KvGR: A graph-based interface for explorative sequential question answering on heterogeneous information sources

Exploring a knowledge base is often an iterative process: initially vague information needs are refined by interaction. We propose a novel approach for such interaction that supports sequential question answering (SQA) on knowledge graphs. As opposed to previous work, we focus on exploratory settings, which we support with a visual representation of graph structures, helping users to better understand relationships. In addition, our approach keeps track of context – an important challenge in SQA – by allowing users to make their focus explicit via subgraph selection. Our results show that the interaction principle is either understood immediately or picked up very quickly – and that the possibility of exploring the information space iteratively is appreciated.

Schlagwörter

Fachgebiet (DDC)

330 - Wirtschaft

Projekt

Veranstaltung

42nd European Conference on IR Research (ECIR 2020)

Startdatum der Ausstellung

Enddatum der Ausstellung

Startdatum der Konferenz

14.04.2020

Enddatum der Konferenz

17.04.2020

Datum der letzten Prüfung

ISBN

978-3-030-45438-8
978-3-030-45439-5

ISSN

Sprache

Englisch

Während FHNW Zugehörigkeit erstellt

Ja

Zukunftsfelder FHNW

Publikationsstatus

Veröffentlicht

Begutachtung

Peer-Review der ganzen Publikation

Open Access-Status

Closed

Lizenz

Zitation

WITSCHEL, Hans Friedrich, Kaspar RIESEN und Loris GRETHER, 2020. KvGR: A graph-based interface for explorative sequential question answering on heterogeneous information sources. In: Joemon M. JOSE, Emine YILMAZ, João MAGALHÃES, Pablo CASTELLS, Nicola FERRO, Mário J. SILVA und Flávio MARTINS (Hrsg.), Advances in Information Retrieval. 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, April 14-17, 2020. Proceedings. Lisbon: Springer. 2020. S. 760–773. Lecture notes in computer science, 12035. ISBN 978-3-030-45438-8. Verfügbar unter: https://irf.fhnw.ch/handle/11654/42675

Komplettanzeige