Cargando…
A Method of Short Text Representation Fusion with Weighted Word Embeddings and Extended Topic Information
Short text representation is one of the basic and key tasks of NLP. The traditional method is to simply merge the bag-of-words model and the topic model, which may lead to the problem of ambiguity in semantic information, and leave topic information sparse. We propose an unsupervised text representa...
Autores principales: | Liu, Wenfu, Pang, Jianmin, Du, Qiming, Li, Nan, Yang, Shudan |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8839561/ https://www.ncbi.nlm.nih.gov/pubmed/35161808 http://dx.doi.org/10.3390/s22031066 |
Ejemplares similares
-
A Topic Recognition Method of News Text Based on Word Embedding Enhancement
por: Du, Qiming, et al.
Publicado: (2022) -
Investigating the Efficient Use of Word Embedding with Neural-Topic Models for Interpretable Topics from Short Texts
por: Murakami, Riki, et al.
Publicado: (2022) -
TextNetTopics: Text Classification Based Word Grouping as Topics and Topics’ Scoring
por: Yousef, Malik, et al.
Publicado: (2022) -
A Method of Short Text Representation Based on the Feature Probability Embedded Vector
por: Zhou, Wanting, et al.
Publicado: (2019) -
Short text topic modelling using local and global word-context semantic correlation
por: Kinariwala, Supriya, et al.
Publicado: (2023)