Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization

2020-10-30 · Tian Li, Xiang Chen, Shanghang Zhang, Zhen Dong, Kurt Keutzer

Contrastive learning (CL) has been successful as a powerful representation learning method. In this work we propose CLIM: Contrastive Learning with mutual Information Maximization, to explore the potential of CL on cross-domain sentiment classification. To the best of our knowledge, CLIM is the first to adopt contrastive learning for natural language processing (NLP) tasks across domains. Due to scarcity of labels on the target domain, we introduce mutual information maximization (MIM) apart from CL to exploit the features that best support the final prediction. Furthermore, MIM is able to maintain a relatively balanced distribution of the model's prediction, and enlarges the margin between classes on the target domain. The larger margin increases our model's robustness and enables the same classifier to be optimal across domains. Consequently, we achieve new state-of-the-art results on the Amazon-review dataset as well as the airlines dataset, showing the efficacy of our proposed method CLIM.

📄 PDF Abstract BibTeX arXiv:2010.16088

Code (1)

CasparSwift/CLIM 공식 구현 pytorch

Tasks

Contrastive Learning General Classification Representation Learning Sentiment AnalysisSentiment Classification

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

MIM 설명 없음

Improving Domain-Adapted Sentiment Classification by Deep Adversarial Mutual Learning

2020-02-01 · Qianming Xue, Wei zhang, Hongyuan Zha

Domain-adapted sentiment classification refers to training on a labeled source domain to well infer document-level sentiment on an unlabeled target domain. Most existing relevant models involve a feature extractor and a …

Classification General Classification Sentiment Analysis Sentiment Classification

Cross-Domain Sentiment Classification with In-Domain Contrastive Learning

2020-12-05 · Tian Li, Xiang Chen, Shanghang Zhang, Zhen Dong 외

Contrastive learning (CL) has been successful as a powerful representation learning method. In this paper, we propose a contrastive learning framework for cross-domain sentiment classification. We aim to induce domain in…

Classification Contrastive Learning General Classification Representation Learning+2

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.…

Classification Continual Learning Contrastive Learning Incremental Learning+4

Mere Contrastive Learning for Cross-Domain Sentiment Analysis

2022-08-18 · COLING 2022 10 · Yun Luo, Fang Guo, Zihan Liu, Yue Zhang

Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain using the model trained on the source domain to cope with the scarcity of labeled data. Previous studies are mostly cross-entrop…

Contrastive Learning Sentence Sentiment Analysis

USA: Universal Sentiment Analysis Model & Construction of Japanese Sentiment Text Classification and Part of Speech Dataset

2023-09-07 · Chengguang Gan, Qinghao Zhang, Tatsunori Mori

Sentiment analysis is a pivotal task in the domain of natural language processing. It encompasses both text-level sentiment polarity classification and word-level Part of Speech(POS) sentiment polarity determination. Suc…

Classification POS Sentiment Analysis Sentiment Classification+2