Scalable syntactic inductive biases for neural language models
<p>Natural language has a sequential surface form, although its underlying structure has been argued to be hierarchical and tree-structured in nature, whereby smaller linguistic units like words are recursively composed to form larger ones, such as phrases and sentences. This thesis aims to an...
Autor principal: | Kuncoro, AS |
---|---|
Outros Autores: | Blunsom, P |
Formato: | Thesis |
Idioma: | English |
Publicado em: |
2022
|
Assuntos: |
Registos relacionados
-
Incremental generative models for syntactic and semantic natural language processing
Por: Buys, J
Publicado em: (2017) -
Large Language Models are Not Models of Natural Language: They are Corpus Models
Por: Csaba Veres
Publicado em: (2022-01-01) -
Understanding video through the lens of language
Por: Bain, M
Publicado em: (2023) -
Simplicity and learning to distinguish arguments from modifiers
Por: Leon Bergen, et al.
Publicado em: (2022-12-01) -
Non-parametric deep learning with applications in active learning
Por: Band, N
Publicado em: (2022)