Zero-Shot Cross-Lingual Transfer
71 papers with code • 2 benchmarks • 4 datasets
Libraries
Use these libraries to find Zero-Shot Cross-Lingual Transfer models and implementations
XTREME
IGLUE
MaRVL
xSID
Most implemented papers
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.
Finding Universal Grammatical Relations in Multilingual BERT
ethanachi/multilingual-probing-visualization
•
•
ACL 2020
Recent work has found evidence that Multilingual BERT (mBERT), a transformer-based multilingual masked language model, is capable of zero-shot cross-lingual transfer, suggesting that some aspects of its representations are shared cross-lingually.
Inducing Language-Agnostic Multilingual Representations
AIPHES/Language-Agnostic-Contextualized-Encoders
•
•
Joint Conference on Lexical and Computational Semantics 2021
Cross-lingual representations have the potential to make NLP techniques available to the vast majority of languages in the world.
FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding
yuwfan/FILTER
•
•
During inference, the model makes predictions based on the text input in the target language and its translation in the source language.
The Multilingual Amazon Reviews Corpus
mojave-pku/uniprompt
•
•
EMNLP 2020
We present the Multilingual Amazon Reviews Corpus (MARC), a large-scale collection of Amazon reviews for multilingual text classification.
XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization
pasinit/xlwic-runs
•
•
EMNLP 2020
The ability to correctly model distinct meanings of a word is crucial for the effectiveness of semantic representation techniques.
Model Selection for Cross-Lingual Transfer
edchengg/model_selection
•
•
EMNLP 2021
Transformers that are pre-trained on multilingual corpora, such as, mBERT and XLM-RoBERTa, have achieved impressive cross-lingual transfer capabilities.
First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT
benjamin-mlr/first-align-then-predict
•
•
EACL 2021
Such transfer emerges by fine-tuning on a task of interest in one language and evaluating on a distinct language, not seen during the fine-tuning.
Beyond the English Web: Zero-Shot Cross-Lingual and Lightweight Monolingual Classification of Registers
We explore cross-lingual transfer of register classification for web documents.
Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation
fe1ixxu/ZeroShot-CrossLing-Parsing
•
•
EACL (AdaptNLP) 2021
Linear embedding transformation has been shown to be effective for zero-shot cross-lingual transfer tasks and achieve surprisingly promising results.
