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/yangalan123/amortized-interpretability
공식 코드Efficient Shapley Values Estimation by Amortization for Text Classification
https://github.com/yangheng95/boosttextaugmentation
공식 코드BootAug: Boosting Text Augmentation via Hybrid Instance Filtering Framework
https://github.com/yangheng95/pyabsa
공식 코드PyABSA: A Modularized Framework for Reproducible Aspect-based Sentiment Analysis
https://github.com/yangzhou12/ncrl
공식 코드None Class Ranking Loss for Document-Level Relation Extraction
https://github.com/yannikbenz/zeroe
공식 코드From Hero to Zéroe: A Benchmark of Low-Level Adversarial Attacks
https://github.com/yao8839836/text_gcn
공식 코드https://github.com/yaodongyu/projnorm
공식 코드Predicting Out-of-Distribution Error with the Projection Norm
https://github.com/yaolu/random-prompt
공식 코드Strings from the Library of Babel: Random Sampling as a Strong Baseline for Prompt Optimisation
https://github.com/ydkwim/ctal
공식 코드CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations
https://github.com/ydli-ai/csl
공식 코드https://github.com/ydongd/prototypical-prompt-verbalizer
공식 코드Eliciting Knowledge from Pretrained Language Models for Prototypical Prompt Verbalizer
https://github.com/ydtydr/hyla
공식 코드Random Laplacian Features for Learning with Hyperbolic Space
https://github.com/yelboudouri/EmoNeXt
공식 코드https://github.com/yeyimilk/llm-zero-shot-classifiers
공식 코드https://github.com/yezhang-xiaofan/Rationale-CNN
공식 코드Rationale-Augmented Convolutional Neural Networks for Text Classification
https://github.com/yeziyi1998/uercm
공식 코드Towards a Better Understanding Human Reading Comprehension with Brain Signals
https://github.com/yi-ding-cs/emt
공식 코드EmT: A Novel Transformer for Generalized Cross-subject EEG Emotion Recognition
https://github.com/yifan-song793/infocl
공식 코드https://github.com/yihongl1u/colexificationnet
공식 코드https://github.com/yinwenpeng/BenchmarkingZeroShot
공식 코드Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach
https://github.com/yiruiliu110/ConditionalVI
공식 코드https://github.com/yisisang/story2personality
공식 코드MBTI Personality Prediction for Fictional Characters Using Movie Scripts
https://github.com/ylwangy/slstm_pytorch
공식 코드Pre-Training a Graph Recurrent Network for Language Representation
https://github.com/ymcui/Chinese-BERT-wwm
공식 코드https://github.com/yookyungkho/mav
공식 코드https://github.com/yoshitomo-matsubara/torchdistill
공식 코드https://github.com/yourh/AttentionXML
공식 코드https://github.com/yousef-younes/radar
공식 코드A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification
https://github.com/youseob/pin
공식 코드Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
https://github.com/ythuang02/AppealCase
공식 코드AppealCase: A Dataset and Benchmark for Civil Case Appeal Scenarios
https://github.com/yuchuantian/aigc_text_detector
공식 코드Multiscale Positive-Unlabeled Detection of AI-Generated Texts
https://github.com/yueeeeeeee/recsys-extraction-attack
공식 코드Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction
https://github.com/yuewang-cuhk/HashtagGeneration
공식 코드Microblog Hashtag Generation via Encoding Conversation Contexts
https://github.com/yueyu1030/COSINE
공식 코드https://github.com/yueyu1030/ReGen
공식 코드ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.