Statements (63)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
Transformer model
|
| gptkbp:application |
Natural Language Processing
|
| gptkbp:architect |
Encoder-Decoder
|
| gptkbp:availableIn |
gptkb:PyTorch
TensorFlow Hugging Face Transformers |
| gptkbp:completed |
State-of-the-art results
|
| gptkbp:designedFor |
Question answering
Summarization Text classification Translation Text generation |
| gptkbp:developedBy |
gptkb:Google_Research
|
| gptkbp:evaluates |
gptkb:BLEU
ROUGE F1 score Exact match |
| https://www.w3.org/2000/01/rdf-schema#label |
T5 series
|
| gptkbp:improves |
Task-specific datasets
|
| gptkbp:influencedBy |
GPT-2
BERT XLNet |
| gptkbp:introduced |
2019
|
| gptkbp:model |
Small
Base Large 3B 11B |
| gptkbp:providesTrainingFor |
C4 dataset
|
| gptkbp:relatedTo |
Chatbots
Data Preprocessing Information Retrieval Knowledge Graphs Machine Translation Named Entity Recognition Sentiment Analysis Speech Recognition Text Summarization User Experience Conversational AI Text Analytics Text Mining Feature Extraction Natural Language Understanding Model Deployment Content Generation API Integration Data Annotation Document Classification Natural Language Generation Text Clustering User_Interface_Design Semantic_Search |
| gptkbp:supports |
Multiple languages
|
| gptkbp:training |
Supervised learning
Unsupervised learning |
| gptkbp:uses |
Transfer learning
Text-to-Text Transfer Transformer Feed-forward neural networks Layer normalization Multi-head attention Positional encoding Self-attention mechanism |