HyperAI

Text Classification

Text Classification is a core task in natural language processing, aimed at categorizing text data into predefined categories. This task achieves efficient information organization and retrieval by analyzing the content of the text and identifying its features such as topic, sentiment, or intent. In recent years, deep learning models like XLNet and RoBERTa have significantly improved the performance of text classification, driving technological advancements. Benchmark datasets such as GLUE and AGNews are widely used to evaluate the effectiveness of these models.

20 Newsgroups
RoBERTaGCN
20NEWS
RoBERTaGCN
Adverse Drug Events (ADE) Corpus
ade_corpus_v2Ade_corpus_v2_classification
AffCon 2020 Emotion Detection
AG News
Amazon-2
Amazon-5
amazon_reviews_multi
An Amharic News Text classification Dataset
Naive Bayes using Tf-idf features
Arxiv HEP-TH citation graph
BigBird
arXiv-10
Protoformer
BANKING77
BLURB
BioLinkBERT (large)
book-text-classifier
catalonia_independence
clinc_oos
DBpedia
XLNet
DODF Data
ULMFiT (pre-trained vocab, no gradual unfreezing)
emotion
Facebook Media
financial_phrasebank
FMC-MWO2KG
Flair
GLUE
GLUE COLA
GLUE MRPC
GLUE QQP
GLUE RTE
GLUE SST2
GLUE STSB
hate_speech18
HateXplain
Hyperpartisan News Detection
BigBird
Hyperpartisan
IMDb
IMDb Movie Reviews
Logistic Regression
KLUE
Lot-insts
Character-BERT+RS
MNIST
MR
MTEB
ST5-XXL
MuLD (Character Type)
MVICTOR (type)
New_York_Times_Topics
NewsDiscourse
NICE-2
NICE-45
NSFW-Safe-Dataset
Ohsumed
SGCN
OneStopEnglish (Readability Assessment)
RoBERTa-RF-T1 hybrid
Overruling
Custom Legal-BERT
Patents
BigBird
R52
1-6 BertGCN
R8
RoBERTaGCN
RCV1
HiLAP (bow-CNN)
RusAge: Corpus for Age-Based Text Classification
LSVC + linguistic features + publishing attributes
Searchsnippets
SemEval 2014 Task 4 (Restaurants)
SILICONE Benchmark
Social media attributions of YouTube comments
Sogou News
BERT-ITPT-FiT
SST-2
SST2
STOPS-2
ERNIE 2.0
STOPS-41
SVICTOR (type)
tecla
Terms of Service
This is not a Dataset
ThreatGram 101 - Extreme Telegram Data
GPT-2
TRAC2-Benghali. Task 2.
BERT
TRAC2-English. Task2.
TREC-10
BERT
TREC-50
TREC-6
Automatic Label Error Correction
Twitter
Twitter Sentiment Analysis
Logistic Regression
Twitter-US
UK Key Stage Readability
Unknown
WeeBit (Readability Assessment)
BERT-FP-LBL
WNUT-2020 Task 2
NutCracker
Yahoo! Answers
BERT-ITPT-FiT
Yelp-2
Yelp-5
HAHNN (CNN)