X-PuDu at SemEval-2022 Task 7: A Replaced Token Detection Task Pre-trained Model with Pattern-aware Ensembling for Identifying Plausible Clarifications

TL;DR

This paper presents a winning system for SemEval-2022 Task 7 that uses a replaced token detection pre-trained model with pattern-aware ensembling to accurately identify plausible clarifications in instructional texts.

Contribution

The paper introduces a novel ensemble approach combined with a replaced token detection model for improved performance on clarification identification tasks.

Findings

Achieved 68.90% accuracy and 0.8070 Spearman correlation, surpassing the second place by significant margins.

Demonstrated the effectiveness of pattern-aware ensembling and ablation studies to validate strategies.

Provided qualitative and quantitative analyses of the system's components and performance.

Abstract

This paper describes our winning system on SemEval 2022 Task 7: Identifying Plausible Clarifications of Implicit and Underspecified Phrases in Instructional Texts. A replaced token detection pre-trained model is utilized with minorly different task-specific heads for SubTask-A: Multi-class Classification and SubTask-B: Ranking. Incorporating a pattern-aware ensemble method, our system achieves a 68.90% accuracy score and 0.8070 spearman's rank correlation score surpassing the 2nd place with a large margin by 2.7 and 2.2 percent points for SubTask-A and SubTask-B, respectively. Our approach is simple and easy to implement, and we conducted ablation studies and qualitative and quantitative analyses for the working strategies used in our system.