Understanding How BERT Learns to Identify Edits

11/28/2020
by   Samuel Stevens, et al.
0

Pre-trained transformer language models such as BERT are ubiquitous in NLP research, leading to work on understanding how and why these models work. Attention mechanisms have been proposed as a means of interpretability with varying conclusions. We propose applying BERT-based models to a sequence classification task and using the data set's labeling schema to measure each model's interpretability. We find that classification performance scores do not always correlate with interpretability. Despite this, BERT's attention weights are interpretable for over 70

READ FULL TEXT

Authors

page 4

04/17/2019

DocBERT: BERT for Document Classification

Pre-trained language representation models achieve remarkable state of t...
04/14/2021

An Interpretability Illusion for BERT

We describe an "interpretability illusion" that arises when analyzing th...
09/14/2021

Explainable Identification of Dementia from Transcripts using Transformer Networks

Alzheimer's disease (AD) is the main cause of dementia which is accompan...
12/30/2020

Improving BERT with Syntax-aware Local Attention

Pre-trained Transformer-based neural language models, such as BERT, have...
12/24/2020

QUACKIE: A NLP Classification Task With Ground Truth Explanations

NLP Interpretability aims to increase trust in model predictions. This m...
09/15/2020

Lessons Learned from Applying off-the-shelf BERT: There is no Silver Bullet

One of the challenges in the NLP field is training large classification ...
02/27/2020

A Primer in BERTology: What we know about how BERT works

Transformer-based models are now widely used in NLP, but we still do not...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.