Cross-Lingual Transfer
129 papers with code • 1 benchmarks • 14 datasets
Cross-lingual transfer refers to transfer learning using data and models available for one language for which ample such resources are available (e.g., English) to solve tasks in another, commonly more low-resource, language.
Benchmarks
| Trend | Dataset | Best Model | Paper Title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
MLQA
TyDi QA
PAWS-X
CoNLL 2002
Tatoeba
TyDiQA-GoldP
JESC
Greatest papers with code
Unsupervised Cross-lingual Representation Learning at Scale
huggingface/transformers
•
•
ACL 2020
We also present a detailed empirical analysis of the key factors that are required to achieve these gains, including the trade-offs between (1) positive transfer and capacity dilution and (2) the performance of high and low resource languages at scale.
InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training
microsoft/unilm
•
•
NAACL 2021
In this work, we present an information-theoretic framework that formulates cross-lingual language model pre-training as maximizing mutual information between multilingual-multi-granularity texts.
Ranked #10 on
Zero-Shot Cross-Lingual Transfer
on XTREME
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.
Cross-Lingual Bitext Mining
Cross-Lingual Document Classification
+5
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalisation
google-research/xtreme
•
•
ICML 2020
However, these broad-coverage benchmarks have been mostly limited to English, and despite an increasing interest in multilingual models, a benchmark that enables the comprehensive evaluation of such methods on a diverse range of languages and tasks is still missing.
Ranked #1 on
Zero-Shot Cross-Lingual Transfer
on XTREME
(AVG metric)
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation
google-research/xtreme
•
•
EMNLP 2021
While a sizeable gap to human-level performance remains, improvements have been easier to achieve in some tasks than in others.
XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization
However, these broad-coverage benchmarks have been mostly limited to English, and despite an increasing interest in multilingual models, a benchmark that enables the comprehensive evaluation of such methods on a diverse range of languages and tasks is still missing.
Learning Compact Metrics for MT
google-research/bleurt
•
•
EMNLP 2021
Recent developments in machine translation and multilingual text generation have led researchers to adopt trained metrics such as COMET or BLEURT, which treat evaluation as a regression problem and use representations from multilingual pre-trained models such as XLM-RoBERTa or mBERT.
Don't Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja
We propose a simple yet effective approach for improving Korean word representations using additional linguistic annotation (i. e. Hanja).
Word Alignment by Fine-tuning Embeddings on Parallel Corpora
neulab/awesome-align
•
•
EACL 2021
In addition, we demonstrate that we are able to train multilingual word aligners that can obtain robust performance on different language pairs.
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.
