In this paper, we investigate the Dual-source Transformer architecture on the WikiReading information extraction and machine reading comprehension dataset. The proposed model outperforms the current state-of-the-art by a large margin. Next, we introduce WikiReading Recycled - a newly developed public dataset, supporting the task of multiple property extraction. It keeps the spirit of the original WikiReading but does not inherit the identified disadvantages of its predecessor.
Cite
@article{arxiv.2006.08281,
title = {On the Multi-Property Extraction and Beyond},
author = {Tomasz Dwojak and Michał Pietruszka and Łukasz Borchmann and Filip Graliński and Jakub Chłędowski},
journal= {arXiv preprint arXiv:2006.08281},
year = {2020}
}