.png){kind=icon}
返回
A Multi-Level Supervised Contrastive Learning Framework for Low-Resource Natural Language Inference
.png){kind=icon}
OA
AI
DOI：10.1109/TASLP.2023.3270771.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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 1.8%, 3.1% and 4.1% on SNLI, MNLI and Sick with 5 instances per label respectively. Moreover, our method outperforms the previous state-of-the-art method on cross-domain tasks of text classification.
Keyword:
Task analysis
Semantics
Training
Annotations
Bicycles
Neural networks
Costs
Natural language inference
contrastive learning
low-resource
multi-level
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Heterochromatin Is Not the Only Place for satDNAs: The High Diversity of satDNAs in the Euchromatin of the Beetle Chrysolina americana (Coleoptera, Chrysomelidae).png)
GenesOAAI
GenesIF0
OAAI分享收藏Eyewitness identification discriminability: ROC analysis versus logistic regression.目击证人识别辨别力：ROC分析与逻辑回归。
PREAI
分享收藏The Potential of Smart Factories and Innovative Industry 4.0 Technologies—A Case Study of Different-Sized Companies in the Furniture Industry in Central EuropeForestsOAAI
ForestsIF0
OAAI分享收藏
查看更多内容