Analysing the effects of transfer learning on low-resourced named entity recognition performance

Michael Beukman

Keywords: Named Entity Recognition, Analysis, Transfer Learning

TL;DR: We analyse the effect of using different language-adaptively fine-tuned models on NER transfer performance and model embeddings.

Abstract:

Transfer learning has led to large gains in performance for nearly all NLP tasks while making downstream models easier and faster to train. This has also been extended to low-resourced languages, with some success. We investigate the properties of transfer learning between 10 low-resourced languages, from the perspective of a named entity recognition task, specifically how much adaptive fine-tuning improves performance, the efficacy of zero-shot transfer as well as the effect of learning on the contextual embeddings computed from the model. Our results give some insight into zero-shot performance as well as the impact of different training schemes and data overlap between the training and testing languages. Particularly, we find that models with the best generalisation to other languages suffer in individual language performance, while models that perform well on a single language often do so at the expense of generalising to others.
In the interest of reproducibility, we publicly release our source code and models.