SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.07255 · 2022

Enhancing Cross-lingual Prompting with Dual Prompt Augmentation

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

Prompting shows promising results in few-shot scenarios. However, its strength for multilingual/cross-lingual problems has not been fully exploited. Zhao and Schütze (2021) made initial explorations in this direction by presenting that cross-lingual prompting outperforms cross-lingual finetuning. In this paper, we conduct an empirical exploration on the effect of each component in cross-lingual prompting and derive language-agnostic Universal Prompting, which helps alleviate the discrepancies between source-language training and target-language inference. Based on this, we propose DPA, a dual prompt augmentation framework, aiming at relieving the data scarcity issue in few-shot cross-lingual prompting. Notably, for XNLI, our method achieves 46.54% with only 16 English training examples per class, significantly better than 34.99% of finetuning. Our code is available at https://github.com/DAMO-NLP-SG/DPA.

For agents

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

get_harvested_code_for_paper("2202.07255")
get_code_for_paper("2202.07255")
have("2202.07255")

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

curl https://syntology.ai/api/ran/2202.07255.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.07255.svg)](https://syntology.ai/paper/2202.07255)

Connect an agent — have() is free.