1 |
mSLAM: Massively multilingual joint pre-training for speech and text ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Larger-Scale Transformers for Multilingual Masked Language Modeling ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Unsupervised Cross-lingual Representation Learning for Speech Recognition ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Multilingual Speech Translation with Efficient Finetuning of Pretrained Models ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Unsupervised Cross-lingual Representation Learning at Scale ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Emerging Cross-lingual Structure in Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
What you can cram into a single vector: Probing sentence embeddings for linguistic properties ...
|
|
|
|
Abstract:
Although much effort has recently been devoted to training high-quality sentence embeddings, we still have a poor understanding of what they are capturing. "Downstream" tasks, often based on sentence classification, are commonly used to evaluate the quality of sentence representations. The complexity of the tasks makes it however difficult to infer what kind of information is present in the representations. We introduce here 10 probing tasks designed to capture simple linguistic features of sentences, and we use them to study embeddings generated by three different encoders trained in eight distinct ways, uncovering intriguing properties of both encoders and training methods. ... : ACL 2018 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1805.01070 https://dx.doi.org/10.48550/arxiv.1805.01070
|
|
BASE
|
|
Hide details
|
|
|
|