SOTAVerified

Text Classification

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 )

Papers

Showing 201250 of 3635 papers

TitleStatusHype
Establishing Baselines for Text Classification in Low-Resource LanguagesCode1
Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based ApproachesCode1
Exploiting Global and Local Hierarchies for Hierarchical Text ClassificationCode1
Exploring and Predicting Transferability across NLP TasksCode1
A Diagnostic Study of Explainability Techniques for Text ClassificationCode1
AMR-DA: Data Augmentation by Abstract Meaning RepresentationCode1
Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text AttacksCode1
FastText.zip: Compressing text classification modelsCode1
A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text ClassificationCode1
Few-Shot Learning with Siamese Networks and Label TuningCode1
Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum LearningCode1
Character-level Convolutional Networks for Text ClassificationCode1
Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text ClassificationCode1
Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training ApproachCode1
FNBench: Benchmarking Robust Federated Learning against Noisy LabelsCode1
FNet: Mixing Tokens with Fourier TransformsCode1
Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language ProcessingCode1
Active Learning for BERT: An Empirical StudyCode1
Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute ManipulationCode1
Generating Hierarchical Explanations on Text Classification via Feature Interaction DetectionCode1
Generating Natural Language Attacks in a Hard Label Black Box SettingCode1
Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLMCode1
Bag of Tricks for Efficient Text ClassificationCode1
Graph Convolutional Networks for Text ClassificationCode1
HateXplain: A Benchmark Dataset for Explainable Hate Speech DetectionCode1
HDLTex: Hierarchical Deep Learning for Text ClassificationCode1
Hierarchical Multi-Label Classification of Scientific DocumentsCode1
Hierarchical Topic Mining via Joint Spherical Tree and Text EmbeddingCode1
Hierarchy-aware Biased Bound Margin Loss Function for Hierarchical Text ClassificationCode1
Hierarchy-aware Label Semantics Matching Network for Hierarchical Text ClassificationCode1
An Evaluation Dataset for Intent Classification and Out-of-Scope PredictionCode1
An Amharic News Text classification DatasetCode1
Random Laplacian Features for Learning with Hyperbolic SpaceCode1
ICS: Total Freedom in Manual Text Classification Supported by Unobtrusive Machine LearningCode1
Are We Really Making Much Progress in Text Classification? A Comparative ReviewCode1
Improving Indonesian Text Classification Using Multilingual Language ModelCode1
Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text ClassificationCode1
VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout GroupsCode1
Approximating Instance-Dependent Noise via Instance-Confidence EmbeddingCode1
iNLTK: Natural Language Toolkit for Indic LanguagesCode1
AEDA: An Easier Data Augmentation Technique for Text ClassificationCode1
Interpreting Language Models with Contrastive ExplanationsCode1
An Embarrassingly Simple Method to Mitigate Undesirable Properties of Pretrained Language Model TokenizersCode1
JointMatch: A Unified Approach for Diverse and Collaborative Pseudo-Labeling to Semi-Supervised Text ClassificationCode1
KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic InterpretationsCode1
An Empirical Study of Invariant Risk MinimizationCode1
KLUE: Korean Language Understanding EvaluationCode1
An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot LabelsCode1
KNN-BERT: Fine-Tuning Pre-Trained Models with KNN ClassifierCode1
Automated Essay Scoring Using Transformer ModelsCode1
Show:102550
← PrevPage 5 of 73Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ST5-XXLAccuracy73.42Unverified
2ST5-XLAccuracy72.84Unverified
3ST5-LargeAccuracy72.31Unverified
4Ada SimilarityAccuracy70.44Unverified
5SGPT-5.8B-nliAccuracy70.14Unverified
6ST5-BaseAccuracy69.81Unverified
7SGPT-5.8B-msmarcoAccuracy68.13Unverified
8MPNet-multilingualAccuracy67.91Unverified
9GTR-XXLAccuracy67.41Unverified
10SimCSE-BERT-supAccuracy67.32Unverified
#ModelMetricClaimedVerifiedStatus
1Mistral-Small-24B + CAPOError15.7Unverified
2ToWE-SGError14Unverified
3Qwen2.5-32B + CAPOError12.93Unverified
4Llama-3.3-70B + CAPOError11.2Unverified
5Seq2CNN with GWS(50)Error9.64Unverified
