Skim-Attention: Learning to Focus via Document Layout
| Autor: | Nguyen, Laura, Scialom, Thomas, Staiano, Jacopo, Piwowarski, Benjamin |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Transformer-based pre-training techniques of text and layout have proven effective in a number of document understanding tasks. Despite this success, multimodal pre-training models suffer from very high computational and memory costs. Motivated by human reading strategies, this paper presents Skim-Attention, a new attention mechanism that takes advantage of the structure of the document and its layout. Skim-Attention only attends to the 2-dimensional position of the words in a document. Our experiments show that Skim-Attention obtains a lower perplexity than prior works, while being more computationally efficient. Skim-Attention can be further combined with long-range Transformers to efficiently process long documents. We also show how Skim-Attention can be used off-the-shelf as a mask for any Pre-trained Language Model, allowing to improve their performance while restricting attention. Finally, we show the emergence of a document structure representation in Skim-Attention. Comment: 15 pages, 6 figures, to be published in EMNLP 2021 Findings |
| Databáze: | arXiv |
| Externí odkaz: |
|