About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Iz Beltagy
- sl:arxiv_num : 2004.05150
- sl:arxiv_published : 2020-04-10T17:54:09Z
- sl:arxiv_summary : Transformer-based models are unable to process long sequences due to their
self-attention operation, which scales quadratically with the sequence length.
To address this limitation, we introduce the Longformer with an attention
mechanism that scales linearly with sequence length, making it easy to process
documents of thousands of tokens or longer. Longformer's attention mechanism is
a drop-in replacement for the standard self-attention and combines a local
windowed attention with a task motivated global attention. Following prior work
on long-sequence transformers, we evaluate Longformer on character-level
language modeling and achieve state-of-the-art results on text8 and enwik8. In
contrast to most prior work, we also pretrain Longformer and finetune it on a
variety of downstream tasks. Our pretrained Longformer consistently outperforms
RoBERTa on long document tasks and sets new state-of-the-art results on WikiHop
and TriviaQA.@en
- sl:arxiv_title : Longformer: The Long-Document Transformer@en
- sl:arxiv_updated : 2020-04-10T17:54:09Z
- sl:bookmarkOf : https://arxiv.org/abs/2004.05150
- sl:creationDate : 2020-04-13
- sl:creationTime : 2020-04-13T11:06:40Z
Documents with similar tags (experimental)