mlsanityData to 7 Oct 2026

Surfing the modeling of PoS taggers in low-resource scenarios

arXiv 2402.02449 ↗First posted 4 Feb 2024cs.CL cs.LGcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 100 references that are in the map. First posted on arXiv 4 Feb 2024.

Builds on

13 of 100 references.

References · 13

  1. 2021Deep Long-Tailed Learning: A Surveycited by 416
  2. 2020A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarioscited by 170
  3. 2018End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classificationcited by 72
  4. 2019Theoretical Issues in Deep Networks: Approximation, Optimization and Generalizationcited by 72
  5. 2018Practical Obstacles to Deploying Active Learningcited by 68
  6. 2021Fast and Informative Model Selection using Learning Curve Cross-Validationcited by 15
  7. 2021Comparing Feature-Engineering and Feature-Learning Approaches for Multilingual Translationese Classificationcited by 13
  8. 2020Reducing Confusion in Active Learning for Part-Of-Speech Taggingcited by 11
  9. 2018Part-of-Speech Tagging on an Endangered Language: a Parallel Griko-Italian Resourcecited by 10
  10. 2020Deep Active Learning for Sequence Labeling Based on Diversity and Uncertainty in Gradientcited by 8
  11. 2020Investigating Bi-LSTM and CRF with POS Tag Embedding for Indonesian Named Entity Taggercited by 5
  12. 2021Analytically Tractable Hidden-States Inference in Bayesian Neural Networkscited by 2
1 more
  1. 2018Building a Kannada POS Tagger Using Machine Learning and Neural Network Modelscited by 1

Built on by

Not cited yet.