Filip Graliński

LAMBERT: Layout-Aware language Modeling using BERT for information extraction.

2020 · arXiv (Cornell University)

In this paper we introduce a novel approach to the problem of understanding documents where the local semantics is influenced by non-trivial layout. Namely, we modify the Transformer architecture in a way that allows it …

From Dataset Recycling to Multi-Property Extraction and Beyond

2020

This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outperforms the current state-of-theart by a large margin.