Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Cross-Lingual Transfer Robustness to Lower-Resource Languages on Adversarial Datasets

Domain:

natural language processing

Record type:

paper
Creator:
ManKri
Host:avatar
Multilingual Language Models (MLLMs) exhibit robust cross-lingual transfer capabilities, or the ability to leverage information acquired in a source language and apply it to a target language. These capabilities find practical applications in well-established Natural Language Processing (NLP) tasks such as Named Entity Recognition (NER). This study aims to investigate the effectiveness of a source language when applied to a target language, particularly in the context of perturbing the input test set. We evaluate on 13 pairs of languages, each including one high-resource language (HRL) and one low-resource language (LRL) with a geographic, genetic, or borrowing relationship. We evaluate two well-known MLLMs--MBERT and XLM-R--on these pairs, in native LRL and cross-lingual transfer settings, in two tasks, under a set of different perturbations. Our findings indicate that NER cross-lingual transfer depends largely on the overlap of entity chunks. If a source and target language have more entities in common, the transfer ability is stronger. Models using cross-lingual transfer also appear to be somewhat more robust to certain perturbations of the input, perhaps indicating an ability to leverage stronger representations derived from the HRL. Our research provides valuable insights into cross-lingual transfer and its implications for NLP applications, and underscores the need to consider linguistic nuances and potential limitations when employing MLLMs across distinct languages. accepted in LREC-COLING 2024

Visit

arxiv.org

Tasks

information extractionnamed entity recognitiontransfer learning

Tags

Computation and Language

Similar

Impact of Intermediate-Task Training on Cross-Lingual Transfer Robustness in Low-Resource LanguagesRobustness of Cross-Lingual Models to Adversarial Examples in Low-Resource Languages After Intermediate-Task TrainingAdversarial Training Effects on Zero-Shot Cross-Lingual Transfer Robustness in XLM-R ModelsSoft Layer Selection for Adversarial Robustness in Zero-Shot Cross-Lingual TransferImpact of Intermediate-Task Diversity on Zero-Shot Cross-Lingual Transfer Robustness in Low-Resource LanguagesImpact of Optimal Transport Distillation on Adversarial Robustness in Zero-Shot Cross-Lingual Retrieval for Low-Resource Languages

Impact of Intermediate-Task Training on Cross-Lingual Transfer Robustness in Low-Resource Languages

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuni

Robustness of Cross-Lingual Models to Adversarial Examples in Low-Resource Languages After Intermediate-Task Training

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuni

Adversarial Training Effects on Zero-Shot Cross-Lingual Transfer Robustness in XLM-R Models

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Soft Layer Selection for Adversarial Robustness in Zero-Shot Cross-Lingual Transfer

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Impact of Intermediate-Task Diversity on Zero-Shot Cross-Lingual Transfer Robustness in Low-Resource Languages

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuni

Impact of Optimal Transport Distillation on Adversarial Robustness in Zero-Shot Cross-Lingual Retrieval for Low-Resource Languages

Benefiting from transformer-based pre-trained language models, neural ranking models have made signi