Offline question answering over linked data using limited resources

Paramjot Kaur; Vincent Blücher; Rricha Jalota; Diego Moussallem; Axel Cyrille Ngonga Ngomo; Ricardo Usbeck

Offline question answering over linked data using limited resources

Paramjot Kaur
, Vincent Blücher
, Rricha Jalota
, Diego Moussallem
, Axel Cyrille Ngonga Ngomo
, Ricardo Usbeck

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

Abstract

Question Answering over Linked Data provides concise information to the user from a natural language request instead of flooding them with documents. However, the accessibility of Linked Data resources, e.g., SPARQL endpoints, is bound to an online connection. We present OQA, the first offline Question Answering system over Linked Data for mobile devices. We built OQA with the limited resources of an Android mobile device, such as battery power, computational power, or memory consumption in mind. Our OQA system has three main components: 1) question analysis and 2) query generation which identify the type of the question and reform it into a semantically meaningful data structure, i.e., a SPARQL query. Finally, the 3) query execution uses a novel mobile triple store, implemented with RDF4J. Our evaluation suggests that OQA is feasible for daily use in terms of battery consumption and able to answer domain-specific questions with up to 72% accuracy.

Original language	English
Title of host publication	SEMPDS 2019 : Posters and Demos at SEMANTiCS 2019
Editors	Mehwish Alam, Ricardo Usbeck, Tassilo Pellegrini, Harald Sack, York Sure-Vetter
Volume	2451
Publisher	Sun Site Central Europe (RWTH Aachen University)
Publication date	09.2019
Publication status	Published - 09.2019
Externally published	Yes
Event	15th International Conference on Semantic Systems, SEMPDS 2019: The Power of AI and Knowledge Graphs - Gartenhalle, Festplatz 3, Karlsruhe, Germany Duration: 09.09.2019 → 12.09.2019 https://2019.semantics.cc

Bibliographical note

Publisher Copyright:
Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

Research areas and keywords

Informatics
Business informatics

Access to Document

https://ceur-ws.org/Vol-2451/paper-15.pdfLicence: CC BY
https://nbn-resolving.org/urn:nbn:de:0074-2451-7Licence: CC BY

Cite this

Kaur, P., Blücher, V., Jalota, R., Moussallem, D., Ngomo, A. C. N., & Usbeck, R. (2019). Offline question answering over linked data using limited resources. In M. Alam, R. Usbeck, T. Pellegrini, H. Sack, & Y. Sure-Vetter (Eds.), SEMPDS 2019: Posters and Demos at SEMANTiCS 2019 (Vol. 2451). (CEUR Workshop Proceedings; Vol. 2451). Sun Site Central Europe (RWTH Aachen University). https://ceur-ws.org/Vol-2451/paper-15.pdf

@inbook{272a2fba22e64597b04c7b5dd0cf472d,

title = "Offline question answering over linked data using limited resources",

abstract = "Question Answering over Linked Data provides concise information to the user from a natural language request instead of flooding them with documents. However, the accessibility of Linked Data resources, e.g., SPARQL endpoints, is bound to an online connection. We present OQA, the first offline Question Answering system over Linked Data for mobile devices. We built OQA with the limited resources of an Android mobile device, such as battery power, computational power, or memory consumption in mind. Our OQA system has three main components: 1) question analysis and 2) query generation which identify the type of the question and reform it into a semantically meaningful data structure, i.e., a SPARQL query. Finally, the 3) query execution uses a novel mobile triple store, implemented with RDF4J. Our evaluation suggests that OQA is feasible for daily use in terms of battery consumption and able to answer domain-specific questions with up to 72\% accuracy.",

keywords = "Informatics, Business informatics",

author = "Paramjot Kaur and Vincent Bl{\"u}cher and Rricha Jalota and Diego Moussallem and Ngomo, \{Axel Cyrille Ngonga\} and Ricardo Usbeck",

note = "Publisher Copyright: Copyright {\textcopyright} 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).; 15th International Conference on Semantic Systems, SEMPDS 2019 : The Power of AI and Knowledge Graphs ; Conference date: 09-09-2019 Through 12-09-2019",

