https://github.com/matheussoranco/abstractive-text-summarization
Abstractive Text Summarization using BART
https://github.com/matheussoranco/abstractive-text-summarization
artificial-intelligence bart deep-learning jupyter-notebook language-model python
Last synced: about 2 months ago
JSON representation
Abstractive Text Summarization using BART
- Host: GitHub
- URL: https://github.com/matheussoranco/abstractive-text-summarization
- Owner: Matheussoranco
- Created: 2024-12-17T14:11:11.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-18T13:20:15.000Z (over 1 year ago)
- Last Synced: 2025-01-30T00:33:53.417Z (over 1 year ago)
- Topics: artificial-intelligence, bart, deep-learning, jupyter-notebook, language-model, python
- Language: Jupyter Notebook
- Homepage:
- Size: 27.3 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Abstractive-Text-Summarization
Bidirectional Autoregressive Transformer (BART) is a Transformer-based encoder-decoder model, often used for sequence-to-sequence tasks like summarization and neural machine translation. BART is pre-trained in a self-supervised fashion on a large text corpus. During pre-training, the text is corrupted and BART is trained to reconstruct the original text (hence called a "denoising autoencoder"). Some pre-training tasks include token masking, token deletion, sentence permutation (shuffle sentences and train BART to fix the order), etc.
# Sources and references:
- [Keras: BART Example](https://keras.io/examples/nlp/abstractive_summarization_with_bart/)
- [BART article on Arxiv](https://arxiv.org/abs/1910.13461)