Impact of Entity Graphs on Extracting Semantic Relations

Rashedur Rahman 1, 2 Brigitte Grau Sophie Rosset
1 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
2 IRT SystemX - IRT SystemX
Abstract : Relation extraction (RE) between a pair of entity mentions from text is an important and challenging task specially for open domain relations. Generally, relations are extracted based on the lexical and syntactical information at the sentence level. However, global information about known entities has not been explored yet for RE task. In this paper, we propose to extract a graph of entities from the overall corpus and to compute features on this graph that are able to capture some evidences of holding relationships between a pair of entities. The proposed features boost the RE performance significantly when these are combined with some linguistic features.
Document type :
Book sections
Liste complète des métadonnées
https://hal.archives-ouvertes.fr/hal-01802577
Contributor : Rashedur Rahman <>
Submitted on : Tuesday, May 29, 2018 - 2:42:48 PM
Last modification on : Saturday, March 16, 2019 - 1:55:46 AM

Identifiers

  • HAL Id : hal-01802577, version 1

Collections

LIMSI | UNIV-PARIS-SACLAY | IRT-SYSTEMX | SORBONNE-UNIVERSITE

Citation

Rashedur Rahman, Brigitte Grau, Sophie Rosset. Impact of Entity Graphs on Extracting Semantic Relations. Springer. Communications in Computer and Information Science, pp.31-47, 2018, Information Management and Big Data. Revised Selected Papers of SIMBig 2017. 〈hal-01802577〉

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

75

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD