SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.08226 · ACL · 2021

Consistency Regularization for Cross-Lingual Fine-Tuning

Furu Wei, Ting Liu, Xia Song, Li Dong, Bo Zheng, Zewen Chi, Shaohan Huang, Saksham Singhal, Wanxiang Che, Wenhui Wang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Fine-tuning pre-trained cross-lingual language models can transfer task-specific supervision from one language to the others. In this work, we propose to improve cross-lingual finetuning with consistency regularization. Specifically, we use example consistency regularization to penalize the prediction sensitivity to four types of data augmentations, i.e., subword sampling, Gaussian noise, code-switch substitution, and machine translation. In addition, we employ model consistency to regularize the models trained with two augmented versions of the same training set. Experimental results on the XTREME benchmark show that our method 1 significantly improves crosslingual fine-tuning across various tasks, including text classification, question answering, and sequence labeling.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.08226")
get_code_for_paper("2106.08226")
have("2106.08226")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2106.08226.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2106.08226.svg)](https://syntology.ai/paper/2106.08226)

Connect an agent — have() is free.