# Surfing the modeling of PoS taggers in low-resource scenarios

arXiv: https://arxiv.org/abs/2402.02449 · HTML: https://mlsanity.com/paper/2402.02449/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 100 references that are in the map.
- First posted on arXiv 4 Feb 2024.

## Builds on (most cited first, 13 of 13)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios](https://mlsanity.com/paper/2010.12309/) (2020)
- [End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification](https://mlsanity.com/paper/1811.04719/) (2018)
- [Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization](https://mlsanity.com/paper/1908.09375/) (2019)
- [Practical Obstacles to Deploying Active Learning](https://mlsanity.com/paper/1807.04801/) (2018)
- [Fast and Informative Model Selection using Learning Curve Cross-Validation](https://mlsanity.com/paper/2111.13914/) (2021)
- [Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classification](https://mlsanity.com/paper/2109.07604/) (2021)
- [Reducing Confusion in Active Learning for Part-Of-Speech Tagging](https://mlsanity.com/paper/2011.00767/) (2020)
- [Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resource](https://mlsanity.com/paper/1806.03757/) (2018)
- [Deep Active Learning for Sequence Labeling Based on Diversity and Uncertainty in Gradient](https://mlsanity.com/paper/2011.13570/) (2020)
- [Investigating Bi-LSTM and CRF with POS Tag Embedding for Indonesian Named Entity Tagger](https://mlsanity.com/paper/2009.05687/) (2020)
- [Analytically Tractable Hidden-States Inference in Bayesian Neural Networks](https://mlsanity.com/paper/2107.03759/) (2021)
- [Building a Kannada POS Tagger Using Machine Learning and Neural Network Models](https://mlsanity.com/paper/1808.03175/) (2018)

## Abstract (arXiv)

The recent trend towards the application of deep structured techniques has revealed the limits of huge models in natural language processing. This has reawakened the interest in traditional machine learning algorithms, which have proved still to be competitive in certain contexts, in particular low-resource settings. In parallel, model selection has become an essential task to boost performance at reasonable cost, even more so when we talk about processes involving domains where the training and/or computational resources are scarce. Against this backdrop, we evaluate the early estimation of learning curves as a practical mechanism for selecting the most appropriate model in scenarios characterized by the use of non-deep learners in resource-lean settings. On the basis of a formal approximation model previously evaluated under conditions of wide availability of training and validation resources, we study the reliability of such an approach in a different and much more demanding operationalenvironment. Using as case study the generation of PoS taggers for Galician, a language belonging to the Western Ibero-Romance group, the experimental results are consistent with our expectations.