SOTAVerified

Topic Classification

Papers

Showing 125 of 186 papers

TitleStatusHype
Prototypical Verbalizer for Prompt-based Few-shot TuningCode4
Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective FunctionCode1
DocSCAN: Unsupervised Text Classification via Learning from NeighborsCode1
LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual LexiconsCode1
Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-TuningCode1
Newswire: A Large-Scale Structured Database of a Century of Historical NewsCode1
Hierarchical Transformers for Long Document ClassificationCode1
Hierarchical Multi-Label Classification of Scientific DocumentsCode1
KLUE: Korean Language Understanding EvaluationCode1
Language Through a Prism: A Spectral Approach for Multiscale Language RepresentationsCode1
MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transferCode1
MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transferCode1
GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph KnowledgeCode1
Polyglot Prompt: Multilingual Multitask PrompTrainingCode1
2kenize: Tying Subword Sequences for Chinese Script ConversionCode1
Cross-Lingual Adaptation using Structural Correspondence LearningCode1
Entailment as Few-Shot LearnerCode1
Explaining NLP Models via Minimal Contrastive Editing (MiCE)Code1
HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient KoreaCode1
In-Context Learning with Iterative Demonstration SelectionCode1
L3Cube-IndicNews: News-based Short Text and Long Document Classification Datasets in Indic LanguagesCode1
Label Semantic Aware Pre-training for Few-shot Text ClassificationCode1
MasakhaNEWS: News Topic Classification for African languagesCode1
Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question AnsweringCode1
SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and DialectsCode1
Show:102550
← PrevPage 1 of 8Next →

No leaderboard results yet.