paper-with-me

홈 › Papers

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

2021-12-06 · NAACL 2021 4 · 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 BibTeX arXiv:2112.03271

Code (1)

zixuanke/pycontinual 공식 구현 pytorch

Tasks

Continual LearningSentiment AnalysisSentiment ClassificationTransfer Learning

Methods 이 논문이 사용한 방법론

Capsule Network A capsule is an activation vector that basically executes on its inputs some complex internal computations. Length of these activation vectors signifies the probability of…
AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks

2021-12-05 · EMNLP 2021 11 · Zixuan Ke, Bing Liu, Hu Xu, Lei Shu

This paper studies continual learning (CL) of a sequence of aspect sentiment classification(ASC) tasks in a particular CL setting called domain incremental learning (DIL). Each task is from a different domain or product.…

ClassificationContinual LearningContrastive LearningIncremental Learning+4

GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis

2020-09-22 · Findings of the Association for Computational Linguistics 2020 · Huaishao Luo, Lei Ji, Tianrui Li, Nan Duan 외

In this paper, we focus on the imbalance issue, which is rarely studied in aspect term extraction and aspect sentiment classification when regarding them as sequence labeling tasks. Besides, previous works usually ignore…

Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)object-detectionObject Detection+3

Aspect-Based Sentiment Analysis using Local Context Focus Mechanism with DeBERTa

2022-07-06 · Tianyu Zhao, Junping Du, Zhe Xue, Ang Li 외

Text sentiment analysis, also known as opinion mining, is research on the calculation of people's views, evaluations, attitude and emotions expressed by entities. Text sentiment analysis can be divided into text-level se…

Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Language ModellingMulti-Task Learning+3

PASTE: A Tagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction

2021-10-10 · EMNLP 2021 11 · Rajdeep Mukherjee, Tapas Nayak, Yash Butala, Sourangshu Bhattacharya 외

Aspect Sentiment Triplet Extraction (ASTE) deals with extracting opinion triplets, consisting of an opinion target or aspect, its associated sentiment, and the corresponding opinion term/span explaining the rationale beh…

Aspect Sentiment Triplet ExtractionDecoderSentenceTriplet

Improving BERT Performance for Aspect-Based Sentiment Analysis

2020-10-22 · ICNLSP 2021 11 · Akbar Karimi, Leonardo Rossi, Andrea Prati

Aspect-Based Sentiment Analysis (ABSA) studies the consumer opinion on the market products. It involves examining the type of sentiments as well as sentiment targets expressed in product reviews. Analyzing the language u…

Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Aspect ExtractionSentiment Analysis+1