Semantic Parsing for Knowledge Graph Question Answering with Large Language Models
Publikation: Beiträge in Sammelwerken › Aufsätze in Konferenzbänden › Forschung › begutachtet
Standard
Semantic Parsing for Knowledge Graph Question Answering with Large Language Models. / Banerjee, Debayan.
The Semantic Web: ESWC 2023 Satellite Events, Hersonissos, Crete, Greece, May 28 - June 1, 2023, Proceedings . Hrsg. / Catia Pesquita; Hala Skaf-Molli; Vasilis Efthymiou; Sabrina Kirrane; Axel Ngonga; Diego Collarana; Renato Cerqueira; Mehwish Alam; Cassia Trojahn; Sven Hertling. Cham : Springer Science and Business Media Deutschland GmbH, 2023. S. 234-243 (Lecture Notes in Computer Science; Band 13998 LNCS).Publikation: Beiträge in Sammelwerken › Aufsätze in Konferenzbänden › Forschung › begutachtet
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Semantic Parsing for Knowledge Graph Question Answering with Large Language Models
AU - Banerjee, Debayan
N1 - Conference code: 20
PY - 2023
Y1 - 2023
N2 - This thesis explores the topic of Knowledge Graph Question Answering with a special emphasis on semantic parsing approaches, incorporating pre-trained text-to-text language models. We use the text generation ability of these models to convert natural language questions to logical forms. We test whether correct logical forms are being generated, and if not, how to mitigate the failure cases. As a second step, we try to make the same models generate additional information to aid the process of grounding of the logical forms to entities, relations and literals in the Knowledge Graph. In experiments conducted so far, we see encouraging results on both generation of base logical forms, and grounding them to the KG elements. At the same time, we discover failure cases prompting directions in future work (The author considers himself a ‘middle-stage’ Ph.D. candidate).
AB - This thesis explores the topic of Knowledge Graph Question Answering with a special emphasis on semantic parsing approaches, incorporating pre-trained text-to-text language models. We use the text generation ability of these models to convert natural language questions to logical forms. We test whether correct logical forms are being generated, and if not, how to mitigate the failure cases. As a second step, we try to make the same models generate additional information to aid the process of grounding of the logical forms to entities, relations and literals in the Knowledge Graph. In experiments conducted so far, we see encouraging results on both generation of base logical forms, and grounding them to the KG elements. At the same time, we discover failure cases prompting directions in future work (The author considers himself a ‘middle-stage’ Ph.D. candidate).
KW - Informatics
UR - http://www.scopus.com/inward/record.url?scp=85176013413&partnerID=8YFLogxK
UR - https://d-nb.info/1306843561
UR - https://www.mendeley.com/catalogue/28b64db7-d8bb-3600-8abf-1a65f182425d/
U2 - 10.1007/978-3-031-43458-7_42
DO - 10.1007/978-3-031-43458-7_42
M3 - Article in conference proceedings
AN - SCOPUS:85176013413
SN - 978-3-031-43457-0
T3 - Lecture Notes in Computer Science
SP - 234
EP - 243
BT - The Semantic Web
A2 - Pesquita, Catia
A2 - Skaf-Molli, Hala
A2 - Efthymiou, Vasilis
A2 - Kirrane, Sabrina
A2 - Ngonga, Axel
A2 - Collarana, Diego
A2 - Cerqueira, Renato
A2 - Alam, Mehwish
A2 - Trojahn, Cassia
A2 - Hertling, Sven
PB - Springer Science and Business Media Deutschland GmbH
CY - Cham
T2 - 20th International Conference on The Semantic Web - ESWC 2023
Y2 - 28 May 2023 through 1 June 2023
ER -