Print Email Facebook Twitter Obtaining Query-specific Similar Concepts with BERT-based retrieval for Commonsense Knowledge Gameboard Title Obtaining Query-specific Similar Concepts with BERT-based retrieval for Commonsense Knowledge Gameboard Author van Woensel, Martijn (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor He, G. (mentor) Gadiraju, Ujwal (mentor) Cruz, Luis (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2022-06-28 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. Subject Natural Language ProcessingCommonsense Knowledgegame with a purpose To reference this document use: http://resolver.tudelft.nl/uuid:1e30eb9c-bd5f-4097-acc0-6c798681693c Bibliographical note https://github.com/mvanwoensel/Similiar_Concepts link to code repo Part of collection Student theses Document type bachelor thesis Rights © 2022 Martijn van Woensel Files PDF Paper_Martijn_van_woensel_final.pdf 182.69 KB Close viewer /islandora/object/uuid:1e30eb9c-bd5f-4097-acc0-6c798681693c/datastream/OBJ/view