Influence Functions for Sequence Tagging Models
This work addresses interpretability for sequence tagging tasks, which is incremental as it adapts an existing method to a new domain.
The paper tackles the lack of interpretability methods for sequence tagging models by extending influence functions to trace predictions back to training data, and demonstrates its utility by identifying systematic annotation errors in two named entity recognition corpora.
Many language tasks (e.g., Named Entity Recognition, Part-of-Speech tagging, and Semantic Role Labeling) are naturally framed as sequence tagging problems. However, there has been comparatively little work on interpretability methods for sequence tagging models. In this paper, we extend influence functions - which aim to trace predictions back to the training points that informed them - to sequence tagging tasks. We define the influence of a training instance segment as the effect that perturbing the labels within this segment has on a test segment level prediction. We provide an efficient approximation to compute this, and show that it tracks with the true segment influence, measured empirically. We show the practical utility of segment influence by using the method to identify systematic annotation errors in two named entity recognition corpora. Code to reproduce our results is available at https://github.com/successar/Segment_Influence_Functions.