Natural Language Processing
 
Edit

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 implementations

Datasets

Subtasks

Latest papers with no code

Most implemented Social Latest No code

Empowering Interdisciplinary Research with BERT-Based Models: An Approach Through SciBERT-CNN with Topic Modeling

no code yet • 16 Apr 2024

Researchers must stay current in their fields by regularly reviewing academic literature, a task complicated by the daily publication of thousands of papers.

 
Paper
Add Code

Quantization of Large Language Models with an Overdetermined Basis

no code yet • 15 Apr 2024

In this paper, we introduce an algorithm for data quantization based on the principles of Kashin representation.

 
Paper
Add Code

OTTER: Improving Zero-Shot Classification via Optimal Transport

no code yet • 12 Apr 2024

Popular zero-shot models suffer due to artifacts inherited from pretraining.

 
Paper
Add Code

VertAttack: Taking advantage of Text Classifiers' horizontal vision

no code yet • 12 Apr 2024

In contrast, humans are easily able to recognize and read words written both horizontally and vertically.

 
Paper
Add Code

Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification

no code yet • 12 Apr 2024

In this paper, we conduct an in-depth study of supervised contrastive learning and its influence on representation in MLTC context.

 
Paper
Add Code

Interactive Prompt Debugging with Sequence Salience

no code yet • 11 Apr 2024

We present Sequence Salience, a visual tool for interactive prompt debugging with input salience methods.

 
Paper
Add Code

Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods

no code yet • 8 Apr 2024

In various real-world applications such as machine translation, sentiment analysis, and question answering, a pivotal role is played by NLP models, facilitating efficient communication and decision-making processes in domains ranging from healthcare to finance.

 
Paper
Add Code

Text clustering applied to data augmentation in legal contexts

no code yet • 8 Apr 2024

Data analysis and machine learning are of preeminent importance in the legal domain, especially in tasks like clustering and text classification.

 
Paper
Add Code

Adversarial Attacks and Dimensionality in Text Classifiers

no code yet • 3 Apr 2024

For all of the aforementioned studies, we have run tests on multiple models with varying dimensionality and used a word-vector level adversarial attack to substantiate the findings.

 
Paper
Add Code

Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data

no code yet • 3 Apr 2024

Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks.

 
Paper
Add Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy