SHAP values for Explaining CNN-based Text Classification Models

08/26/2020
by   Wei Zhao, et al.
0

Deep neural networks are increasingly used in natural language processing (NLP) models. However, the need to interpret and explain the results from complex algorithms are limiting their widespread adoption in regulated industries such as banking. There has been recent work on interpretability of machine learning algorithms with structured data. But there are only limited techniques for NLP applications where the problem is more challenging due to the size of the vocabulary, high-dimensional nature, and the need to consider textual coherence and language structure. This paper develops a methodology to compute SHAP values for local explainability of CNN-based text classification models. The approach is also extended to compute global scores to assess the importance of features. The results are illustrated on sentiment analysis of Amazon Electronic Review data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/05/2023

A Semantic Approach to Negation Detection and Word Disambiguation with Natural Language Processing

This study aims to demonstrate the methods for detecting negations in a ...
research
11/10/2022

Towards Human-Centred Explainability Benchmarks For Text Classification

Progress on many Natural Language Processing (NLP) tasks, such as text c...
research
11/09/2020

Bangla Text Classification using Transformers

Text classification has been one of the earliest problems in NLP. Over t...
research
09/10/2020

Rank over Class: The Untapped Potential of Ranking in Natural Language Processing

Text classification has long been a staple in natural language processin...
research
08/17/2020

A Survey of Active Learning for Text Classification using Deep Neural Networks

Natural language processing (NLP) and neural networks (NNs) have both un...
research
04/08/2021

Exploring the Relationship Between Algorithm Performance, Vocabulary, and Run-Time in Text Classification

Text classification is a significant branch of natural language processi...
research
06/11/2021

FedNLP: An interpretable NLP System to Decode Federal Reserve Communications

The Federal Reserve System (the Fed) plays a significant role in affecti...

Please sign up or login with your details

Forgot password? Click here to reset