6Char-level CNNError9.51Unverified
7SVDCNNError9.45Unverified
8VDCNError8.67Unverified
9Balanced+bi-leaf-RNNError7.9Unverified
10CCCapsNetError7.61Unverified
#ModelMetricClaimedVerifiedStatus
1Seq2CNN(50)Error2.77Unverified
2Char-level CNNError1.55Unverified
3SWEM-concatError1.43Unverified
4FastTextError1.4Unverified
5VDCNError1.29Unverified
6CCCapsNetError1.28Unverified
7Balanced+bi-leaf-RNNError1.2Unverified
8BERT large UDAError1.09Unverified
9M-ACNNError1.07Unverified
10EXAMError1Unverified
#ModelMetricClaimedVerifiedStatus
1DeBERTaAccuracy98.45Unverified
2C-BERT (ESGNN + BERT)Accuracy98.28Unverified
3ESGNNAccuracy98.23Unverified
4RoBERTaGCNAccuracy98.2Unverified
5BERTAccuracy98.17Unverified
6SGNNAccuracy98.09Unverified
7ERNIE 2.0Accuracy98.04Unverified
8DistilBERTAccuracy97.98Unverified
9Our Model*Accuracy97.8Unverified
10ALBERTv2Accuracy97.62Unverified
#ModelMetricClaimedVerifiedStatus
1TM-GloveError9.96Unverified
2byte mLSTM7Error9.6Unverified
3DELTA (CNN)Error7.8Unverified
4SWEM-averError7.8Unverified
5Capsule-BError7.2Unverified
6STM+TSED+PT+2LError7.04Unverified
7GRU-RNN-GLOVEError7Unverified
8MPAD-pathError6.2Unverified
9VLAWEError5.8Unverified
10C-LSTMError5.4Unverified
#ModelMetricClaimedVerifiedStatus
1LinearSVM+TFIDFAccuracy93Unverified
2RoBERTaGCNAccuracy89.5Unverified
3SSGCAccuracy88.6Unverified
4SGCAccuracy88.5Unverified
5SGCNAccuracy88.5Unverified
6RMDL (15 RDLs)Accuracy87.91Unverified
7Sparse Tensor ClassifierAccuracy87.3Unverified
8GraphStarAccuracy86.9Unverified
9NABoE-fullAccuracy86.8Unverified
10Text GCNAccuracy86.34Unverified
#ModelMetricClaimedVerifiedStatus
1ELECTRA + ANNF199.6Unverified
2ERNIE + ANNF199.4Unverified
3XLNet + ANNF199.2Unverified
4RoBERTa + ANNF198.7Unverified
5Longformer + ANNF193.9Unverified
6BERT + ANNF190.5Unverified
7ALBERT + ANNF179.7Unverified
8BERTF175Unverified
9DistilBERTF174.4Unverified
10LongformerF174Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTaGCNAccuracy72.8Unverified
2Our Model*Accuracy69.4Unverified
3SSGCAccuracy68.5Unverified
4SGCNAccuracy68.5Unverified
5SGCAccuracy68.5Unverified
6Text GCNAccuracy68.36Unverified
7GraphStarAccuracy64.2Unverified
8ApproxRepSetAccuracy64.06Unverified
9REL-RWMD k-NNAccuracy58.74Unverified
10CNN+LowercasedAccuracy36.2Unverified
#ModelMetricClaimedVerifiedStatus
1BERT-ITPT-FiTAccuracy77.62Unverified
2DRNNAccuracy76.26Unverified
3DELTA (HAN)Accuracy75.1Unverified
4EXAMAccuracy74.8Unverified
5DNC+CUWAccuracy74.3Unverified
6ULMFiT (Small data)Accuracy74.3Unverified
7CCCapsNetAccuracy73.85Unverified
8SWEM-concatAccuracy73.53Unverified
9FastTextAccuracy72.3Unverified
10Seq2CNN(50)Accuracy55.39Unverified
#ModelMetricClaimedVerifiedStatus
1DeBERTaAccuracy90.21Unverified
2RoBERTaGCNAccuracy89.7Unverified
3ERNIE 2.0 (optimized)Accuracy89.53Unverified
4RoBERTaAccuracy89.42Unverified
5ERNIE 2.0Accuracy88.97Unverified
6BERTAccuracy86.94Unverified
7ALBERTv2Accuracy86.02Unverified
8DistilBERTAccuracy85.31Unverified
9SSGCAccuracy76.7Unverified
#ModelMetricClaimedVerifiedStatus
1CliReBERT (P0L3/clirebert_clirevocab_uncased)Evaluation Macro F10.65Unverified
2ClimateBERT (climatebert/distilroberta-base-climate-f)Evaluation Macro F10.64Unverified
3BERT (google-bert/bert-base-uncased)Evaluation Macro F10.61Unverified
4CliSciBERT (P0L3/cliscibert_scivocab_uncased)Evaluation Macro F10.61Unverified
5SciBERT (allenai/scibert_scivocab_cased)Evaluation Macro F10.59Unverified
6DistilRoBERTa (distilbert/distilroberta-base)Evaluation Macro F10.58Unverified
7SciClimateBERT (P0L3/sciclimatebert)Evaluation Macro F10.58Unverified
8RoBERTa (FacebookAI/roberta-base)Evaluation Macro F10.57Unverified
#ModelMetricClaimedVerifiedStatus
1Human (Post-Rec.) (Spangher et al., 2021)macro F173.69Unverified
2MT-Mac (Spangher et al., 2021)macro F163.46Unverified
3MT-Mic (Spangher et al., 2021)macro F161.89Unverified
4RL-IP/TT (Choubey et al., 2021)macro F157Unverified
5Document LSTM + Document encoding (Choubey et al., 2020)macro F154.4Unverified
6CRF Fine-grained (Choubey et al., 2020)macro F152.9Unverified
7Human (Blind) (Spangher et al., 2021)macro F146.18Unverified
8Feature-based (SVM) (Choubey et al., 2020)macro F138.3Unverified
#ModelMetricClaimedVerifiedStatus
11-6 BertGCNAccuracy96.6Unverified
2GraphStarAccuracy95Unverified
3Our Model*Accuracy94.6Unverified
4SSGCAccuracy94.5Unverified
5SGCAccuracy94Unverified
6SGCNAccuracy94Unverified
7Text GCNAccuracy93.56Unverified
8TM-GloveAccuracy89.14Unverified