Towards Automated Error Analysis: Learning to Characterize Errors

TL;DR

This paper introduces a meta learning approach that automatically learns interpretable rules to characterize and understand errors in NLP systems, leading to insights and modest performance improvements.

Contribution

It presents a novel method for automatically learning interpretable error characterization rules using meta features, applicable to different NLP systems.

Findings

Learned interpretable error rules for VilBERT and RoBERTa

Provided insights into systemic errors of NLP models

Achieved modest performance improvements using error insights

Abstract

Characterizing the patterns of errors that a system makes helps researchers focus future development on increasing its accuracy and robustness. We propose a novel form of "meta learning" that automatically learns interpretable rules that characterize the types of errors that a system makes, and demonstrate these rules' ability to help understand and improve two NLP systems. Our approach works by collecting error cases on validation data, extracting meta-features describing these samples, and finally learning rules that characterize errors using these features. We apply our approach to VilBERT, for Visual Question Answering, and RoBERTa, for Common Sense Question Answering. Our system learns interpretable rules that provide insights into systemic errors these systems make on the given tasks. Using these insights, we are also able to "close the loop" and modestly improve performance of these systems.