Assessment of Pre-Trained Models Across Languages and Grammars
A Muñoz-Ortiz, D Vilares… - arXiv preprint arXiv …, 2023 - arxiv.org
We present an approach for assessing how multilingual large language models (LLMs)
learn syntax in terms of multi-formalism syntactic structures. We aim to recover constituent …
learn syntax in terms of multi-formalism syntactic structures. We aim to recover constituent …
Dependency Graph Parsing as Sequence Labeling
Various linearizations have been proposed to cast syntactic dependency parsing as
sequence labeling. However, these approaches do not support more complex graph-based …
sequence labeling. However, these approaches do not support more complex graph-based …
The Fragility of Multi-Treebank Parsing Evaluation
I Alonso-Alonso, D Vilares… - arXiv preprint arXiv …, 2022 - arxiv.org
Treebank selection for parsing evaluation and the spurious effects that might arise from a
biased choice have not been explored in detail. This paper studies how evaluating on a …
biased choice have not been explored in detail. This paper studies how evaluating on a …
Parsing linearizations appreciate PoS tags-but some are fussy about errors
A Muñoz-Ortiz, M Anderson, D Vilares… - arXiv preprint arXiv …, 2022 - arxiv.org
PoS tags, once taken for granted as a useful resource for syntactic parsing, have become
more situational with the popularization of deep learning. Recent work on the impact of PoS …
more situational with the popularization of deep learning. Recent work on the impact of PoS …
From Tokens to Trees: Mapping Syntactic Structures in the Deserts of Data-Scarce Languages
D Vilares, A Muñoz Ortiz - CEUR Workshop 2024, 2024 - ruc.udc.es
Low-resource learning in natural language processing focuses on developing effective
resources, tools, and technologies for languages that are less popular within the industry …
resources, tools, and technologies for languages that are less popular within the industry …
Cross-lingual Inflection as a Data Augmentation Method for Parsing
A Muñoz-Ortiz, C Gómez-Rodríguez… - arXiv preprint arXiv …, 2022 - arxiv.org
We propose a morphology-based method for low-resource (LR) dependency parsing. We
train a morphological inflector for target LR languages, and apply it to related rich-resource …
train a morphological inflector for target LR languages, and apply it to related rich-resource …
Clasificación de género en espacios multi-dimensionales: modelos neuronales y la influencia de la información sintáctica
IM Veiga Menéndez - 2023 - ruc.udc.es
El lenguaje es utilizado por los humanos como herramienta de comunicación, pero también
como vehículo para expresar sus emociones y reflejar su identidad. Diversos factores como …
como vehículo para expresar sus emociones y reflejar su identidad. Diversos factores como …
Dependency parsing as sequence labeling for low-resource languages
A Muñoz Ortiz - 2021 - e-spacio.uned.es
El procesamiento de lenguaje natural (PLN) ha experimentado claros avances en los
últimos años. Sin embargo, la mayoría de mejoras y estudios se han centrado en un selecto …
últimos años. Sin embargo, la mayoría de mejoras y estudios se han centrado en un selecto …