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/mhaseeb123/DeepMSim
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/mhjabreel/CharCNN
Character-level Convolutional Networks for Text Classification
https://github.com/mhjabreel/CharCnn_Keras
Character-level Convolutional Networks for Text Classification
https://github.com/mhw32/prototransformer-public
https://github.com/michael-wzhu/dynamic_routing_pytorch
Information Aggregation via Dynamic Routing for Sequence Encoding
https://github.com/microsoft/automated-explanations
https://github.com/microsoft/chunk-attention
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
https://github.com/microsoft/unilm/tree/master/layoutlm
https://github.com/midobal/OpenNMT-py
https://github.com/migrationsKB/MGKB
https://github.com/mim-solutions/bert_for_longer_texts
https://github.com/mim-solutions/roberta_for_longer_texts
https://github.com/mindspore-ai/models/tree/master/official/cv/deeptext
DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images
https://github.com/mindspore-ai/models/tree/master/official/gnn/gat
https://github.com/mindspore-ai/models/tree/master/official/nlp/bert
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/mindspore-ai/models/tree/master/official/nlp/bert_thor
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/mindspore-ai/models/tree/master/official/nlp/fasttext
https://github.com/mindspore-ai/models/tree/master/official/nlp/pangu_alpha
https://github.com/mindspore-ai/models/tree/master/official/nlp/textcnn
https://github.com/mindspore-ai/models/tree/master/research/nlp/hypertext
https://github.com/mindspore-courses/ABSA-MindSpore
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/mindspore-courses/DeepNLP-models-MindSpore
https://github.com/mindspore-courses/d2l-mindspore/tree/master/chapter_14_natural_language_processing_pretraining
SqueezeBERT: What can computer vision teach NLP about efficient neural networks?
https://github.com/mindspore-courses/d2l-mindspore/tree/master/chapter_15_natural_language_processing_applications
https://github.com/mindspore-lab/mindnlp/blob/master/mindnlp/models/bert/bert.py
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/mingdachen/bilm-tf
https://github.com/mipot101/GNM-Implementations
https://github.com/mirbostani/QA-KD-AL
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/mithunpaul08/bert_tensorflow
https://github.com/mitya8128/experiments_notes
https://github.com/mkavim/finetune_bert
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
https://github.com/mleimeister/document-image-classification
Multimodal deep networks for text and image-based document classification
https://github.com/mlzxzhou/keras-gnm
https://github.com/moado/expression_recognition
Real-time Convolutional Neural Networks for Emotion and Gender Classification
https://github.com/mocherson/aki_bert
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.