Syntactically-informed word representations from graph neural network

Most deep language understanding models depend only on word representations, which are mainly based on language modelling derived from a large amount of raw text. These models encode distributional knowledge without considering syntactic structural information, although several studies have shown be...

Descripción completa

Detalles Bibliográficos
Autores principales: Tran, Thy Thy, Miwa, Makoto, Ananiadou, Sophia
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier Science Publishers 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7593959/
https://www.ncbi.nlm.nih.gov/pubmed/33162674
http://dx.doi.org/10.1016/j.neucom.2020.06.070

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7593959/
https://www.ncbi.nlm.nih.gov/pubmed/33162674
http://dx.doi.org/10.1016/j.neucom.2020.06.070

Ejemplares similares