1 |
Improving Word Translation via Two-Stage Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Emergent Communication Pretraining for Few-Shot Machine Translation ...
|
|
|
|
Abstract:
While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world's languages lack such resources. Hence, we investigate a more radical form of unsupervised knowledge transfer in the absence of linguistic data. In particular, for the first time we pretrain neural networks via emergent communication from referential games. Our key assumption is that grounding communication on images---as a crude approximation of real-world environments---inductively biases the model towards learning natural languages. On the one hand, we show that this substantially benefits machine translation in few-shot settings. On the other hand, this also provides an extrinsic evaluation protocol to probe the properties of emergent languages ex vitro. Intuitively, the closer they are to natural languages, the higher the gains from pretraining on them should be. For instance, ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.2011.00890 https://arxiv.org/abs/2011.00890
|
|
BASE
|
|
Hide details
|
|
3 |
Emergent Communication Pretraining for Few-Shot Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Emergent Communication Pretraining for Few-Shot Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Emergent Communication Pretraining for Few-Shot Machine Translation
|
|
Vulic, Ivan; Ponti, Edoardo; Korhonen, Anna. - : International Committee on Computational Linguistics, 2020. : https://www.aclweb.org/anthology/2020.coling-main.416, 2020. : Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020), 2020
|
|
BASE
|
|
Show details
|
|
|
|