Accountable Error Characterization
This work addresses the need for accountability in machine learning systems for customers and developers, though it appears incremental as it builds on existing error analysis methods.
The authors tackled the problem of understanding when and where errors occur in black-box machine learning models by proposing an accountable error characterization method (AEC) that uses human-understandable linguistic features. In a sentiment analysis case study, AEC successfully characterized erroneous predictions into understandable categories and showed promising results in selecting erroneous samples compared to uncertainty-based sampling.
Customers of machine learning systems demand accountability from the companies employing these algorithms for various prediction tasks. Accountability requires understanding of system limit and condition of erroneous predictions, as customers are often interested in understanding the incorrect predictions, and model developers are absorbed in finding methods that can be used to get incremental improvements to an existing system. Therefore, we propose an accountable error characterization method, AEC, to understand when and where errors occur within the existing black-box models. AEC, as constructed with human-understandable linguistic features, allows the model developers to automatically identify the main sources of errors for a given classification system. It can also be used to sample for the set of most informative input points for a next round of training. We perform error detection for a sentiment analysis task using AEC as a case study. Our results on the sample sentiment task show that AEC is able to characterize erroneous predictions into human understandable categories and also achieves promising results on selecting erroneous samples when compared with the uncertainty-based sampling.