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/tata1661/shine-emnlp21
공식 코드Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification
https://github.com/tathi/maxmatch_dropout
공식 코드https://github.com/tca19/near-lossless-binarization
공식 코드https://github.com/tdopierre/FewShotText
공식 코드https://github.com/teapot123/JASen
공식 코드Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding
https://github.com/tensorflow/lingvo
공식 코드https://github.com/tensorflow/models
공식 코드Adversarial Training Methods for Semi-Supervised Text Classification
https://github.com/tgisaturday/Seq2CNN
공식 코드Abstractive Text Classification Using Sequence-to-convolution Neural Networks
https://github.com/thefonseca/concept-guidelines
공식 코드https://github.com/themody/nasforsentenceembeddingheads
공식 코드Neural Architecture Search for Sentence Classification with BERT
https://github.com/thestephencasper/latent_adversarial_training
공식 코드Defending Against Unforeseen Failure Modes with Latent Adversarial Training
https://github.com/thezingaro/multimodal-side-tuning
공식 코드https://github.com/thomasnguyen92/two-stage-decoder-icd
공식 코드https://github.com/thu-coai/augesc
공식 코드AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation
https://github.com/thu-coai/picl
공식 코드https://github.com/thulawtech/muser
공식 코드https://github.com/thumbe3/label-noise-nlp
공식 코드Towards Robustness to Label Noise in Text Classification via Noise Modeling
https://github.com/thunlp-mt/panda
공식 코드PANDA: Preference Adaptation for Enhancing Domain-Specific Abilities of LLMs
https://github.com/thunlp/MixADA
공식 코드https://github.com/thunlp/PTR
공식 코드https://github.com/thunlp/dpt
공식 코드Prompt Tuning for Discriminative Pre-trained Language Models
https://github.com/thunlp/knowledgeableprompttuning
공식 코드Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification
https://github.com/thunlp/moefication
공식 코드MoEfication: Transformer Feed-forward Layers are Mixtures of Experts
https://github.com/thunlp/opendelta
공식 코드Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models
https://github.com/tian14267/ls_mbert
공식 코드Incorporating Lexical and Syntactic Knowledge for Unsupervised Cross-Lingual Transfer
https://github.com/timmytonga/crois
공식 코드Improved Group Robustness via Classifier Retraining on Independent Splits
https://github.com/timoschick/pet
공식 코드Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference
https://github.com/tiwarylab/terp
공식 코드Thermodynamics-inspired Explanations of Artificial Intelligence
https://github.com/tkanchin/adaptive_reg_active_learning
공식 코드A Simple yet Brisk and Efficient Active Learning Platform for Text Classification
https://github.com/tkipf/pygcn
공식 코드Semi-Supervised Classification with Graph Convolutional Networks
https://github.com/tnhaider/poetry-emotion
공식 코드https://github.com/toneli/petailor-for-bio-triple-extraction
공식 코드BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicine
https://github.com/tonyw42/noisy-ie
공식 코드Learning Mutually Informed Representations for Characters and Subwords
https://github.com/tonyzhou98/concept-spurious-correlation
공식 코드Explore Spurious Correlations at the Concept Level in Language Models for Text Classification
https://github.com/tools-only/Evasion-Attack-against-LDA-Model
공식 코드EvaLDA: Efficient Evasion Attacks Towards Latent Dirichlet Allocation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.