Cargando…
Comparison of Structural Parsers and Neural Language Models as Surprisal Estimators
Expectation-based theories of sentence processing posit that processing difficulty is determined by predictability in context. While predictability quantified via surprisal has gained empirical support, this representation-agnostic measure leaves open the question of how to best approximate the huma...
Autores principales: | Oh, Byung-Doh, Clark, Christian, Schuler, William |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8929193/ https://www.ncbi.nlm.nih.gov/pubmed/35310956 http://dx.doi.org/10.3389/frai.2022.777963 |
Ejemplares similares
-
Schrödinger's tree—On syntax and neural language models
por: Kulmizev, Artur, et al.
Publicado: (2022) -
The neural machine translation models for the low-resource Kazakh–English language pair
por: Karyukin, Vladislav, et al.
Publicado: (2023) -
Information Theoretic Characterization of Uncertainty Distinguishes Surprise From Accuracy Signals in the Brain
por: Loued-Khenissi, Leyla, et al.
Publicado: (2020) -
Extracting relations from texts using vector language models and a neural network classifier
por: Shishaev, Maksim, et al.
Publicado: (2023) -
AlphaZe∗∗: AlphaZero-like baselines for imperfect information games are surprisingly strong
por: Blüml, Jannis, et al.
Publicado: (2023)