Skip to yearly menu bar Skip to main content


Towards a Deep and Unified Understanding of Deep Neural Models in NLP

Chaoyu Guan · Xiting Wang · Quanshi Zhang · Runjin Chen · Di He · Xing Xie

Pacific Ballroom #62

Keywords: [ Natural Language Processing ] [ Interpretability ] [ Algorithms ]


We define a unified information-based measure to provide quantitative explanations on how intermediate layers of deep Natural Language Processing (NLP) models leverage information of input words. Our method advances existing explanation methods by addressing issues in coherency and generality. Explanations generated by using our method are consistent and faithful across different timestamps, layers, and models. We show how our method can be applied to four widely used models in NLP and explain their performances on three real-world benchmark datasets.

Live content is unavailable. Log in and register to view live content