About

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 METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

Greatest papers with code

Unsupervised Cross-lingual Representation Learning at Scale

ACL 2020 huggingface/transformers

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.

CROSS-LINGUAL TRANSFER LANGUAGE MODELLING REPRESENTATION LEARNING

InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training

15 Jul 2020microsoft/unilm

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.

CROSS-LINGUAL TRANSFER LANGUAGE MODELLING

XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalisation

ICML 2020 google-research/xtreme

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.

CROSS-LINGUAL TRANSFER

XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation

15 Apr 2021google-research/xtreme

Machine learning has brought striking advances in multilingual natural language processing capabilities over the past year.

CROSS-LINGUAL TRANSFER NATURAL LANGUAGE UNDERSTANDING TRANSFER LEARNING

XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization

24 Mar 2020google-research/xtreme

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.

CROSS-LINGUAL TRANSFER

Don't Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja

IJCNLP 2019 shin285/KOMORAN

We propose a simple yet effective approach for improving Korean word representations using additional linguistic annotation (i. e. Hanja).

CROSS-LINGUAL TRANSFER TRANSFER LEARNING

Cross-Lingual Natural Language Generation via Pre-Training

23 Sep 2019CZWin32768/xnlg

In this work we focus on transferring supervision signals of natural language generation (NLG) tasks between multiple languages.

ABSTRACTIVE TEXT SUMMARIZATION CROSS-LINGUAL TRANSFER MACHINE TRANSLATION QUESTION GENERATION TEXT GENERATION

Word Alignment by Fine-tuning Embeddings on Parallel Corpora

20 Jan 2021neulab/awesome-align

In addition, we demonstrate that we are able to train multilingual word aligners that can obtain robust performance on different language pairs.

CROSS-LINGUAL TRANSFER WORD ALIGNMENT WORD EMBEDDINGS

UniTrans: Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data

15 Jul 2020microsoft/vert-papers

Prior works in cross-lingual named entity recognition (NER) with no/little labeled data fall into two primary categories: model transfer based and data transfer based methods.

CROSS-LINGUAL NER KNOWLEDGE DISTILLATION NAMED ENTITY RECOGNITION