Volltext-Downloads (blau) und Frontdoor-Views (grau)

Knowledge Base Question Answering by Transformer-Based Graph Pattern Scoring

  • Question Answering (QA) has gained significant attention in recent years, with transformer-based models improving natural language processing. However, issues of explainability remain, as it is difficult to determine whether an answer is based on a true fact or a hallucination. Knowledge-based question answering (KBQA) methods can address this problem by retrieving answers from a knowledge graph. This paper proposes a hybrid approach to KBQA called FRED, which combines pattern-based entity retrieval with a transformer-based question encoder. The method uses an evolutionary approach to learn SPARQL patterns, which retrieve candidate entities from a knowledge base. The transformer-based regressor is then trained to estimate each pattern’s expected F1 score for answering the question, resulting in a ranking ofcandidate entities. Unlike other approaches, FRED can attribute results to learned SPARQL patterns, making them more interpretable. The method is evaluated on two datasets and yields MAP scores of up to 73 percent, with the transformer-based interpretation falling only 4 pp short of an oracle run. Additionally, the learned patterns successfully complement manually generated ones and generalize well to novel questions.

Download full text files

Export metadata

Additional Services

Search Google Scholar Check availability

Statistics

Show usage statistics
Metadaten
Document Type:Conference Object
Language:English
Author:Marcel Lamott, Jörn Hees, Adrian Ulges
Parent Title (English):ICCBR TMG’23: Workshop on Text Mining and Generation at ICCBR2023, July 17 – 20, 2023, Aberdeen, Scotland
Number of pages:16
First Page:98
Last Page:113
ISSN:1613-0073
URN:urn:nbn:de:hbz:1044-opus-74387
URL:https://ceur-ws.org/Vol-3438/#paper_08
Publisher:RWTH Aachen
Place of publication:Aachen, Germany
Publishing Institution:Hochschule Bonn-Rhein-Sieg
Date of first publication:2023/07/08
Copyright:© 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Keyword:knowledge graphs; question answering; transfer learning
Departments, institutes and facilities:Fachbereich Informatik
Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE)
Dewey Decimal Classification (DDC):0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 005 Computerprogrammierung, Programme, Daten
Entry in this database:2023/07/25
Licence (German):License LogoCreative Commons - CC BY - Namensnennung 4.0 International