English

On the Multi-Property Extraction and Beyond

Computation and Language 2020-06-16 v1 Information Retrieval

Abstract

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}
}

Comments

5 pages

R2 v1 2026-06-23T16:19:48.415Z