PK PyTorchKR Papers
Papers with Code · CC BY-SA 4.0

Text Classification

583 평가 기록 191 datasets

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>

개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.

벤치마크

Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.

Dataset기록된 모델 예시MetricPaperCode
ST5-XXL
Accuracy: 73.42
논문 코드
XLNet
Error: 4.45
논문 코드
RoBERTa Focal Loss
AUROC: 0.9818Macro F1: 0.4648Micro F1: 0.5524Precision: 0.4017
논문 코드
XLNet
Error: 0.62
논문 코드
R8
DeBERTa
Accuracy: 98.451
논문 코드
Automatic Label Error Correction
Error: 0.40
논문 코드
LinearSVM+TFIDF
Accuracy: 93F-measure: 93
논문 -
ELECTRA + ANN
F1: 99.6
논문 -
BERT-ITPT-FiT
2019-05-14
논문 코드
MR
VLAWE
Accuracy: 93.3
논문 코드
RoBERTaGCN
Accuracy: 72.8
논문 코드
BERT-ITPT-FiT
Accuracy: 77.62
논문 코드

데이터셋

191개
MTEBAG NewsCivil CommentsDBpediaR8TREC-620NEWSUK Key Stage ReadabilityIMDbMROhsumedYahoo! Answers

논문

라이브러리

Papers with Code 리더보드 row에 연결된 구현 저장소입니다.

github.com/huggingface/transformers 2 논문
github.com/peluz/VICTOR-dataset 1 논문
github.com/michiyasunaga/LinkBERT 1 논문
github.com/2024-MindSpore-1/Code2/tree/main/model-1/big_bird 1 논문
github.com/2miatran/Natural-Language-Processing 1 논문
github.com/abhilash1910/MiniAttention 1 논문
github.com/bionlu-coling2024/biomed-ner-intent_detection 1 논문
github.com/chesterdu/contrastive_summary 1 논문

하위 태스크

DC Document Classification 22 데이터셋 · 51 rows MT Multi-Label Text Classification 20 데이터셋 · 50 rows TC Toxic Comment Classification 4 데이터셋 · 25 rows TM Topic Models 9 데이터셋 · 23 rows EC Emotion Classification 9 데이터셋 · 19 rows FT Few-Shot Text Classification 8 데이터셋 · 19 rows CI Citation Intent Classification 2 데이터셋 · 16 rows SC Sentence Classification 6 데이터셋 · 16 rows CE Coherence Evaluation 2 데이터셋 · 7 rows UT Unsupervised Text Classification 4 데이터셋 · 7 rows ST Semi-Supervised Text Classification 2 데이터셋 · 6 rows VD Variable Detection 1 데이터셋 · 2 rows