A taxonomy and review of generalization research in NLP

D Hupkes, M Giulianelli, V Dankers, M Artetxe… - Nature Machine …, 2023 - nature.com
The ability to generalize well is one of the primary desiderata for models of natural language
processing (NLP), but what 'good generalization'entails and how it should be evaluated is …

NusaCrowd: Open source initiative for Indonesian NLP resources

S Cahyawijaya, H Lovenia, AF Aji… - Findings of the …, 2023 - aclanthology.org
We present NusaCrowd, a collaborative initiative to collect and unify existing resources for
Indonesian languages, including opening access to previously non-public resources …

State-of-the-art generalisation research in NLP: a taxonomy and review

D Hupkes, M Giulianelli, V Dankers, M Artetxe… - arxiv preprint arxiv …, 2022 - arxiv.org
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …

One country, 700+ languages: NLP challenges for underrepresented languages and dialects in Indonesia

AF Aji, GI Winata, F Koto, S Cahyawijaya… - arxiv preprint arxiv …, 2022 - arxiv.org
NLP research is impeded by a lack of resources and awareness of the challenges presented
by underrepresented languages and dialects. Focusing on the languages spoken in …

Hints on the data for language modeling of synthetic languages with transformers

R Zevallos, N Bel - Proceedings of the 61st Annual Meeting of the …, 2023 - aclanthology.org
Abstract Language Models (LM) are becoming more and more useful for providing
representations upon which to train Natural Language Processing applications. However …

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 …

Morphological inflection: A reality check

J Kodner, S Payne, S Khalifa, Z Liu - arxiv preprint arxiv:2305.15637, 2023 - arxiv.org
Morphological inflection is a popular task in sub-word NLP with both practical and cognitive
applications. For years now, state-of-the-art systems have reported high, but also highly …

Morphology without borders: Clause-level morphology

O Goldman, R Tsarfaty - Transactions of the Association for …, 2022 - direct.mit.edu
Morphological tasks use large multi-lingual datasets that organize words into inflection
tables, which then serve as training and evaluation data for various tasks. However, a closer …

SIGMORPHON–UniMorph 2022 shared task 0: generalization and typologically diverse morphological inflection

J Kodner, S Khalifa, K Batsuren… - … of the 19th …, 2022 - research-collection.ethz.ch
The 2022 SIGMORPHON–UniMorph shared task on large scale morphological inflection
generation included a wide range of typologically diverse languages: 33 languages from 11 …

Re-Evaluating the Evaluation of Neural Morphological Inflection Models

J Kodner, S Khalifa, SRB Payne… - Proceedings of the Annual …, 2023 - escholarship.org
Computational models of morphology acquisition have played a central role in debates over
the nature of morphological representations. The apparent success of recent artificial neural …