1 |
On the Representation Collapse of Sparse Mixture of Experts ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoders ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
XLM-E: Cross-lingual Language Model Pre-training via ELECTRA ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training ...
|
|
Chi, Zewen; Dong, Li; Wei, Furu; Yang, Nan; Singhal, Saksham; Wang, Wenhui; Song, Xia; Mao, Xian-Ling; Huang, Heyan; Zhou, Ming. - : arXiv, 2020
|
|
Abstract:
In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts. The unified view helps us to better understand the existing methods for learning cross-lingual representations. More importantly, inspired by the framework, we propose a new pre-training task based on contrastive learning. Specifically, we regard a bilingual sentence pair as two views of the same meaning and encourage their encoded representations to be more similar than the negative examples. By leveraging both monolingual and parallel corpora, we jointly train the pretext tasks to improve the cross-lingual transferability of pre-trained models. Experimental results on several benchmarks show that our approach achieves considerably better performance. The code and pre-trained models are available at https://aka.ms/infoxlm. ... : NAACL 2021 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2007.07834 https://arxiv.org/abs/2007.07834
|
|
BASE
|
|
Hide details
|
|
7 |
XLM-T: Scaling up Multilingual Machine Translation with Pretrained Cross-lingual Transformer Encoders ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|