Timezone: »

 
Oral
Towards a Deep and Unified Understanding of Deep Neural Models in NLP
Chaoyu Guan · Xiting Wang · Quanshi Zhang · Runjin Chen · Di He · Xing Xie

Thu Jun 13 09:20 AM -- 09:25 AM (PDT) @ Grand Ballroom
in Interpretability »

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

[ Slides] 

Author Information

Chaoyu Guan (Shanghai Jiao Tong University)
Xiting Wang (Microsoft Research Asia)
Quanshi Zhang (Shanghai Jiao Tong University)
Runjin Chen (Shanghai Jiao Tong University)
Di He (Peking University)
Xing Xie (Microsoft Research Asia)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors