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

Revealing entities from textual documents using a hybrid approach

Plu, Julien; Rizzo, Giuseppe; Troncy, Raphaël

DBPEDIA, 3rd International Workshop on NLP & DBpedia, October 11-12, 2015, Bethlehem, Pennsylvania, USA

The tasks of entity extraction, recognition, and linking are largely affected by the nature of the textual documents being analyzed. In fact, a lot of research efforts have focused on improving each task for both formal text (such as newswire documents) and for informal text (such as tweets). In this work, we propose a so-called hybrid approach that aims to be agnostic of the document type. Two datasets, namely the #Micropost2014 NEEL corpus and the OKE2015 test dataset, are used to benchmark the performance of our approach. The experimental results show that the approach presented in this paper outperforms the state-of-the-art systems on OKE2015 dataset and provides good results for the #Micropost2014 dataset. 

Document Bibtex

Titre:Revealing entities from textual documents using a hybrid approach
Mots Clés:Entity Recognition, Entity Linking, Entity Filtering, Entity Resolution, Micropost, Formal Text
Type:Conférence
Langue:English
Ville:Bethlehem
Pays:ÉTATS-UNIS
Date:
Département:Data Science
Eurecom ref:4677
Copyright: © Springer. Personal use of this material is permitted. The definitive version of this paper was published in DBPEDIA, 3rd International Workshop on NLP & DBpedia, October 11-12, 2015, Bethlehem, Pennsylvania, USA and is available at :
Bibtex: @inproceedings{EURECOM+4677, year = {2015}, title = {{R}evealing entities from textual documents using a hybrid approach}, author = {{P}lu, {J}ulien and {R}izzo, {G}iuseppe and {T}roncy, {R}apha{\"e}l }, booktitle = {{DBPEDIA}, 3rd {I}nternational {W}orkshop on {NLP} \& {DB}pedia, {O}ctober 11-12, 2015, {B}ethlehem, {P}ennsylvania, {USA}}, address = {{B}ethlehem, {\'{E}}{TATS}-{UNIS}}, month = {10}, url = {http://www.eurecom.fr/publication/4677} }
Voir aussi: