BART is a denoising autoencoder for pretraining sequence-to-sequence models. It is trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. It uses a standard Transformer-based neural machine translation architecture. It uses a standard seq2seq/NMT architecture with a bidirectional encoder (like BERT) and a left-to-right decoder (like GPT). This means the encoder's attention mask is fully visible, like BERT, and the decoder's attention mask is causal, like GPT2.
Source: BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Retrieval | 129 | 13.11% |
Question Answering | 79 | 8.03% |
Language Modelling | 71 | 7.22% |
Text Generation | 64 | 6.50% |
Abstractive Text Summarization | 45 | 4.57% |
Sentence | 40 | 4.07% |
Text Summarization | 27 | 2.74% |
Large Language Model | 21 | 2.13% |
Information Retrieval | 21 | 2.13% |