Zero-Shot Cross-Lingual Transfer
53 papers with code • 2 benchmarks • 4 datasets
Libraries
Use these libraries to find Zero-Shot Cross-Lingual Transfer models and implementations
XTREME
IGLUE
xSID
MaRVL
Most implemented papers
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
facebookresearch/LASER
•
•
TACL 2019
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.
XLM-E: Cross-lingual Language Model Pre-training via ELECTRA
In this paper, we introduce ELECTRA-style tasks to cross-lingual language model pre-training.
Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT
shijie-wu/crosslingual-nlp
•
•
IJCNLP 2019
Pretrained contextual representation models (Peters et al., 2018; Devlin et al., 2018) have pushed forward the state-of-the-art on many NLP tasks.
Simple and Effective Zero-shot Cross-lingual Phoneme Recognition
Recent progress in self-training, self-supervised pretraining and unsupervised learning enabled well performing speech recognition systems without any labeled data.
Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization
cambridgeltl/adversarial-postspec
•
•
EMNLP 2018
Our adversarial post-specialization method propagates the external lexical knowledge to the full distributional space.
Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing
WangYuxuan93/CLBT
•
•
IJCNLP 2019
In this approach, a linear transformation is learned from contextual word alignments to align the contextualized embeddings independently trained in different languages.
Cross-Lingual Natural Language Generation via Pre-Training
CZWin32768/xnlg
•
•
In this work we focus on transferring supervision signals of natural language generation (NLG) tasks between multiple languages.
Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages
cambridgeltl/parameter-factorization
•
•
In this work, we propose a Bayesian generative model for the space of neural parameters.
Zero-Shot Cross-Lingual Transfer with Meta Learning
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.
On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation
AIPHES/ACL20-Reference-Free-MT-Evaluation
•
•
ACL 2020
We systematically investigate a range of metrics based on state-of-the-art cross-lingual semantic representations obtained with pretrained M-BERT and LASER.
