Scalable graph-based method for individual named entity identification

Sammy Khalife, Michalis Vazirgiannis


Abstract
In this paper, we consider the named entity linking (NEL) problem. We assume a set of queries, named entities, that have to be identified within a knowledge base. This knowledge base is represented by a text database paired with a semantic graph, endowed with a classification of entities (ontology). We present state-of-the-art methods in NEL, and propose a new method for individual identification requiring few annotated data samples. We demonstrate its scalability and performance over standard datasets, for several ontology configurations. Our approach is well-motivated for integration in real systems. Indeed, recent deep learning methods, despite their capacity to improve experimental precision, require lots of parameter tuning along with large volume of annotated data.
Anthology ID:
D19-5303
Volume:
Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)
Month:
November
Year:
2019
Address:
Hong Kong
Venue:
TextGraphs
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
17–25
Language:
URL:
https://aclanthology.org/D19-5303
DOI:
10.18653/v1/D19-5303
Bibkey:
Cite (ACL):
Sammy Khalife and Michalis Vazirgiannis. 2019. Scalable graph-based method for individual named entity identification. In Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13), pages 17–25, Hong Kong. Association for Computational Linguistics.
Cite (Informal):
Scalable graph-based method for individual named entity identification (Khalife & Vazirgiannis, TextGraphs 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/D19-5303.pdf