GETT-QA: Graph Embedding Based T2T Transformer for Knowledge Graph Question Answering

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet


In this work, we present an end-to-end Knowledge Graph Question Answering (KGQA) system named GETT-QA. GETT-QA uses T5, a popular text-to-text pre-trained language model. The model takes a question in natural language as input and produces a simpler form of the intended SPARQL query. In the simpler form, the model does not directly produce entity and relation IDs. Instead, it produces corresponding entity and relation labels. The labels are grounded to KG entity and relation IDs in a subsequent step. To further improve the results, we instruct the model to produce a truncated version of the KG embedding for each entity. The truncated KG embedding enables a finer search for disambiguation purposes. We find that T5 is able to learn the truncated KG embeddings without any change of loss function, improving KGQA performance. As a result, we report strong results for LC-QuAD 2.0 and SimpleQuestions-Wikidata datasets on end-to-end KGQA over Wikidata.

TitelThe Semantic Web - 20th International Conference, ESWC 2023, Proceedings
HerausgeberCatia Pesquita, Daniel Faria, Ernesto Jimenez-Ruiz, Jamie McCusker, Mauro Dragoni, Anastasia Dimou, Raphael Troncy, Sven Hertling
Anzahl der Seiten19
VerlagSpringer Science and Business Media Deutschland GmbH
ISBN (Print)978-3-031-33455-9
ISBN (elektronisch)978-3-031-33454-2
PublikationsstatusErschienen - 23.05.2023
Extern publiziertJa
Veranstaltung20th International Conference on The Semantic Web - ESWC 2023: The Extended Semantic Web Conference - Aldemar Knossos Royal & Royal Villa, Hersonissos, Griechenland
Dauer: 28.05.202301.06.2023
Konferenznummer: 20

Bibliographische Notiz

Funding Information:
This research was supported by grants from NVIDIA and utilized NVIDIA 2 x RTX A5000 24 GB. Furthermore, we acknowledge the financial support from the Federal Ministry for Economic Affairs and Energy of Germany in the project CoyPu (project number 01MK21007[G]) and the German Research Foundation in the project NFDI4DS (project number 460234259). This research is additionally funded by the “Idea and Venture Fund” research grant by Universität Hamburg, which is part of the Excellence Strategy of the Federal and State Governments.

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.