relevance, language use, and overall ASA performance, highlighting the benefits of using richer, more nuanced feature sets for holistic speaking assessment.