SOTAVerified

Document Classification

Document Classification is a procedure of assigning one or more labels to a document from a predetermined set of labels.

Source: Long-length Legal Document Classification

Papers

Showing 51100 of 641 papers

TitleStatusHype
Improving accuracy and speeding up Document Image Classification through parallel systemsCode1
HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation LearningCode1
Pre-training technique to localize medical BERT and enhance biomedical BERTCode1
Taken by Surprise: Contrast effect for Similarity ScoresCode1
Are Large Language Models Ready for Healthcare? A Comparative Study on Clinical Language UnderstandingCode1
A Comparative Study of Pretrained Language Models for Long Clinical TextCode1
Efficient Few-shot Learning for Multi-label Classification of Scientific Documents with Many ClassesCode1
ANLS* -- A Universal Document Processing Metric for Generative Large Language ModelsCode1
Bioformer: an efficient transformer language model for biomedical text miningCode1
GeoGalactica: A Scientific Large Language Model in GeoscienceCode1
Aspect-based Document Similarity for Research PapersCode1
German's Next Language ModelCode1
Hierarchical Metadata-Aware Document Categorization under Weak SupervisionCode1
Improving Document Classification with Multi-Sense EmbeddingsCode1
Bridge Correlational Neural Networks for Multilingual Multimodal Representation LearningCode1
HDLTex: Hierarchical Deep Learning for Text ClassificationCode1
Three-level Hierarchical Transformer Networks for Long-sequence and Multiple Clinical Documents ClassificationCode1
Can a Fruit Fly Learn Word Embeddings?Code1
ChordMixer: A Scalable Neural Attention Model for Sequences with Different LengthsCode1
HiPool: Modeling Long Documents Using Graph Neural NetworksCode1
Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequencesCode1
Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM NetworkCode1
Improving Language Understanding by Generative Pre-TrainingCode1
Keyword Assisted Topic ModelsCode1
Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined TopicsCode1
ContraDoc: Understanding Self-Contradictions in Documents with Large Language ModelsCode1
Minimally Supervised Categorization of Text with MetadataCode1
LSD-C: Linearly Separable Deep ClustersCode1
SPECTER: Document-level Representation Learning using Citation-informed TransformersCode1
MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transferCode1
MultiFiT: Efficient Multi-lingual Language Model Fine-tuningCode1
Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label GraphsCode1
DocBERT: BERT for Document ClassificationCode1
Specialized Document Embeddings for Aspect-based Similarity of Research PapersCode1
Multimodal Side-Tuning for Document ClassificationCode1
GloVe: Global Vectors for Word RepresentationCode0
Geometric deep learning on graphs and manifolds using mixture model CNNsCode0
Glyce: Glyph-vectors for Chinese Character RepresentationsCode0
A Confidence-Calibrated MOBA Game Winner PredictorCode0
A Robust Hybrid Approach for Textual Document ClassificationCode0
Generative Topic Embedding: a Continuous Representation of DocumentsCode0
Generalized Sobolev Transport for Probability Measures on a GraphCode0
Generative Topic Embedding: a Continuous Representation of Documents (Extended Version with Proofs)Code0
AraDIC: Arabic Document Classification using Image-Based Character Embeddings and Class-Balanced LossCode0
Exploring Topic Coherence over Many Models and Many TopicsCode0
Explainable and Discourse Topic-aware Neural Language UnderstandingCode0
Corpus-level and Concept-based Explanations for Interpretable Document ClassificationCode0
Exploring the Relationship Between Algorithm Performance, Vocabulary, and Run-Time in Text ClassificationCode0
FLAG: Financial Long Document Classification via AMR-based GNNCode0
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature VectorsCode0
Show:102550
← PrevPage 2 of 13Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ApproxRepSetAccuracy97.17Unverified
2REL-RWMD k-NNAccuracy95.61Unverified
3Orthogonalized Soft VSMAccuracy92.65Unverified
4MAGNETF189.9Unverified
5VLAWEF189.3Unverified
6KD-LSTMregF188.9Unverified
7LSTM-reg (single model)F187Unverified
8SCDV-MSF182.71Unverified
#ModelMetricClaimedVerifiedStatus
1ACNetAccuracy83.5Unverified
2LGCNAccuracy83.3Unverified
3GATAccuracy83Unverified
4MoNetAccuracy81.7Unverified
5DeepWalkAccuracy67.2Unverified
#ModelMetricClaimedVerifiedStatus
1BioLinkBERT (large)F188.1Unverified
2NCBI_BERT(large) (P)F187.3Unverified
3SciFive-largeF186.08Unverified
4BioGPTMicro F185.12Unverified
5PubMedBERT uncasedMicro F182.32Unverified
#ModelMetricClaimedVerifiedStatus
1MPAD-pathAccuracy99.59Unverified
2Orthogonalized Soft VSMAccuracy97.73Unverified
3ApproxRepSetAccuracy95.73Unverified
4REL-RWMD k-NNAccuracy95.18Unverified
#ModelMetricClaimedVerifiedStatus
1ApproxRepSetAccuracy94.31Unverified
2Orthogonalized Soft VSMAccuracy93.42Unverified
3REL-RWMD k-NNAccuracy93.03Unverified
#ModelMetricClaimedVerifiedStatus
1ApproxRepSetAccuracy72.6Unverified
2REL-RWMD k-NNAccuracy71.05Unverified
3Orthogonalized Soft VSMAccuracy69.21Unverified
#ModelMetricClaimedVerifiedStatus
1KD-LSTMregF172.9Unverified
2MAGNETF169.6Unverified
#ModelMetricClaimedVerifiedStatus
1REL-RWMD k-NNAccuracy96.85Unverified
2ApproxRepSetAccuracy96.24Unverified
#ModelMetricClaimedVerifiedStatus
1Document Classification Using Importance of SentencesAccuracy54.8Unverified
2LSTM-reg (single model)Accuracy52.8Unverified
#ModelMetricClaimedVerifiedStatus
1ApproxRepSetAccuracy59.06Unverified
2REL-RWMD k-NNAccuracy56.8Unverified
#ModelMetricClaimedVerifiedStatus
1SPECTERF1 (micro)82Unverified
2SciNCLF1 (micro)81.4Unverified
#ModelMetricClaimedVerifiedStatus
1SciNCLF1 (micro)88.7Unverified
2SPECTERF1 (micro)86.4Unverified
#ModelMetricClaimedVerifiedStatus
1ConvTextTMAccuracy91.28Unverified
2HDLTexAccuracy90.93Unverified
#ModelMetricClaimedVerifiedStatus
1ChuLoAccuracy95.38Unverified
#ModelMetricClaimedVerifiedStatus
1ChuLoAccuracy64.4Unverified
#ModelMetricClaimedVerifiedStatus
1MPAD-pathAccuracy89.81Unverified
#ModelMetricClaimedVerifiedStatus
1BilBOWAAccuracy75Unverified
#ModelMetricClaimedVerifiedStatus
1BilBOWAAccuracy86.5Unverified
#ModelMetricClaimedVerifiedStatus
1HDLTexAccuracy86.07Unverified
#ModelMetricClaimedVerifiedStatus
1HDLTexAccuracy76.58Unverified
#ModelMetricClaimedVerifiedStatus
1KD-LSTMregAccuracy69.4Unverified