Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon

TL;DR

This paper introduces a method that leverages multilingual sentiment lexicons during pretraining to improve zero-shot sentiment analysis in low-resource languages without relying on sentence-level sentiment data.

Contribution

It presents a novel pretraining approach using multilingual lexicons that enhances zero-shot sentiment analysis across diverse low-resource and code-switching languages.

Findings

Pretraining with multilingual lexicons outperforms fine-tuned models on English sentiment data.

The approach improves zero-shot performance in unseen low-resource languages.

Effective in code-mixed language scenarios.

Abstract

Improving multilingual language models capabilities in low-resource languages is generally difficult due to the scarcity of large-scale data in those languages. In this paper, we relax the reliance on texts in low-resource languages by using multilingual lexicons in pretraining to enhance multilingual capabilities. Specifically, we focus on zero-shot sentiment analysis tasks across 34 languages, including 6 high/medium-resource languages, 25 low-resource languages, and 3 code-switching datasets. We demonstrate that pretraining using multilingual lexicons, without using any sentence-level sentiment data, achieves superior zero-shot performance compared to models fine-tuned on English sentiment datasets, and large language models like GPT--3.5, BLOOMZ, and XGLM. These findings are observable for unseen low-resource languages to code-mixed scenarios involving high-resource languages.