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 with no code
Empowering Interdisciplinary Research with BERT-Based Models: An Approach Through SciBERT-CNN with Topic Modeling
Researchers must stay current in their fields by regularly reviewing academic literature, a task complicated by the daily publication of thousands of papers.
Quantization of Large Language Models with an Overdetermined Basis
In this paper, we introduce an algorithm for data quantization based on the principles of Kashin representation.
OTTER: Improving Zero-Shot Classification via Optimal Transport
Popular zero-shot models suffer due to artifacts inherited from pretraining.
VertAttack: Taking advantage of Text Classifiers' horizontal vision
In contrast, humans are easily able to recognize and read words written both horizontally and vertically.
Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification
In this paper, we conduct an in-depth study of supervised contrastive learning and its influence on representation in MLTC context.
Interactive Prompt Debugging with Sequence Salience
We present Sequence Salience, a visual tool for interactive prompt debugging with input salience methods.
Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods
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.
Text clustering applied to data augmentation in legal contexts
Data analysis and machine learning are of preeminent importance in the legal domain, especially in tasks like clustering and text classification.
Adversarial Attacks and Dimensionality in Text Classifiers
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.
Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data
Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks.