Local Interpretations for Explainable Natural Language Processing: A Survey
arXiv:2103.11072 · doi:10.1145/3649450
Abstract
As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models. This work investigates various methods to improve the interpretability of deep neural networks for Natural Language Processing (NLP) tasks, including machine translation and sentiment analysis. We provide a comprehensive discussion on the definition of the term interpretability and its various aspects at the beginning of this work. The methods collected and summarised in this survey are only associated with local interpretation and are specifically divided into three categories: 1) interpreting the model's predictions through related input features; 2) interpreting through natural language explanation; 3) probing the hidden states of models and word representations.
arXiv commentAccepted by ACM Computing Surveys
References in corpus (17)
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Interpretable machine learning: definitions, methods, and applications
- Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
- What do Neural Machine Translation Models Learn about Morphology?
- e-SNLI: Natural Language Inference with Natural Language Explanations
- "What is Relevant in a Text Document?": An Interpretable Machine Learning Approach
- Stability
- Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models
- Towards a Grounded Dialog Model for Explainable Artificial Intelligence
- VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions
- Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment
- Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
- SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering
- Are Training Resources Insufficient? Predict First Then Explain!
- Learning Credible Deep Neural Networks with Rationale Regularization
- Generating Rationales in Visual Question Answering
- Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision