Title: Conversational question answering over knowledge graphs with transformer and graph attention networks
Authors: Kacupaj, Endri
Plepi, Joan
Singh, Kuldeep
Thakkar, Harsh
Lehmann, Jens
Maleshkova, Maria 
Language: eng
Issue Date: 1-Jan-2021
Publisher: Association for Computational Linguistics (ACL)
Document Type: Conference Object
Published in (Book): he 16th Conference of the European Chapter of the Association for Computational Linguistics - proceedings of the conference
Publisher Place: Stroudsburg, PA
Conference: 16th conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), April 19-23, 2021
This paper addresses the task of (complex) conversational question answering over a knowledge graph. For this task, we propose LASAGNE (muLti-task semAntic parSing with trAnsformer and Graph atteNtion nEtworks). It is the first approach, which employs a transformer architecture extended with Graph Attention Networks for multi-task neural semantic parsing. LASAGNE uses a transformer model for generating the base logical forms, while the Graph Attention model is used to exploit correlations between (entity) types and predicates to produce node representations. LASAGNE also includes a novel entity recognition module which detects, links, and ranks all relevant entities in the question context. We evaluate LASAGNE on a standard dataset for complex sequential question answering, on which it outperforms existing baseline averages on all question types. Specifically, we show that LASAGNE improves the F1-score on eight out of ten question types; in some cases, the increase in F1-score is more than 20% compared to the state of the art.
Organization Units (connected with the publication): Universit├Ąt Bonn
ISBN: 9781954085022
ISSN: 23318422
Publisher DOI: 10.48550/arXiv.2104.01569
Appears in Collections:6 - Publication references (only metadata) of your publications before HSU

Show full item record

CORE Recommender


checked on Feb 21, 2024

Google ScholarTM




Items in openHSU are protected by copyright, with all rights reserved, unless otherwise indicated.