paper-with-me

Papers

Explaining high-dimensional text classifiers

2023-11-22 · Odelia Melamed, Rich Caruana

Explainability has become a valuable tool in the last few years, helping humans better understand AI-guided decisions. However, the classic explainability tools are sometimes quite limited when considering high-dimensional inputs and neural network classifiers. We present a new explainability method using theoretically proven high-dimensional properties in neural network classifiers. We present two usages of it: 1) On the classical sentiment analysis task for the IMDB reviews dataset, and 2) our Malware-Detection task for our PowerShell scripts dataset.

📄 PDF Abstract BibTeX arXiv:2311.13454

Code (0)

등록된 구현이 없습니다.

Tasks

Malware DetectionSentiment Analysis

Similar Papers 제목 키워드 기반

Contextual Prediction Difference Analysis for Explaining Individual Image Classifications

2019-10-21 · Jindong Gu, Volker Tresp

Much effort has been devoted to understanding the decisions of deep neural networks in recent years. A number of model-aware saliency methods were proposed to explain individual classification decisions by creating salie…

Prediction

A Symbolic Approach to Explaining Bayesian Network Classifiers

2018-05-09 · Andy Shih, Arthur Choi, Adnan Darwiche

We propose an approach for explaining Bayesian network classifiers, which is based on compiling such classifiers into decision functions that have a tractable and symbolic form. We introduce two types of explanations for…

General Classification

SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers

2021-03-23 · EMNLP 2021 11 · Dheeraj Rajagopal, Vidhisha Balachandran, Eduard Hovy, Yulia Tsvetkov

We introduce SelfExplain, a novel self-explaining model that explains a text classifier's predictions using phrase-based concepts. SelfExplain augments existing neural classifiers by adding (1) a globally interpretable l…

text-classificationText Classification

Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection

2022-05-06 · NAACL 2022 7 · Esma Balkir, Isar Nejadgholi, Kathleen C. Fraser, Svetlana Kiritchenko

We present a novel feature attribution method for explaining text classifiers, and analyze it in the context of hate speech detection. Although feature attribution models usually provide a single importance score for eac…

Hate Speech Detection

Explaining Predictions of Non-Linear Classifiers in NLP

2016-06-23 · WS 2016 8 · Leila Arras, Franziska Horn, Grégoire Montavon, Klaus-Robert Müller 외

Layer-wise relevance propagation (LRP) is a recently proposed technique for explaining predictions of complex non-linear classifiers in terms of input variables. In this paper, we apply LRP for the first time to natural …

General Classificationimage-classificationImage Classification