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/singaln/Roformer_Simlarity
RoFormer: Enhanced Transformer with Rotary Position Embedding
https://github.com/sinhasam/Sentalyze
Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling
https://github.com/siramatu/brigade-visualizer
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/sirius8050/Expected-Calibration-Error
https://github.com/sjmiller8182/character-convolutions-classification
Character-level Convolutional Networks for Text Classification
https://github.com/skesiraju/BaySMM
https://github.com/skoltech-nlp/rudetoxifier
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/skyve2012/DBA
Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification
https://github.com/sleep3r/garrus
https://github.com/slme1109/Lyrics_Generator_Using_LSTM
https://github.com/slme1109/lyrics-generator
https://github.com/smalik169/recursive-convolutional-autoencoder
https://github.com/smarton-empower/smarton-ai
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/snowkylin/gnn
https://github.com/snownus/COOP
https://github.com/sntcristian/and-kge
SPECTER: Document-level Representation Learning using Citation-informed Transformers
https://github.com/soarsmu/BiasFinder
https://github.com/socc-io/piqaboo
https://github.com/softmax1/flash-attention-softmax-n
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
https://github.com/somiltg/bert
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/somiltg/xquad
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/sonalisrijan/Deep-Learning-based-Defect-Prediction-Model-for-Source-Code
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/sophieburkhardt/dirichlet-vae-topic-models
https://github.com/soutsios/pos-tagger-bert-tensorflow
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/spice-h2020/SON
https://github.com/spokoyny/spokoyny.github.io
Towards Answering Climate Questionnaires from Unstructured Climate Reports
https://github.com/srviest/char-cnn-text-classification-pytorch
Character-level Convolutional Networks for Text Classification
https://github.com/sswetank-CS/MIL
Multiple Instance Learning: A Survey of Problem Characteristics and Applications
https://github.com/stanford-oval/genienlp
The Natural Language Decathlon: Multitask Learning as Question Answering
https://github.com/stefan-it/europeana-bert
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/stefan-it/fine-tuned-berts-seq
Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT
https://github.com/stefan-it/historic-ner
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/stephenbeckr/AIMS
https://github.com/stephenbeckr/CambridgeOptimisationCourse
https://github.com/studio-ousia/wikipedia2vec
Neural Attentive Bag-of-Entities Model for Text Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.