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

Context-enhanced adaptive entity linking

Ilievski, Filip; Rizzo, Giuseppe; van Erp, Marieke; Plu, Julien; Troncy, Raphaël

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

More and more knowledge bases are publicly available as linked data. Since these knowledge bases contain structured descriptions of real-world entities, they can be exploited by entity linking systems that anchor entity mentions from text to the most relevant resources describing those entities. In this paper, we investigate adaptation of the entity linking task using contextual knowledge. The key intuition is that entity linking can be customized depending on the textual content, as well as on the application that would make use of the extracted information. We present an adaptive approach that relies on contextual knowledge from text to enhance the performance of ADEL, a hybrid linguistic and graph-based entity linking system. We evaluate our approach on a domain-specific corpus consisting of annotated WikiNews articles.

Document Bibtex

Titre:Context-enhanced adaptive entity linking
Mots Clés:Adaptive, Contextual, Entity Linking, Knowledge Extraction
Département:Data Science
Eurecom ref:4845
Copyright: ELRA
Bibtex: @inproceedings{EURECOM+4845, year = {2016}, title = {{C}ontext-enhanced adaptive entity linking}, author = {{I}lievski, {F}ilip and {R}izzo, {G}iuseppe and van {E}rp, {M}arieke and {P}lu, {J}ulien and {T}roncy, {R}apha{\"e}l}, 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 = {} }
Voir aussi: