Fine-grained Interpretation and Causation Analysis in Deep NLP Models
arXiv:2105.08039
Abstract
This paper is a write-up for the tutorial on "Fine-grained Interpretation and Causation Analysis in Deep NLP Models" that we are presenting at NAACL 2021. We present and discuss the research work on interpreting fine-grained components of a model from two perspectives, i) fine-grained interpretation, ii) causation analysis. The former introduces methods to analyze individual neurons and a group of neurons with respect to a language property or a task. The latter studies the role of neurons and input features in explaining decisions made by the model. We also discuss application of neuron analysis such as network manipulation and domain adaptation. Moreover, we present two toolkits namely NeuroX and Captum, that support functionalities discussed in this tutorial.
arXiv commentAccepted at NAACL Tutorial
References in corpus (10)
- Visualizing and Understanding Recurrent Networks
- Understanding Neural Networks through Representation Erasure
- What do Neural Machine Translation Models Learn about Morphology?
- A Survey of the State of Explainable AI for Natural Language Processing
- Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias
- Explaining Explanations: Axiomatic Feature Interactions for Deep Networks
- How does this interaction affect me? Interpretable attribution for feature interactions
- Finding Experts in Transformer Models
- Ablation of a Robot's Brain: Neural Networks Under a Knife
- Unsupervised Transfer Learning via BERT Neuron Selection