https://github.com/jackbandy/deep_learning_ulmfit
Universal Language Model Fine-tuning for Text Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Universal Language Model Fine-tuning for Text Classification
Universal Language Model Fine-tuning for Text Classification
Improving accuracy and speeding up Document Image Classification through parallel systems
Supervised and Unsupervised Neural Approaches to Text Readability
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Pruning and Sparsemax Methods for Hierarchical Attention Networks
PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts
Generative and Discriminative Text Classification with Recurrent Neural Networks
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Very Large Language Model as a Unified Methodology of Text Mining
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
XLNet: Generalized Autoregressive Pretraining for Language Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.