Standard
EARL: Joint entity and relation linking for question answering over knowledge graphs. / Dubey, Mohnish
; Banerjee, Debayan; Chaudhuri, Debanjan et al.
The Semantic Web – ISWC 2018: 17th International Semantic Web Conference, Monterey, CA, USA, October 8–12, 2018 : proceedings. Hrsg. / Denny Vrandecic; Kalina Bontcheva; Mari Carmen Suárez-Figueroa; Valentina Presutti; Irene Celino; Marta Sabou; Lucie-Aimee Kaffee; Elena Simperl. Band 1 Cham: Springer Schweiz, 2018. S. 108-126 (Lecture Notes in Computer Science ; Band 11136 LNCS).
Publikation: Beiträge in Sammelwerken › Aufsätze in Konferenzbänden › Forschung › begutachtet
Harvard
Dubey, M
, Banerjee, D, Chaudhuri, D & Lehmann, J 2018,
EARL: Joint entity and relation linking for question answering over knowledge graphs. in D Vrandecic, K Bontcheva, MC Suárez-Figueroa, V Presutti, I Celino, M Sabou, L-A Kaffee & E Simperl (Hrsg.),
The Semantic Web – ISWC 2018: 17th International Semantic Web Conference, Monterey, CA, USA, October 8–12, 2018 : proceedings. Bd. 1, Lecture Notes in Computer Science , Bd. 11136 LNCS, Springer Schweiz, Cham, S. 108-126, 17th International Semantic Web Conference - ISWC 2018, Monterey, California, USA / Vereinigte Staaten,
08.10.18.
https://doi.org/10.1007/978-3-030-00671-6_7APA
Dubey, M.
, Banerjee, D., Chaudhuri, D., & Lehmann, J. (2018).
EARL: Joint entity and relation linking for question answering over knowledge graphs. In D. Vrandecic, K. Bontcheva, M. C. Suárez-Figueroa, V. Presutti, I. Celino, M. Sabou, L.-A. Kaffee, & E. Simperl (Hrsg.),
The Semantic Web – ISWC 2018: 17th International Semantic Web Conference, Monterey, CA, USA, October 8–12, 2018 : proceedings (Band 1, S. 108-126). (Lecture Notes in Computer Science ; Band 11136 LNCS). Springer Schweiz.
https://doi.org/10.1007/978-3-030-00671-6_7Vancouver
Dubey M
, Banerjee D, Chaudhuri D, Lehmann J.
EARL: Joint entity and relation linking for question answering over knowledge graphs. in Vrandecic D, Bontcheva K, Suárez-Figueroa MC, Presutti V, Celino I, Sabou M, Kaffee LA, Simperl E, Hrsg., The Semantic Web – ISWC 2018: 17th International Semantic Web Conference, Monterey, CA, USA, October 8–12, 2018 : proceedings. Band 1. Cham: Springer Schweiz. 2018. S. 108-126. (Lecture Notes in Computer Science ). doi: 10.1007/978-3-030-00671-6_7
Bibtex
@inbook{4d171965051b4ba4a5aa8e9fba6ac532,
title = "EARL: Joint entity and relation linking for question answering over knowledge graphs",
abstract = "Many question answering systems over knowledge graphs rely on entity and relation linking components in order to connect the natural language input to the underlying knowledge graph. Traditionally, entity linking and relation linking have been performed either as dependent sequential tasks or as independent parallel tasks. In this paper, we propose a framework called EARL, which performs entity linking and relation linking as a joint task. EARL implements two different solution strategies for which we provide a comparative analysis in this paper: The first strategy is a formalisation of the joint entity and relation linking tasks as an instance of the Generalised Travelling Salesman Problem (GTSP). In order to be computationally feasible, we employ approximate GTSP solvers. The second strategy uses machine learning in order to exploit the connection density between nodes in the knowledge graph. It relies on three base features and re-ranking steps in order to predict entities and relations. We compare the strategies and evaluate them on a dataset with 5000 questions. Both strategies significantly outperform the current state-of-the-art approaches for entity and relation linking.",
keywords = "Entity linking, GTSP, Question answering, Relation linking, Informatics",
author = "Mohnish Dubey and Debayan Banerjee and Debanjan Chaudhuri and Jens Lehmann",
note = "Funding Information: Acknowledgement. This work is supported by the funding received from the EU H2020 projects WDAqua (ITN, GA. 642795) and HOBBIT (GA. 688227). Funding Information: This work is supported by the funding received from the EU H2020 projects WDAqua (ITN, GA. 642795) and HOBBIT (GA. 688227). Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2018.; 17th International Semantic Web Conference - ISWC 2018, ISWC 2018 ; Conference date: 08-10-2018 Through 12-10-2018",
