https://github.com/allegro/allenoise
공식 코드AlleNoise: large-scale text classification benchmark dataset with real-world label noise
Papers with Code 아카이브
Text Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 16
- 평가표
- 101
- 보존된 평가 기록
- 341
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>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/allenai/VILA
공식 코드VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups
https://github.com/allenai/contrastive-explanations
공식 코드https://github.com/allenai/dont-stop-pretraining
공식 코드Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
https://github.com/allenai/embeddingrecycling
공식 코드https://github.com/allenai/multicite
공식 코드https://github.com/allenai/scibert
공식 코드https://github.com/allenai/scicite
공식 코드Structural Scaffolds for Citation Intent Classification in Scientific Publications
https://github.com/allenai/scidocs
공식 코드SPECTER: Document-level Representation Learning using Citation-informed Transformers
https://github.com/allenai/sequential_sentence_classification
공식 코드Pretrained Language Models for Sequential Sentence Classification
https://github.com/allenai/sledgehammer
공식 코드The Right Tool for the Job: Matching Model and Instance Complexities
https://github.com/allenai/specter
공식 코드SPECTER: Document-level Representation Learning using Citation-informed Transformers
https://github.com/allenai/vampire
공식 코드Variational Pretraining for Semi-supervised Text Classification
https://github.com/allglc/tva-calibration
공식 코드https://github.com/alps-lab/trojan-lm
공식 코드https://github.com/alshedivat/cen
공식 코드https://github.com/alvinchangw/CARA_EMNLP2020
공식 코드Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder
https://github.com/amaiya/ktrain
공식 코드https://github.com/amao0o0/synwmd
공식 코드SynWMD: Syntax-aware Word Mover's Distance for Sentence Similarity Evaluation
https://github.com/amarallab/synthetic_benchmark_topic_model
공식 코드A new evaluation framework for topic modeling algorithms based on synthetic corpora
https://github.com/amazon-research/label-aware-pretrain
공식 코드Label Semantic Aware Pre-training for Few-shot Text Classification
https://github.com/amazon-science/text_generation_diffusion_llm_topic
공식 코드DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM
https://github.com/aminkaramlou/qnlg
공식 코드https://github.com/amirabaskohi/lm-cppf
공식 코드LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning
https://github.com/amirveyseh/definition_extraction
공식 코드A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency
https://github.com/amr-keleg/aldi-and-iaa
공식 코드https://github.com/amurtadha/rnt
공식 코드Rank-Aware Negative Training for Semi-Supervised Text Classification
https://github.com/amzn/pecos
공식 코드Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification
https://github.com/amzn/pretraining-or-self-training
공식 코드https://github.com/amzn/sto-transformer
공식 코드Transformer Uncertainty Estimation with Hierarchical Stochastic Attention
https://github.com/ancatache/LaRoSeDa
공식 코드https://github.com/andreapdr/gfun
공식 코드https://github.com/andst/sepll
공식 코드SepLL: Separating Latent Class Labels from Weak Supervision Noise
https://github.com/andychiangsh/pre-cofactv3
공식 코드Team Trifecta at Factify5WQA: Setting the Standard in Fact Verification with Fine-Tuning
https://github.com/andyweizhao/capsule_text_classification
공식 코드Investigating Capsule Networks with Dynamic Routing for Text Classification
https://github.com/angione-lab/12-machine-learning-models-for-text-classification
공식 코드A pipeline and comparative study of 12 machine learning models for text classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.