Cross-lingual Inflection as a Data Augmentation Method for Parsing

Alberto Muñoz-Ortiz, Carlos Gómez-Rodríguez, and David Vilares. 2022. Cross-lingual Inflection as a Data Augmentation Method for Parsing. In Proceedings of the Third Workshop on Insights from Negative Results in NLP, pages 54–61, Dublin, Ireland. Association for Computational Linguistics.

Resumen

[Absctract]: 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 (RR) treebanks to create cross-lingual (x-inflected) treebanks that resemble the target LR language. We use such inflected treebanks to train parsers in zero- (training on x-inflected treebanks) and few-shot (training on x-inflected and target language treebanks) setups. The results show that the method sometimes improves the baselines, but not consistently.

Palabras clave

Cross-lingual inflection
Morphological Inflection
Data augmentation
Dependency parsing
Low-resource languages
Syntactic data augmentation

Descripción

Held 26 May 2022, Dublin, Ireland.

Versión del editor

https://aclanthology.org/2022.insights-1.7/

Derechos

Atribución 3.0 España