DeepAI AI Chat
Log In Sign Up

Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff

07/12/2021
by   Mitchell Naylor, et al.
0

The healthcare domain is one of the most exciting application areas for machine learning, but a lack of model transparency contributes to a lag in adoption within the industry. In this work, we explore the current art of explainability and interpretability within a case study in clinical text classification, using a task of mortality prediction within MIMIC-III clinical notes. We demonstrate various visualization techniques for fully interpretable methods as well as model-agnostic post hoc attributions, and we provide a generalized method for evaluating the quality of explanations using infidelity and local Lipschitz across model types from logistic regression to BERT variants. With these metrics, we introduce a framework through which practitioners and researchers can assess the frontier between a model's predictive performance and the quality of its available explanations. We make our code available to encourage continued refinement of these methods.

READ FULL TEXT
03/24/2020

Towards Explainability of Machine Learning Models in Insurance Pricing

Machine learning methods have garnered increasing interest among actuari...
10/28/2022

Can Current Explainability Help Provide References in Clinical Notes to Support Humans Annotate Medical Codes?

The medical codes prediction problem from clinical notes has received su...
08/12/2022

The Weighting Game: Evaluating Quality of Explainability Methods

The objective of this paper is to assess the quality of explanation heat...
11/22/2022

Explainability of Traditional and Deep Learning Models on Longitudinal Healthcare Records

Recent advances in deep learning have led to interest in training deep l...
04/28/2020

Towards Prediction Explainability through Sparse Communication

Explainability is a topic of growing importance in NLP. In this work, we...
09/25/2020

A Diagnostic Study of Explainability Techniques for Text Classification

Recent developments in machine learning have introduced models that appr...