year = "2019",

month = sep,

language = "English",

volume = "2451",

series = "CEUR Workshop Proceedings",

publisher = "Sun Site Central Europe (RWTH Aachen University)",

editor = "Mehwish Alam and Ricardo Usbeck and Tassilo Pellegrini and Harald Sack and York Sure-Vetter",

booktitle = "SEMPDS 2019",

address = "Germany",

url = "https://2019.semantics.cc",

}

Kaur, P, Blücher, V, Jalota, R, Moussallem, D, Ngomo, ACN & Usbeck, R 2019, Offline question answering over linked data using limited resources. in M Alam, R Usbeck, T Pellegrini, H Sack & Y Sure-Vetter (eds), SEMPDS 2019: Posters and Demos at SEMANTiCS 2019. vol. 2451, CEUR Workshop Proceedings, vol. 2451, Sun Site Central Europe (RWTH Aachen University), 15th International Conference on Semantic Systems, SEMPDS 2019, Karlsruhe, Baden-Württemberg, Germany, 09.09.19. <https://ceur-ws.org/Vol-2451/paper-15.pdf>

Offline question answering over linked data using limited resources. / Kaur, Paramjot; Blücher, Vincent; Jalota, Rricha et al.
SEMPDS 2019: Posters and Demos at SEMANTiCS 2019. ed. / Mehwish Alam; Ricardo Usbeck; Tassilo Pellegrini; Harald Sack; York Sure-Vetter. Vol. 2451 Sun Site Central Europe (RWTH Aachen University), 2019. (CEUR Workshop Proceedings; Vol. 2451).

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

TY - CHAP

T1 - Offline question answering over linked data using limited resources

AU - Kaur, Paramjot

AU - Blücher, Vincent

AU - Jalota, Rricha

AU - Moussallem, Diego

AU - Ngomo, Axel Cyrille Ngonga

AU - Usbeck, Ricardo

PY - 2019/9

Y1 - 2019/9

N2 - Question Answering over Linked Data provides concise information to the user from a natural language request instead of flooding them with documents. However, the accessibility of Linked Data resources, e.g., SPARQL endpoints, is bound to an online connection. We present OQA, the first offline Question Answering system over Linked Data for mobile devices. We built OQA with the limited resources of an Android mobile device, such as battery power, computational power, or memory consumption in mind. Our OQA system has three main components: 1) question analysis and 2) query generation which identify the type of the question and reform it into a semantically meaningful data structure, i.e., a SPARQL query. Finally, the 3) query execution uses a novel mobile triple store, implemented with RDF4J. Our evaluation suggests that OQA is feasible for daily use in terms of battery consumption and able to answer domain-specific questions with up to 72% accuracy.

AB - Question Answering over Linked Data provides concise information to the user from a natural language request instead of flooding them with documents. However, the accessibility of Linked Data resources, e.g., SPARQL endpoints, is bound to an online connection. We present OQA, the first offline Question Answering system over Linked Data for mobile devices. We built OQA with the limited resources of an Android mobile device, such as battery power, computational power, or memory consumption in mind. Our OQA system has three main components: 1) question analysis and 2) query generation which identify the type of the question and reform it into a semantically meaningful data structure, i.e., a SPARQL query. Finally, the 3) query execution uses a novel mobile triple store, implemented with RDF4J. Our evaluation suggests that OQA is feasible for daily use in terms of battery consumption and able to answer domain-specific questions with up to 72% accuracy.

KW - Informatics

KW - Business informatics

UR - https://www.scopus.com/pages/publications/85072892371

M3 - Article in conference proceedings

AN - SCOPUS:85072892371

VL - 2451

T3 - CEUR Workshop Proceedings

BT - SEMPDS 2019

A2 - Alam, Mehwish

A2 - Usbeck, Ricardo

A2 - Pellegrini, Tassilo

A2 - Sack, Harald

A2 - Sure-Vetter, York

PB - Sun Site Central Europe (RWTH Aachen University)

T2 - 15th International Conference on Semantic Systems, SEMPDS 2019

Y2 - 9 September 2019 through 12 September 2019

ER -

Offline question answering over linked data using limited resources

Abstract

Bibliographical note

Research areas and keywords

Access to Document

Fingerprint

Cite this