Zero-Shot Cross-Lingual Transfer
38 papers with code • 2 benchmarks • 4 datasets
LibrariesUse these libraries to find Zero-Shot Cross-Lingual Transfer models and implementations
We introduce an architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts.
Pretrained contextual representation models (Peters et al., 2018; Devlin et al., 2018) have pushed forward the state-of-the-art on many NLP tasks.
Recent progress in self-training, self-supervised pretraining and unsupervised learning enabled well performing speech recognition systems without any labeled data.
The design of widespread vision-and-language datasets and pre-trained encoders directly adopts, or draws inspiration from, the concepts and images of ImageNet.
Our adversarial post-specialization method propagates the external lexical knowledge to the full distributional space.
In this approach, a linear transformation is learned from contextual word alignments to align the contextualized embeddings independently trained in different languages.
In this work we focus on transferring supervision signals of natural language generation (NLG) tasks between multiple languages.
We show that this challenging setup can be approached using meta-learning, where, in addition to training a source language model, another model learns to select which training instances are the most beneficial to the first.