BERTologyNavigator: Advanced Question Answering with BERT-based Semantics
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Standard
Joint Proceedings of Scholarly QALD 2023 and SemREC 2023 co-located with 22nd International Semantic Web Conference ISWC 2023 : Athens, Greece, November 6-10, 2023. ed. / Debayan Banerjee; Ricardo Usbeck; Nandana Mihindukulasooriya; Mohamad Yaser Jaradeh; Sören Auer; Gunjan Singh; Raghava Mutharaju; Pavan Kapanipathi. Vol. 3592 Aachen: Rheinisch-Westfälische Technische Hochschule Aachen, 2023. 7 (CEUR Workshop Proceedings; Vol. 3592).
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - BERTologyNavigator: Advanced Question Answering with BERT-based Semantics
AU - Rajpal, Shreya
AU - Usbeck, Ricardo
N1 - Conference code: 1
PY - 2023
Y1 - 2023
N2 - The development and integration of knowledge graphs and language models has significance in artificial intelligence and natural language processing. In this study, we introduce the BERTologyNavigator- a two-phased system that combines relation extraction techniques and BERT embeddings to navigate the relationships within the DBLP Knowledge Graph (KG). Our approach focuses on extracting one-hop relations and labelled candidate pairs in the first phases. This is followed by employing BERT's CLS embeddings and additional heuristics for relation selection in the second phase. Our system reaches an F1 score of 0.2175 on the DBLP QuAD Final test dataset for Scholarly QALD and 0.98 F1 score on the subset of the DBLP QuAD test dataset during the QA phase.
AB - The development and integration of knowledge graphs and language models has significance in artificial intelligence and natural language processing. In this study, we introduce the BERTologyNavigator- a two-phased system that combines relation extraction techniques and BERT embeddings to navigate the relationships within the DBLP Knowledge Graph (KG). Our approach focuses on extracting one-hop relations and labelled candidate pairs in the first phases. This is followed by employing BERT's CLS embeddings and additional heuristics for relation selection in the second phase. Our system reaches an F1 score of 0.2175 on the DBLP QuAD Final test dataset for Scholarly QALD and 0.98 F1 score on the subset of the DBLP QuAD test dataset during the QA phase.
KW - Informatics
KW - Business informatics
KW - Language Models
KW - Knowledge Graph Question Answering (KGQA)
KW - DBLP QuAD
KW - DBLP KG
KW - Relation extraction
KW - Relation selection
UR - https://ceur-ws.org/Vol-3592/
UR - http://www.scopus.com/inward/record.url?scp=85180554489&partnerID=8YFLogxK
M3 - Article in conference proceedings
VL - 3592
T3 - CEUR Workshop Proceedings
BT - Joint Proceedings of Scholarly QALD 2023 and SemREC 2023 co-located with 22nd International Semantic Web Conference ISWC 2023
A2 - Banerjee, Debayan
A2 - Usbeck, Ricardo
A2 - Mihindukulasooriya, Nandana
A2 - Jaradeh, Mohamad Yaser
A2 - Auer, Sören
A2 - Singh, Gunjan
A2 - Mutharaju, Raghava
A2 - Kapanipathi, Pavan
PB - Rheinisch-Westfälische Technische Hochschule Aachen
CY - Aachen
T2 - Scholarly QALD 2023
Y2 - 6 November 2023 through 10 November 2023
ER -