paper-with-me

홈 › Papers

A Multi-level Supervised Contrastive Learning Framework for Low-Resource Natural Language Inference

2022-05-31 · Shu'ang Li, Xuming Hu, Li Lin, Aiwei Liu, Lijie Wen, Philip S. Yu

Natural Language Inference (NLI) is a growingly essential task in natural language understanding, which requires inferring the relationship between the sentence pairs (premise and hypothesis). Recently, low-resource natural language inference has gained increasing attention, due to significant savings in manual annotation costs and a better fit with real-world scenarios. Existing works fail to characterize discriminative representations between different classes with limited training data, which may cause faults in label prediction. Here we propose a multi-level supervised contrastive learning framework named MultiSCL for low-resource natural language inference. MultiSCL leverages a sentence-level and pair-level contrastive learning objective to discriminate between different classes of sentence pairs by bringing those in one class together and pushing away those in different classes. MultiSCL adopts a data augmentation module that generates different views for input samples to better learn the latent representation. The pair-level representation is obtained from a cross attention module. We conduct extensive experiments on two public NLI datasets in low-resource settings, and the accuracy of MultiSCL exceeds other models by 3.1% on average. Moreover, our method outperforms the previous state-of-the-art method on cross-domain tasks of text classification.

📄 PDF Abstract BibTeX arXiv:2205.15550

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningData AugmentationNatural Language InferenceNatural Language UnderstandingSentencetext-classificationText Classification

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Incremental False Negative Detection for Contrastive Learning

2021-06-07 · ICLR 2022 4 · Tsai-Shien Chen, Wei-Chih Hung, Hung-Yu Tseng, Shao-Yi Chien 외

Self-supervised learning has recently shown great potential in vision tasks through contrastive learning, which aims to discriminate each image, or instance, in the dataset. However, such instance-level learning ignores …

Contrastive LearningSelf-Supervised Learning

CSS-LM: A Contrastive Framework for Semi-supervised Fine-tuning of Pre-trained Language Models

2021-02-07 · Yusheng Su, Xu Han, Yankai Lin, Zhengyan Zhang 외

Fine-tuning pre-trained language models (PLMs) has demonstrated its effectiveness on various downstream NLP tasks recently. However, in many low-resource scenarios, the conventional fine-tuning strategies cannot sufficie…

Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation

2021-03-19 · Christiaan Jacobs, Yevgen Matusevych, Herman Kamper

Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length speech segments. For zero-resource languages where labelled data is not available, one AWE approach is to use unsupervised autoenco…

Contrastive LearningWord Embeddings

Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation

2021-06-03 · Saurabhchand Bhati, Jesús Villalba, Piotr Żelasko, Laureano Moro-Velazquez 외

Automatic detection of phoneme or word-like units is one of the core objectives in zero-resource speech processing. Recent attempts employ self-supervised training methods, such as contrastive predictive coding (CPC), wh…

Prototypical Contrastive Learning of Unsupervised Representations

2020-05-11 · ICLR 2021 1 · Junnan Li, Pan Zhou, Caiming Xiong, Steven C. H. Hoi

This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning. PCL not only learns low-level …

ClusteringContrastive LearningRepresentation LearningSelf-Supervised Image Classification+2