paper-with-me

Papers

Constructing Contrastive samples via Summarization for Text Classification with limited annotations

2021-04-11 · Findings (EMNLP) 2021 11 · Yangkai Du, Tengfei Ma, Lingfei Wu, Fangli Xu, Xuhong Zhang, Bo Long, Shouling Ji

Contrastive Learning has emerged as a powerful representation learning method and facilitates various downstream tasks especially when supervised data is limited. How to construct efficient contrastive samples through data augmentation is key to its success. Unlike vision tasks, the data augmentation method for contrastive learning has not been investigated sufficiently in language tasks. In this paper, we propose a novel approach to construct contrastive samples for language tasks using text summarization. We use these samples for supervised contrastive learning to gain better text representations which greatly benefit text classification tasks with limited annotations. To further improve the method, we mix up samples from different classes and add an extra regularization, named Mixsum, in addition to the cross-entropy-loss. Experiments on real-world text classification datasets (Amazon-5, Yelp-5, AG News, and IMDb) demonstrate the effectiveness of the proposed contrastive learning framework with summarization-based data augmentation and Mixsum regularization.

📄 PDF Abstract BibTeX arXiv:2104.05094

Code (1)

chesterdu/contrastive_summary 공식 구현 pytorch

Tasks

Contrastive LearningData AugmentationGeneral ClassificationRepresentation Learningtext-classificationText ClassificationText Summarization

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization

2021-10-14 · Prafulla Kumar Choubey, Alexander R. Fabbri, Jesse Vig, Chien-Sheng Wu 외

Hallucination is a known issue for neural abstractive summarization models. Recent work suggests that the degree of hallucination may depend on errors in the training data. In this work, we propose a new method called Co…

Abstractive Text SummarizationARCHallucinationInformativeness

Align and Attend: Multimodal Summarization with Dual Contrastive Losses

2023-03-13 · CVPR 2023 1 · Bo He, Jun Wang, JieLin Qiu, Trung Bui 외

The goal of multimodal summarization is to extract the most important information from different modalities to form output summaries. Unlike the unimodal summarization, the multimodal summarization task explicitly levera…

Extractive Text SummarizationSupervised Video SummarizationVideo Summarization

Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning

2024-12-30 · En Fu, Yanyan Hu

Contrastive learning underpins most current self-supervised time series representation methods. The strategy for constructing positive and negative sample pairs significantly affects the final representation quality. How…

Contrastive LearningLinear evaluationRepresentation LearningTime Series

Contrastive Data and Learning for Natural Language Processing

2022-07-01 · NAACL (ACL) 2022 7 · Rui Zhang, Yangfeng Ji, Yue Zhang, Rebecca J. Passonneau

Current NLP models heavily rely on effective representation learning algorithms. Contrastive learning is one such technique to learn an embedding space such that similar data sample pairs have close representations while…

Contrastive LearningQuestion AnsweringRepresentation LearningSentence+3

ConCur: Self-supervised graph representation based on contrastive learning with curriculum negative sampling

2023-09-01 · journal 2023 9 · Rong Yan, Peng Bao

Contrastive learning has made breakthrough advancements in graph representation learning, which encourages the representation of positive samples to be close and those of negative samples to be far away. However, existin…

Contrastive LearningGraph Representation LearningNode ClassificationRepresentation Learning+1