Ecole d'ingénieur et centre de recherche en Sciences du numérique

Evaluating entity linking: An analysis of current benchmark datasets and a roadmap for doing a better job

van Erp, Marieke; Mendes, Pablo; Paulheim, Heiko; Ilievski, Filip; Plu, Julien; Rizzo, Giuseppe; Waitelonis, Joerg

LREC 2016, 10th edition of the Language Resources and Evaluation Conference, 23-28 May 2016, Portoroz, Slovenia

Entity linking has become a popular task in both natural language processing and semantic web communities. However, we find that the benchmark datasets for entity linking tasks do not accurately evaluate entity linking systems. In this paper, we aim to chart the strengths and weaknesses of current benchmark datasets and sketch a roadmap for the community to devise better benchmark datasets.

Document Bibtex

Titre:Evaluating entity linking: An analysis of current benchmark datasets and a roadmap for doing a better job
Mots Clés:entity linking, evaluation, benchmark
Type:Conférence
Langue:English
Ville:Portoroz
Pays:SLOVÉNIE
Date:
Département:Data Science
Eurecom ref:4859
Copyright: ELRA
Bibtex: @inproceedings{EURECOM+4859, year = {2016}, title = {{E}valuating entity linking: {A}n analysis of current benchmark datasets and a roadmap for doing a better job}, author = {van {E}rp, {M}arieke and {M}endes, {P}ablo and {P}aulheim, {H}eiko and {I}lievski, {F}ilip and {P}lu, {J}ulien and {R}izzo, {G}iuseppe and {W}aitelonis, {J}oerg}, booktitle = {{LREC} 2016, 10th edition of the {L}anguage {R}esources and {E}valuation {C}onference, 23-28 {M}ay 2016, {P}ortoroz, {S}lovenia}, address = {{P}ortoroz, {SLOV}{\'{E}}{NIE}}, month = {05}, url = {http://www.eurecom.fr/publication/4859} }
Voir aussi: