Depending on the amount of data to process, file generation may take longer.

If it takes too long to generate, you can limit the data by, for example, reducing the range of years.

Chapter

Download BibTeX

Title

Should We Afford Affordances? Injecting ConceptNet Knowledge into BERT-Based Models to Improve Commonsense Reasoning Ability

Authors

[ 1 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ S ] student | [ P ] employee

Scientific discipline (Law 2.0)

[2.3] Information and communication technology

Year of publication

2022

Chapter type

chapter in monograph / paper

Publication language

english

Keywords
EN
  • Commonsense reasoning
  • Natural Language Processing
  • Deep Learning
  • Knowledge Graph
Abstract

EN Recent years have shown that deep learning models pre-trained on large text corpora using the language model objective can help solve various tasks requiring natural language understanding. However, many commonsense concepts are underrepresented in online resources because they are too obvious for most humans. To solve this problem, we propose the use of affordances – common-sense knowledge that can be injected into models to increase their ability to understand our world. We show that injecting ConceptNet knowledge into BERT-based models leads to an increase in evaluation scores measured on the PIQA dataset.

Date of online publication

20.09.2022

Pages (from - to)

97 - 104

DOI

10.1007/978-3-031-17105-5_7

URL

https://link.springer.com/chapter/10.1007/978-3-031-17105-5_7

Book

Knowledge Engineering and Knowledge Management : 23rd International Conference, EKAW 2022, Bolzano, Italy, September 26–29, 2022, Proceedings

Presented on

23rd International Conference on Knowledge Engineering and Knowledge Management EKAW 2022, 26-29.09.2022, Bolzano, Italy

Open Access Mode

publisher's website

Open Access Text Version

final published version

Ministry points / chapter

20

Ministry points / conference (CORE)

70

This website uses cookies to remember the authenticated session of the user. For more information, read about Cookies and Privacy Policy.