Cross-lingual Inflection as a Data Augmentation Method for Parsing

Alberto Muñoz-Ortiz, Carlos Gómez-Rodríguez, David Vilares


Abstract
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.
Anthology ID:
2022.insights-1.7
Volume:
Proceedings of the Third Workshop on Insights from Negative Results in NLP
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Shabnam Tafreshi, João Sedoc, Anna Rogers, Aleksandr Drozd, Anna Rumshisky, Arjun Akula
Venue:
insights
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
54–61
Language:
URL:
https://aclanthology.org/2022.insights-1.7
DOI:
10.18653/v1/2022.insights-1.7
Bibkey:
Cite (ACL):
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.
Cite (Informal):
Cross-lingual Inflection as a Data Augmentation Method for Parsing (Muñoz-Ortiz et al., insights 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.insights-1.7.pdf
Video:
 https://aclanthology.org/2022.insights-1.7.mp4