Neural machine translation for low-resource languages: A survey

S Ranathunga, ESA Lee, M Prifti Skenduli… - ACM Computing …, 2023 - dl.acm.org
Neural Machine Translation (NMT) has seen tremendous growth in the last ten years since
the early 2000s and has already entered a mature phase. While considered the most widely …

Scaling data-constrained language models

N Muennighoff, A Rush, B Barak… - Advances in …, 2023 - proceedings.neurips.cc
The current trend of scaling language models involves increasing both parameter count and
training dataset size. Extrapolating this trend suggests that training dataset size may soon be …

Towards multidomain and multilingual abusive language detection: a survey

EW Pamungkas, V Basile, V Patti - Personal and Ubiquitous Computing, 2023 - Springer
Abusive language is an important issue in online communication across different platforms
and languages. Having a robust model to detect abusive instances automatically is a …

Xtreme: A massively multilingual multi-task benchmark for evaluating cross-lingual generalisation

J Hu, S Ruder, A Siddhant, G Neubig… - International …, 2020 - proceedings.mlr.press
Much recent progress in applications of machine learning models to NLP has been driven
by benchmarks that evaluate models across a wide variety of tasks. However, these broad …

Ext5: Towards extreme multi-task scaling for transfer learning

V Aribandi, Y Tay, T Schuster, J Rao, HS Zheng… - ar** session dataset for recommendation and text generation
W **, H Mao, Z Li, H Jiang, C Luo… - Advances in …, 2024 - proceedings.neurips.cc
Modeling customer shop** intentions is a crucial task for e-commerce, as it directly
impacts user experience and engagement. Thus, accurately understanding customer …

Survey of low-resource machine translation

B Haddow, R Bawden, AVM Barone, J Helcl… - Computational …, 2022 - direct.mit.edu
We present a survey covering the state of the art in low-resource machine translation (MT)
research. There are currently around 7,000 languages spoken in the world and almost all …

From zero to hero: On the limitations of zero-shot cross-lingual transfer with multilingual transformers

A Lauscher, V Ravishankar, I Vulić… - arxiv preprint arxiv …, 2020 - arxiv.org
Massively multilingual transformers pretrained with language modeling objectives (eg,
mBERT, XLM-R) have become a de facto default transfer paradigm for zero-shot cross …

Neural unsupervised domain adaptation in NLP---a survey

A Ramponi, B Plank - arxiv preprint arxiv:2006.00632, 2020 - arxiv.org
Deep neural networks excel at learning from labeled data and achieve state-of-the-art
resultson a wide array of Natural Language Processing tasks. In contrast, learning from …

Intermediate-task transfer learning with pretrained models for natural language understanding: When and why does it work?

Y Pruksachatkun, J Phang, H Liu, PM Htut… - arxiv preprint arxiv …, 2020 - arxiv.org
While pretrained models such as BERT have shown large gains across natural language
understanding tasks, their performance can be improved by further training the model on a …