On the Multi-Property Extraction and Beyond

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 publi...

Full description

Saved in:
Bibliographic Details
Main Authors Dwojak, Tomasz, Pietruszka, Michał, Borchmann, Łukasz, Graliński, Filip, Chłędowski, Jakub
Format Journal Article
LanguageEnglish
Published 15.06.2020
Subjects
Computer Science - Computation and Language
Computer Science - Information Retrieval
Online AccessGet full text

Cover

More Information
Summary: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.
DOI:10.48550/arxiv.2006.08281