natural-language-processing-8

Zero-Shot Cross-Lingual Transfer

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in zero-shot-cross-lingual-transfer-8

Trend

Dataset

Best Model

Actions

XTREME

MaRVL

Libraries

i

Use these libraries to find zero-shot-cross-lingual-transfer-8 models and implementations

CZWin32768/xnlg

2 papers 128

Datasets

Subtasks

No subtasks available.

Most implemented papers

Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond

Holger Schwenk, Mikel Artetxe•Tue Dec 25 2018

An architecture to learn joint multilingual sentence representations for 93 languages, belonging to more than 30 different families and written in 28 different scripts using a single BiLSTM encoder with a shared byte-pair encoding vocabulary for all languages, coupled with an auxiliary decoder and trained on publicly available parallel corpora.

1102

Content

0

Paper Graph

Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT

Mark Dredze, Shijie Wu•Thu Apr 18 2019

This paper explores the broader cross-lingual potential of mBERT (multilingual) as a zero shot language transfer model on 5 NLP tasks covering a total of 39 languages from various language families: NLI, document classification, NER, POS tagging, and dependency parsing.

723 0

Paper Graph

XLM-E: Cross-lingual Language Model Pre-training via ELECTRA

Shaohan Huang, Xia Song, Li Dong, Zewen Chi, Furu Wei, Shuming Ma, Saksham Singhal, Payal Bajaj•Tue Jun 29 2021

This paper introduces ELECTRA-style tasks to cross-lingual language model pre-training, and pretrain the model, named as XLM-E, on both multilingual and parallel corpora, which outperforms the baseline models on various cross-lingsual understanding tasks with much less computation cost.

131 0

Paper Graph

Simple and Effective Zero-shot Cross-lingual Phoneme Recognition

Michael Auli, Qiantong Xu, Alexei Baevski•Wed Sep 22 2021

This paper extends previous work on zero-shot cross-lingual transfer learning by fine-tuning a multilingually pretrained wav2vec 2.0 model to transcribe unseen languages by mapping phonemes of the training languages to the target language using articulatory features.

120 0

Paper Graph

Composable Sparse Fine-Tuning for Cross-Lingual Transfer

A. Korhonen, E. Ponti, Ivan Vulic, Alan Ansell•Wed Oct 13 2021

This work introduces a new fine-tuning method that outperforms adapters in zero-shot cross-lingual transfer by a large margin in a series of multilingual benchmarks, including Universal Dependencies, MasakhaNER, and AmericasNLI.

169 0

Paper Graph

Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization

A. Korhonen, N. Mrksic, E. Ponti, Ivan Vulic, Goran Glavas•Mon Sep 10 2018

This work proposes a novel approach to specializing the full distributional vocabulary by combining a standard L2-distance loss with a adversarial loss, and proposes a cross-lingual transfer method for zero-shot specialization which successfully specializes a full target distributional space without any lexical knowledge in the target language and without any bilingual data.

49 0

Paper Graph

Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing

Ting Liu, Yijia Liu, Wanxiang Che, Yuxuan Wang, Jiang Guo•Sat Sep 14 2019

This paper proposes Cross-Lingual BERT Transformation (CLBT), a simple and efficient approach to generate cross-lingual contextualized word embeddings based on publicly available pre-trained BERT models (Devlin et al., 2018).

122 0

Paper Graph

Cross-Lingual Natural Language Generation via Pre-Training

Li Dong, Zewen Chi, Heyan Huang, Xian-Ling Mao, Furu Wei, Wenhui Wang•Sun Sep 22 2019

Experimental results on question generation and abstractive summarization show that the model outperforms the machine-translation-based pipeline methods for zero-shot cross-lingual generation and improves NLG performance of low-resource languages by leveraging rich-resource language data.

141 0

Paper Graph

Zero-Shot Cross-Lingual Transfer with Meta Learning

Isabelle Augenstein, Johannes Bjerva, F. Nooralahzadeh, Giannis Bekoulis•Wed Mar 04 2020

This work considers the setting of training models on multiple different languages at the same time, when little or no data is available for languages other than English, and demonstrates the consistent effectiveness of meta-learning for a total of 15 languages.

117 0

Paper Graph

Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages

A. Korhonen, E. Ponti, Ivan Vulic, Ryan Cotterell, Marinela Parovic, Roi Reichart•Wed Jan 29 2020

A Bayesian generative model for the space of neural parameters is proposed that can be factorized into latent variables for each language and each task, and infer the posteriors over such latent variables based on data from seen task–language combinations through variational inference.

30 0

Paper Graph

Adding a benchmark result helps the community track progress.