Text Classification
1107 papers with code • 93 benchmarks • 136 datasets
Text Classification is the task of assigning a sentence or document an appropriate category. The categories depend on the chosen dataset and can range from topics.
Text Classification problems include emotion classification, news classification, citation intent classification, among others. Benchmark datasets for evaluating text classification capabilities include GLUE, AGNews, among others.
In recent years, deep learning techniques like XLNet and RoBERTa have attained some of the biggest performance jumps for text classification problems.
( Image credit: Text Classification Algorithms: A Survey )
Libraries
Use these libraries to find Text Classification models and implementationsSubtasks
- Topic Models
- Document Classification
- Sentence Classification
- Emotion Classification
- Emotion Classification
- Multi-Label Text Classification
- Few-Shot Text Classification
- Text Categorization
- Semi-Supervised Text Classification
- Coherence Evaluation
- Toxic Comment Classification
- Citation Intent Classification
- Cross-Domain Text Classification
- Unsupervised Text Classification
- Satire Detection
- Hierarchical Text Classification of Blurbs (GermEval 2019)
- Variable Detection
Latest papers
DiLM: Distilling Dataset into Language Model for Text-level Dataset Distillation
To address this issue, we propose a novel text dataset distillation approach, called Distilling dataset into Language Model (DiLM), which trains a language model to generate informative synthetic training samples as text data, instead of directly optimizing synthetic samples.
HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification
Existing self-supervised methods in natural language processing (NLP), especially hierarchical text classification (HTC), mainly focus on self-supervised contrastive learning, extremely relying on human-designed augmentation rules to generate contrastive samples, which can potentially corrupt or distort the original information.
LlamBERT: Large-scale low-cost data annotation in NLP
Large Language Models (LLMs), such as GPT-4 and Llama 2, show remarkable proficiency in a wide range of natural language processing (NLP) tasks.
A Model Ensemble Approach with LLM for Chinese Text Classification
Automatic medical text categorization can assist doctors in efficiently managing patient information.
SpikeGraphormer: A High-Performance Graph Transformer with Spiking Graph Attention
In this work, we propose a novel insight into integrating SNNs with Graph Transformers and design a Spiking Graph Attention (SGA) module.
SynerMix: Synergistic Mixup Solution for Enhanced Intra-Class Cohesion and Inter-Class Separability in Image Classification
It also surpasses the top-performer of either Manifold MixUp or SynerMix-Intra by 0. 12% to 5. 16%, with an average gain of 1. 11%.
Investigating Text Shortening Strategy in BERT: Truncation vs Summarization
In this study, we investigate the performance of document truncation and summarization in text classification tasks.
Team Trifecta at Factify5WQA: Setting the Standard in Fact Verification with Fine-Tuning
In this paper, we present Pre-CoFactv3, a comprehensive framework comprised of Question Answering and Text Classification components for fact verification.
Defending Against Unforeseen Failure Modes with Latent Adversarial Training
Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors.
RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical Rules
Weakly supervised text classification (WSTC), also called zero-shot or dataless text classification, has attracted increasing attention due to its applicability in classifying a mass of texts within the dynamic and open Web environment, since it requires only a limited set of seed words (label names) for each category instead of labeled data.