Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks
This addresses the problem of black-box models for researchers and practitioners in NLP, offering interpretable alternatives, though it appears incremental as it builds on existing prototypical network methods.
The dissertation tackles the lack of interpretability in transformer-based language models for NLP tasks by developing intrinsically interpretable models using prototypical networks, achieving enhanced accuracy in sarcasm detection and maintaining performance in text classification without sacrificing the original models' effectiveness.
Pretrained transformer-based Language Models (LMs) are well-known for their ability to achieve significant improvement on NLP tasks, but their black-box nature, which leads to a lack of interpretability, has been a major concern. My dissertation focuses on developing intrinsically interpretable models when using LMs as encoders while maintaining their superior performance via prototypical networks. I initiated my research by investigating enhancements in performance for interpretable models of sarcasm detection. My proposed approach focuses on capturing sentiment incongruity to enhance accuracy while offering instance-based explanations for the classification decisions. Later, I developed a novel white-box multi-head graph attention-based prototype network designed to explain the decisions of text classification models without sacrificing the accuracy of the original black-box LMs. In addition, I am working on extending the attention-based prototype network with contrastive learning to redesign an interpretable graph neural network, aiming to enhance both the interpretability and performance of the model in document classification.