Constructing a word similarity graph from vector based word representation for named entity recognition
College
College of Science
Department/Unit
Mathematics and Statistics Department
Document Type
Conference Proceeding
Source Title
WEBIST 2018 - Proceedings of the 14th International Conference on Web Information Systems and Technologies
First Page
166
Last Page
171
Publication Date
1-1-2018
Abstract
In this paper, we discuss a method for identifying a seed word that would best represent a class of named entities in a graphical representation of words and their similarities. Word networks, or word graphs, are representations of vectorized text where nodes are the words encountered in a corpus, and the weighted edges incident on the nodes represent how similar the words are to each other. Word networks are then divided into communities using the Louvain Method for community detection, then betweenness centrality of each node in each community is computed. The most central node in each community represents the most ideal candidate for a seed word of a named entity group which represents the community. Our results from our bilingual data set show that words with similar lexical content, from either language, belong to the same community. Copyright © 2018 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved
html
Digitial Object Identifier (DOI)
10.5220/0006926201660171
Recommended Citation
Feria, M., Balbin, J. S., & Bautista, F. (2018). Constructing a word similarity graph from vector based word representation for named entity recognition. WEBIST 2018 - Proceedings of the 14th International Conference on Web Information Systems and Technologies, 166-171. https://doi.org/10.5220/0006926201660171
Disciplines
Computer Sciences | Mathematics
Keywords
Linguistics—Graphic methods; Semantics—Mathematical models
Upload File
wf_yes