Longformer-Encoder-Decoder
Year: 2,020
Journal: Allen Institute for Artificial Intelligence
Languages: English
Programming languages: Python
Input data:
text
Project website: https://huggingface.co/transformers/model_doc/led.html
We finally introduce the Longformer-Encoder-Decoder (LED), a Longformer variant for supporting long document generative sequence-to-sequence tasks, and demonstrate its effectiveness on the arXiv summarization dataset.