Cargando…
Confusion2Vec: towards enriching vector space word representations with representational ambiguities
Word vector representations are a crucial part of natural language processing (NLP) and human computer interaction. In this paper, we propose a novel word vector representation, Confusion2Vec, motivated from the human speech production and perception that encodes representational ambiguity. Humans e...
Autores principales: | Gurunath Shivakumar, Prashanth, Georgiou, Panayiotis |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
PeerJ Inc.
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7924673/ https://www.ncbi.nlm.nih.gov/pubmed/33816848 http://dx.doi.org/10.7717/peerj-cs.195 |
Ejemplares similares
-
Confusion2Vec 2.0: Enriching ambiguous spoken language representations with subwords
por: Gurunath Shivakumar, Prashanth, et al.
Publicado: (2022) -
Persona2vec: a flexible multi-role representations learning framework for graphs
por: Yoon, Jisung, et al.
Publicado: (2021) -
A tale of two lexica: Investigating computational pressures on word representation with neural networks
por: Avcu, Enes, et al.
Publicado: (2023) -
Beyond the Benchmarks: Toward Human-Like Lexical Representations
por: Stevenson, Suzanne, et al.
Publicado: (2022) -
Vector representation based on a supervised codebook for Nepali documents classification
por: Sitaula, Chiranjibi, et al.
Publicado: (2021)