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/OctoberChang/X-Transformer
공식 코드Taming Pretrained Transformers for Extreme Multi-label Text Classification
https://github.com/PAIR-code/lit
공식 코드https://github.com/PRIS-CV/AdvancedDropout
공식 코드Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
https://github.com/PaddlePaddle/PaddleNLP/tree/develop/paddlenlp/transformers/ernie_doc
공식 코드ERNIE-Doc: A Retrospective Long-Document Modeling Transformer
https://github.com/PetarV-/GAT
공식 코드https://github.com/QData/TextAttack
공식 코드BAE: BERT-based Adversarial Examples for Text Classification
https://github.com/QData/TextAttack/blob/master/textattack/attack_recipes/bae_garg_2019.py
공식 코드BAE: BERT-based Adversarial Examples for Text Classification
https://github.com/QData/deepWordBug
공식 코드Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers
https://github.com/Quadflor/quadflor
공식 코드Using Titles vs. Full-text as Source for Automated Semantic Document Annotation
https://github.com/Quicksign/ocrized-text-dataset
공식 코드Multimodal deep networks for text and image-based document classification
https://github.com/QwenLM/Qwen-7B
공식 코드https://github.com/Raibows/RSE-Adversarial-Defense
공식 코드Defense of Word-level Adversarial Attacks via Random Substitution Encoding
https://github.com/RingBDStack/HE-AGCRCNN
공식 코드https://github.com/RingBDStack/HTCInfoMax
공식 코드HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization
https://github.com/RishabhMaheshwary/contextattack
공식 코드A Context Aware Approach for Generating Natural Language Attacks
https://github.com/RishabhMaheshwary/hard-label-attack
공식 코드Generating Natural Language Attacks in a Hard Label Black Box Setting
https://github.com/Roche/BalancedLossNLP
공식 코드Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution
https://github.com/RowitZou/RankAE
공식 코드Unsupervised Summarization for Chat Logs with Topic-Oriented Ranking and Context-Aware Auto-Encoders
https://github.com/Rqcker/eai2024
공식 코드https://github.com/RyanWangZf/Influence_Subsampling
공식 코드Less Is Better: Unweighted Data Subsampling via Influence Function
https://github.com/SAP-samples/security-research-dp-hierarchical-text
공식 코드On the privacy-utility trade-off in differentially private hierarchical text classification
https://github.com/SDPRA-2021/shared-task
공식 코드Using Transformer based Ensemble Learning to classify Scientific Articles
https://github.com/SDPRA-2021/shared-task/tree/main/FideLIPI
공식 코드Using Transformer based Ensemble Learning to classify Scientific Articles
https://github.com/SDRMp/DRPG
공식 코드GUIDEQ: Framework for Guided Questioning for progressive informational collection and classification
https://github.com/SITE5039/AgrLearn
공식 코드Aggregated Learning: A Vector-Quantization Approach to Learning Neural Network Classifiers
https://github.com/SLAD-ml/few-shot-ood
공식 코드Out-of-Domain Detection for Low-Resource Text Classification Tasks
https://github.com/SUSTechBruce/G-MAP
공식 코드G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks
https://github.com/Sachin19/adversarial-classify
공식 코드Topics to Avoid: Demoting Latent Confounds in Text Classification
https://github.com/SenWu/dauphin
공식 코드On the Generalization Effects of Linear Transformations in Data Augmentation
https://github.com/SenticNet/conv-emotion
공식 코드DialogueRNN: An Attentive RNN for Emotion Detection in Conversations
https://github.com/ShannonAI/ChineseBert
공식 코드ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information
https://github.com/ShannonAI/Neural-Semi-Supervised-Learning-for-Text-Classification
공식 코드Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining
https://github.com/ShannonAI/glyce
공식 코드https://github.com/ShannonAI/kfolden-ood-detection
공식 코드$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection
https://github.com/SkBlaz/attviz
공식 코드AttViz: Online exploration of self-attention for transparent neural language modeling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.