Neural Network-based Models with Commonsense Knowledge for Machine Reading Comprehension

Denis Smirnov


Abstract
State-of-the-art machine reading comprehension models are capable of producing answers for factual questions about a given piece of text. However, some type of questions requires commonsense knowledge which cannot be inferred from the given text passage. Thus, external semantic information could enhance the performance of these models. This PhD research proposal provides a brief overview of some existing machine reading comprehension datasets and models and outlines possible ways of their improvement.
Anthology ID:
R19-2014
Volume:
Proceedings of the Student Research Workshop Associated with RANLP 2019
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Editors:
Venelin Kovatchev, Irina Temnikova, Branislava Šandrih, Ivelina Nikolova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
90–94
Language:
URL:
https://aclanthology.org/R19-2014
DOI:
10.26615/issn.2603-2821.2019_014
Bibkey:
Cite (ACL):
Denis Smirnov. 2019. Neural Network-based Models with Commonsense Knowledge for Machine Reading Comprehension. In Proceedings of the Student Research Workshop Associated with RANLP 2019, pages 90–94, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Neural Network-based Models with Commonsense Knowledge for Machine Reading Comprehension (Smirnov, RANLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/R19-2014.pdf