Text Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 16
- 평가표
- 101
- 보존된 평가 기록
- 341
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.
<span style="color:grey; opacity: 0.6">( Image credit: Text Classification Algorithms: A Survey )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
topicwizard -- a Modern, Model-agnostic Framework for Topic Model Visualization and Interpretation
The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
Token Masking Improves Transformer-Based Text Classification
Interpretable Multi-Task PINN for Emotion Recognition and EDA Prediction
HAMLET: Healthcare-focused Adaptive Multilingual Learning Embedding-based Topic Modeling
KDH-MLTC: Knowledge Distillation for Healthcare Multi-Label Text Classification
EmoMeta: A Multimodal Dataset for Fine-grained Emotion Classification in Chinese Metaphors
MELLM: Exploring LLM-Powered Micro-Expression Understanding Enhanced by Subtle Motion Perception
The Efficiency of Pre-training with Objective Masking in Pseudo Labeling for Semi-Supervised Text Classification
FNBench: Benchmarking Robust Federated Learning against Noisy Labels
Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification
Towards Robust Few-Shot Text Classification Using Transformer Architectures and Dual Loss Strategies
KG-HTC: Integrating Knowledge Graphs into LLMs for Effective Zero-shot Hierarchical Text Classification
Survey of Abstract Meaning Representation: Then, Now, Future
Rethinking Multimodal Sentiment Analysis: A High-Accuracy, Simplified Fusion Architecture
Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets
A Simple Ensemble Strategy for LLM Inference: Towards More Stable Text Classification
Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification
LLM-based Semantic Augmentation for Harmful Content Detection
Automated Bug Report Prioritization in Large Open-Source Projects
CAPO: Cost-Aware Prompt Optimization
Fully Bayesian Approaches to Topics over Time
Feeding LLM Annotations to BERT Classifiers at Your Own Risk
Enhancing Multimodal In-Context Learning for Image Classification through Coreset Optimization
Word Embedding Techniques for Classification of Star Ratings
Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models
How Large Language Models Are Changing MOOC Essay Answers: A Comparison of Pre- and Post-LLM Responses
Selective Attention Federated Learning: Improving Privacy and Efficiency for Clinical Text Classification
SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians
Integrated ensemble of BERT- and features-based models for authorship attribution in Japanese literary works
Integrating Emotion Distribution Networks and Textual Message Analysis for X User Emotional State Classification
Traversal Learning Coordination For Lossless And Efficient Distributed Learning
SaRoHead: A Dataset for Satire Detection in Romanian Multi-Domain News Headlines
MuSaRoNews: A Multidomain, Multimodal Satire Dataset from Romanian News Articles
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.