Semi-Supervised Text Classification
19 papers with code • 2 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Semi-Supervised Text Classification
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
AG News
HeriGraph
Most implemented papers
Adversarial Training Methods for Semi-Supervised Text Classification
We extend adversarial and virtual adversarial training to the text domain by applying perturbations to the word embeddings in a recurrent neural network rather than to the original input itself.
Deconvolutional Paragraph Representation Learning
dreasysnail/deconv_paragraph_represention
•
•
NeurIPS 2017
Learning latent representations from long text sequences is an important first step in many natural language processing applications.
Did You Really Just Have a Heart Attack? Towards Robust Detection of Personal Health Mentions in Social Media
The first, critical, task for these applications is classifying whether a personal health event was mentioned, which we call the (PHM) problem.
Adversarial Dropout for Recurrent Neural Networks
sungraepark/adversarial_dropout_text_classification
•
•
Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs).
Semi-Supervised Learning with Normalizing Flows
izmailovpavel/flowgmm
•
•
ICML 2020
Normalizing flows transform a latent distribution through an invertible neural network for a flexible and pleasingly simple approach to generative modelling, while preserving an exact likelihood.
MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification
This paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix.
Rethinking Semi-supervised Learning with Language Models
amzn/pretraining-or-self-training
•
•
Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks.
Delta-training: Simple Semi-Supervised Text Classification using Pretrained Word Embeddings
We propose a novel and simple method for semi-supervised text classification.
Variational Pretraining for Semi-supervised Text Classification
We accompany this paper with code to pretrain and use VAMPIRE embeddings in downstream tasks.
Semi-Supervised Models via Data Augmentationfor Classifying Interactive Affective Responses
GT-SALT/AAAI_CLF
•
•
We present semi-supervised models with data augmentation (SMDA), a semi-supervised text classification system to classify interactive affective responses.
