Interpretable Natural Language Understanding

Yulan He

Abstract: In recent years, we have witnessed the shift of paradigms in Natural Language Processing (NLP) from fine-tuning large-scale pre-trained language models (PLMs) on task-specific data to prompt-based learning. In the latter, the task description is embedded into the PLM input, enabling the same model to handle multiple tasks. While both approaches have demonstrated impressive performance in various NLP tasks, their opaque nature makes comprehending their inner workings and decision-making processes challenging for humans.In this talk, I will share the research undertaken in my group to address the interpretability concerns surrounding neural models in language understanding. This includes a hierarchical interpretable text classifier going beyond word-level interpretations, uncertainty interpretation of text classifiers built on PLMs, explainable recommender systems by harnessing information across diverse modalities, and explainable student answer scoring. I will conclude my talk by offering insights into potential future developments in interpretable language understanding.