Obtaining Query-specific Similar Concepts with BERT-based retrieval for Commonsense Knowledge Gameboard
M.G.A. van Woensel (TU Delft - Electrical Engineering, Mathematics and Computer Science)
G. He – Mentor (TU Delft - Web Information Systems)
U.K. Gadiraju – Mentor (TU Delft - Web Information Systems)
Luis Cruz – Graduation committee member (TU Delft - Software Engineering)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Commonsense knowledge based question answer- ing is a recent topic that has seen a surge in inter- est. Yet most models obtain general data, this pa- per looks at obtaining query-specific similar con- cepts using first and second-order proximity to- gether with BERT-based retrieval. Using these query-specific concepts new commonsense knowl- edge can be obtained using a Game with a pur- pose. Results show that this current implementa- tion leaves room for improvement.