Cargando…
Document vectorization method using network information of words
We propose a new method for vectorizing a document using the relational characteristics of the words in the document. For the relational characteristics, we use two types of relational information of a word: 1) the centrality measures of the word and 2) the number of times that the word is used with...
Autor principal: | Lee, Sang Yup |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6638850/ https://www.ncbi.nlm.nih.gov/pubmed/31318881 http://dx.doi.org/10.1371/journal.pone.0219389 |
Ejemplares similares
-
Exploiting domain information for Word Sense Disambiguation of medical documents
por: Stevenson, Mark, et al.
Publicado: (2011) -
Document Network Projection in Pretrained Word Embedding Space
por: Gourru, Antoine, et al.
Publicado: (2020) -
Inductive Document Network Embedding with Topic-Word Attention
por: Brochier, Robin, et al.
Publicado: (2020) -
Creating research and scientific documents using Microsoft Word
por: Mamishev, Alexander, et al.
Publicado: (2013) -
Word 2003 document automation with VBA, XML, XSLT, and Smart Documents
por: Driza, Scott
Publicado: (2005)