18 citations · 38 across the 10 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.CL2020★ 1 cited
Sparsifying Transformer Models with Trainable Representation Pooling
Michał Pietruszka, Łukasz Borchmann, Łukasz Garncarek
We propose a novel method to sparsify attention in the Transformer model by learning to select the most-informative token representations during the training process, thus focusing…
cs.CL2020★ 7 cited
LAMBERT: Layout-Aware (Language) Modeling for information extraction
Łukasz Garncarek, Rafał Powalski, Tomasz Stanisławek +4
We introduce a simple new approach to the problem of understanding documents where non-trivial layout influences the local semantics. To this end, we modify the Transformer encoder…