year = "2018",
month = sep,
day = "18",
doi = "10.1007/978-3-030-00671-6_7",
language = "English",
isbn = "978-3-030-00670-9",
volume = "1",
series = "Lecture Notes in Computer Science ",
publisher = "Springer Schweiz",
pages = "108--126",
editor = "Denny Vrandecic and Kalina Bontcheva and Su{\'a}rez-Figueroa, {Mari Carmen} and Valentina Presutti and Irene Celino and Marta Sabou and Lucie-Aimee Kaffee and Elena Simperl",
booktitle = "The Semantic Web – ISWC 2018",
address = "Switzerland",
url = "http://iswc2018.semanticweb.org/",
}
RIS
TY - CHAP
T1 - EARL
T2 - 17th International Semantic Web Conference - ISWC 2018
AU - Dubey, Mohnish
AU - Banerjee, Debayan
AU - Chaudhuri, Debanjan
AU - Lehmann, Jens
N1 - Conference code: 17
PY - 2018/9/18
Y1 - 2018/9/18
N2 - Many question answering systems over knowledge graphs rely on entity and relation linking components in order to connect the natural language input to the underlying knowledge graph. Traditionally, entity linking and relation linking have been performed either as dependent sequential tasks or as independent parallel tasks. In this paper, we propose a framework called EARL, which performs entity linking and relation linking as a joint task. EARL implements two different solution strategies for which we provide a comparative analysis in this paper: The first strategy is a formalisation of the joint entity and relation linking tasks as an instance of the Generalised Travelling Salesman Problem (GTSP). In order to be computationally feasible, we employ approximate GTSP solvers. The second strategy uses machine learning in order to exploit the connection density between nodes in the knowledge graph. It relies on three base features and re-ranking steps in order to predict entities and relations. We compare the strategies and evaluate them on a dataset with 5000 questions. Both strategies significantly outperform the current state-of-the-art approaches for entity and relation linking.
AB - Many question answering systems over knowledge graphs rely on entity and relation linking components in order to connect the natural language input to the underlying knowledge graph. Traditionally, entity linking and relation linking have been performed either as dependent sequential tasks or as independent parallel tasks. In this paper, we propose a framework called EARL, which performs entity linking and relation linking as a joint task. EARL implements two different solution strategies for which we provide a comparative analysis in this paper: The first strategy is a formalisation of the joint entity and relation linking tasks as an instance of the Generalised Travelling Salesman Problem (GTSP). In order to be computationally feasible, we employ approximate GTSP solvers. The second strategy uses machine learning in order to exploit the connection density between nodes in the knowledge graph. It relies on three base features and re-ranking steps in order to predict entities and relations. We compare the strategies and evaluate them on a dataset with 5000 questions. Both strategies significantly outperform the current state-of-the-art approaches for entity and relation linking.
KW - Entity linking
KW - GTSP
KW - Question answering
KW - Relation linking
KW - Informatics
UR - http://www.scopus.com/inward/record.url?scp=85054809353&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-00671-6_7
DO - 10.1007/978-3-030-00671-6_7
M3 - Article in conference proceedings
AN - SCOPUS:85054809353
SN - 978-3-030-00670-9
VL - 1
T3 - Lecture Notes in Computer Science
SP - 108
EP - 126
BT - The Semantic Web – ISWC 2018
A2 - Vrandecic, Denny
A2 - Bontcheva, Kalina
A2 - Suárez-Figueroa, Mari Carmen
A2 - Presutti, Valentina
A2 - Celino, Irene
A2 - Sabou, Marta
A2 - Kaffee, Lucie-Aimee
A2 - Simperl, Elena
PB - Springer Schweiz
CY - Cham
Y2 - 8 October 2018 through 12 October 2018
ER -
