1 |
XTREME-S: Evaluating Cross-lingual Speech Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
MasakhaNER: Named entity recognition for African languages
|
|
|
|
In: EISSN: 2307-387X ; Transactions of the Association for Computational Linguistics ; https://hal.inria.fr/hal-03350962 ; Transactions of the Association for Computational Linguistics, The MIT Press, 2021, ⟨10.1162/tacl⟩ (2021)
|
|
BASE
|
|
Show details
|
|
5 |
Charformer: Fast Character Transformers via Gradient-based Subword Tokenization ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Efficient Test Time Adapter Ensembling for Low-resource Language Varieties ...
|
|
|
|
Abstract:
Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models. Specialized language and task adapters have recently been proposed to facilitate cross-lingual transfer of multilingual pretrained models (Pfeiffer et al., 2020b). However, this approach requires training a separate language adapter for every language one wishes to support, which can be impractical for languages with limited data. An intuitive solution is to use a related language adapter for the new language variety, but we observe that this solution can lead to sub-optimal performance. In this paper, we aim to improve the robustness of language adapters to uncovered languages without training new adapters. We find that ensembling multiple existing language adapters makes the fine-tuned model significantly more robust to other language varieties not included in these adapters. Building upon this observation, we propose Entropy Minimized Ensemble of Adapters (EMEA), a method that optimizes the ensemble weights ... : EMNLP 2021 Findings ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2109.04877 https://arxiv.org/abs/2109.04877
|
|
BASE
|
|
Hide details
|
|
10 |
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
A Call for More Rigor in Unsupervised Cross-lingual Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Rethinking embedding coupling in pre-trained language models ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
UNKs Everywhere: Adapting Multilingual Language Models to New Scripts ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Morphologically Aware Word-Level Translation
|
|
|
|
In: Proceedings of the 28th International Conference on Computational Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
20 |
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|