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

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

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.

Original languageEnglish
Title of host publicationThe Semantic Web - 20th International Conference, ESWC 2023, Proceedings
EditorsCatia Pesquita, Daniel Faria, Ernesto Jimenez-Ruiz, Jamie McCusker, Mauro Dragoni, Anastasia Dimou, Raphael Troncy, Sven Hertling
Number of pages19
PublisherSpringer Science and Business Media Deutschland GmbH
Publication date23.05.2023
Pages279-297
ISBN (print)978-3-031-33455-9
ISBN (electronic)978-3-031-33454-2
DOIs
Publication statusPublished - 23.05.2023
Externally publishedYes
Event20th International Conference on The Semantic Web - ESWC 2023: The Extended Semantic Web Conference - Aldemar Knossos Royal & Royal Villa, Hersonissos, Greece
Duration: 28.05.202301.06.2023
Conference number: 20
https://2023.eswc-conferences.org/

Bibliographical note

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