paper-with-me

홈 › Papers

On Explaining Your Explanations of BERT: An Empirical Study with Sequence Classification

2021-01-01 · Zhengxuan Wu, Desmond C. Ong

BERT, as one of the pretrianed language models, attracts the most attention in recent years for creating new benchmarks across GLUE tasks via fine-tuning. One pressing issue is to open up the blackbox and explain the decision makings of BERT. A number of attribution techniques have been proposed to explain BERT models, but are often limited to sequence to sequence tasks. In this paper, we adapt existing attribution methods on explaining decision makings of BERT in sequence classification tasks. We conduct extensive analyses of four existing attribution methods by applying them to four different datasets in sentiment analysis. We compare the reliability and robustness of each method via various ablation studies. Furthermore, we test whether attribution methods explain generalized semantics across semantically similar tasks. Our work provides solid guidance for using attribution methods to explain decision makings of BERT for downstream classification tasks.

📄 PDF Abstract BibTeX arXiv:2101.00196

Code (2)

frankaging/BERT_LRP 공식 구현 pytorch
frankaging/bert-lrp pytorch

Tasks

General ClassificationSentiment Analysis

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Multi-Head Attention 설명 없음
Attention 설명 없음

Similar Papers 제목 키워드 기반

VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions

2018-03-20 · ECCV 2018 9 · Qing Li, Qingyi Tao, Shafiq Joty, Jianfei Cai 외

Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations. We argue that the explanation for an answer is of the same or even…

Explanatory Visual Question AnsweringMulti-Task LearningQuestion AnsweringVisual Question Answering+1

Explaining Explanations in AI

2018-11-04 · Brent Mittelstadt, Chris Russell, Sandra Wachter

Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions. These models are a useful pedagogical device for teac…

BIG-bench Machine LearningPhilosophySociology

How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods

2020-12-01 · NeurIPS 2020 12 · Jeya Vikranth Jeyakumar, Joseph Noor, Yu-Hsi Cheng, Luis Garcia 외

Explaining the inner workings of deep neural network models have received considerable attention in recent years. Researchers have attempted to provide human parseable explanations justifying why a model performed a spec…

General ClassificationSentiment AnalysisSentiment Classification

Evaluating Post-hoc Explanations of the Transformer-based Genome Language Model DNABERT-2

2026-04-23 · Isabel Kurth, Paulo Yanez Sarmiento, Bernhard Y. Renard arxiv

Explaining deep neural network predictions on genome sequences enables biological insight and hypothesis generation-often of greater interest than predictive performance alone. While explanations of convolutional neural …

“Mama Always Had a Way of Explaining Things So I Could Understand”: A Dialogue Corpus for Learning to Construct Explanations

2022-10-01 · COLING 2022 10 · Henning Wachsmuth, Milad Alshomary

As AI is more and more pervasive in everyday life, humans have an increasing demand to understand its behavior and decisions. Most research on explainable AI builds on the premise that there is one ideal explanation to b…