Low-resource languages: A review of past work and future challenges

A Magueresse, V Carles, E Heetderks - arXiv preprint arXiv:2006.07264, 2020 - arxiv.org
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 …

Morphological Processing of Low-Resource Languages: Where We Are and What's Next

A Wiemerslage, M Silfverberg, C Yang… - arXiv preprint arXiv …, 2022 - arxiv.org
Automatic morphological processing can aid downstream natural language processing
applications, especially for low-resource languages, and assist language documentation …

The SIGMORPHON 2020 shared task on unsupervised morphological paradigm completion

K Kann, A McCarthy, G Nicolai, M Hulden - arXiv preprint arXiv …, 2020 - arxiv.org
In this paper, we describe the findings of the SIGMORPHON 2020 shared task on
unsupervised morphological paradigm completion (SIGMORPHON 2020 Task 2), a novel …

The paradigm discovery problem

A Erdmann, M Elsner, S Wu, R Cotterell… - arXiv preprint arXiv …, 2020 - arxiv.org
This work treats the paradigm discovery problem (PDP), the task of learning an inflectional
morphological system from unannotated sentences. We formalize the PDP and develop …

[PDF][PDF] Computational models of morphological learning

J Kodner - Oxford Research Encyclopedia of Linguistics, 2022 - lingbuzz.net
The most elucidating computational model of morphology learning from the perspective of a
linguist is one that learns morphology like a child does, that is, on child-like input and along …

Findings of the sigmorphon 2021 shared task on unsupervised morphological paradigm clustering

A Wiemerslage, AD McCarthy, A Erdmann… - Proceedings of the …, 2021 - aclanthology.org
We describe the second SIGMORPHON shared task on unsupervised morphology: the goal
of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm …

Evaluating Cross Lingual Transfer for Morphological Analysis: a Case Study of Indian Languages

S Pawar, P Bhattacharyya… - Proceedings of the 20th …, 2023 - aclanthology.org
Recent advances in pretrained multilingual models such as Multilingual T5 (mT5) have
facilitated cross-lingual transfer by learning shared representations across languages …

Neural Arabic singular-to-plural conversion using a pretrained Character-BERT and a fused transformer

A Radman, M Atros, R Duwairi - Natural Language Engineering, 2023 - cambridge.org
Morphological re-inflection generation is one of the most challenging tasks in the natural
language processing (NLP) domain, especially with morphologically rich, low-resource …

The Zeno's Paradox ofLow-Resource'Languages

HH Nigatu, AL Tonja, B Rosman, T Solorio… - arXiv preprint arXiv …, 2024 - arxiv.org
The disparity in the languages commonly studied in Natural Language Processing (NLP) is
typically reflected by referring to languages as low vs high-resourced. However, there is …

Machine translation between high-resource languages in a language documentation setting

K Kann, A Ebrahimi, K Stenzel, A Palmer - … International Conference on …, 2022 - par.nsf.gov
Language documentation encompasses translation, typically into the dominant high-
resource language in the region where the target language is spoken. To make data …