TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Continual Learning	20Newsgroup (10 tasks)	B-CL	F1 - macro	0.9504	# 4
Continual Learning	ASC (19 tasks)	B-CL	F1 - macro	0.8140	# 3
Continual Learning	DSC (10 tasks)	B-CL	F1 - macro	0.7651	# 5

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/adapting-bert-for-continual-learning-of-a-1/continual-learning-on-asc-19-tasks)](https://paperswithcode.com/sota/continual-learning-on-asc-19-tasks?p=adapting-bert-for-continual-learning-of-a-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/adapting-bert-for-continual-learning-of-a-1/continual-learning-on-20newsgroup-10-tasks)](https://paperswithcode.com/sota/continual-learning-on-20newsgroup-10-tasks?p=adapting-bert-for-continual-learning-of-a-1)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/adapting-bert-for-continual-learning-of-a-1/continual-learning-on-dsc-10-tasks)](https://paperswithcode.com/sota/continual-learning-on-dsc-10-tasks?p=adapting-bert-for-continual-learning-of-a-1)`

Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks

NAACL 2021 · Zixuan Ke, Hu Xu, Bing Liu ·

This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment classification, we are not aware of any CL work on ASC. A CL system that incrementally learns a sequence of ASC tasks should address the following two issues: (1) transfer knowledge learned from previous tasks to the new task to help it learn a better model, and (2) maintain the performance of the models for previous tasks so that they are not forgotten. This paper proposes a novel capsule network based model called B-CL to address these issues. B-CL markedly improves the ASC performance on both the new task and the old tasks via forward and backward knowledge transfer. The effectiveness of B-CL is demonstrated through extensive experiments.

PDF Abstract NAACL 2021 PDF NAACL 2021 Abstract

Code

Add Remove Mark official

zixuanke/pycontinual official

274

Tasks

Add Remove

Continual Learning

Sentiment Analysis

Sentiment Classification

Transfer Learning

Datasets

Introduced in the Paper:

ASC (TIL, 19 tasks)

Used in the Paper:

20Newsgroup (10 tasks) DSC (10 tasks)

Results from the Paper

Edit

Ranked #3 on Continual Learning on ASC (19 tasks)

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Continual Learning	20Newsgroup (10 tasks)	B-CL	F1 - macro	0.9504	# 4	Compare
Continual Learning	ASC (19 tasks)	B-CL	F1 - macro	0.8140	# 3	Compare
Continual Learning	DSC (10 tasks)	B-CL	F1 - macro	0.7651	# 5	Compare

Methods

Add Remove

AWARE • Capsule Network

Edit Social Preview

Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove