Low-resource Languages: A Review of Past Work and Future Challenges
arXiv:2006.07264
Abstract
A current problem in NLP is massaging and processing low-resource languages which lack useful training attributes such as supervised data, number of native speakers or experts, etc. This review paper concisely summarizes previous groundbreaking achievements made towards resolving this problem, and analyzes potential improvements in the context of the overall future research direction.
References in corpus (6)
- How multilingual is Multilingual BERT?
- Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation
- Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fields
- Establishing Baselines for Text Classification in Low-Resource Languages
- Towards Zero-resource Cross-lingual Entity Linking
- Unsupervised Morphological Paradigm Completion