VOGUE: Answer Verbalization Through Multi-Task Learning
Publication date
2021-09-11
Document type
Konferenzbeitrag
Author
Organisational unit
University of Bonn
ISBN
ISSN
Conference
European Conference, ECML PKDD 2021 Bilbao, Spain, September 13–17, 2021
Series or journal
Lecture Notes in Computer Science
Periodical volume
12977
Book title
Machine Learning and Knowledge Discovery in Databases. Research Track : European Conference, ECML PKDD 2021 Bilbao, Spain, September 13–17, 2021 Proceedings, Part III
First page
563
Last page
579
Part of the university bibliography
Nein
Keyword
Answer verbalization
Knowledge graphs
Multi-task learning
Natural language generation
Question answering
Abstract
In recent years, there have been significant developments in Question Answering over Knowledge Graphs (KGQA). Despite all the notable advancements, current KGQA systems only focus on answer generation techniques and not on answer verbalization. However, in real-world scenarios (e.g., voice assistants such as Alexa, Siri, etc.), users prefer verbalized answers instead of a generated response. This paper addresses the task of answer verbalization for (complex) question answering over knowledge graphs. In this context, we propose a multi-task-based answer verbalization framework: VOGUE (Verbalization thrOuGh mUlti-task lEarning). The VOGUE framework attempts to generate a verbalized answer using a hybrid approach through a multi-task learning paradigm. Our framework can generate results based on using questions and queries as inputs concurrently. VOGUE comprises four modules that are trained simultaneously through multi-task learning. We evaluate our framework on existing datasets for answer verbalization, and it outperforms all current baselines on both BLEU and METEOR scores. © 2021, Springer Nature Switzerland AG.
Cite as
Kacupaj, E., Premnadh, S., Singh, K., Lehmann, J., Maleshkova, M. (2021). VOGUE: Answer Verbalization Through Multi-Task Learning. In: Oliver, N., Pérez-Cruz, F., Kramer, S., Read, J., Lozano, J.A. (eds) Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2021. Lecture Notes in Computer Science(), vol 12977. Springer, Cham. https://doi.org/10.1007/978-3-030-86523-8_34
Version
Published version
Access right on openHSU
Metadata only access