SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages

TL;DR

SEACrowd is a comprehensive multilingual multimodal dataset and benchmark suite designed to improve AI model evaluation and development for Southeast Asian languages, addressing resource scarcity and cultural representation issues.

Contribution

It introduces a large, standardized resource hub with datasets in nearly 1,000 SEA languages and benchmarks across 13 tasks, filling a critical gap in AI resources for the region.

Findings

Assessment of AI models on 36 indigenous SEA languages

Identification of current limitations in model performance

Strategies proposed for enhancing AI resource equity in SEA

Abstract

Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA, compromising the quality of AI models for SEA languages. Evaluating models for SEA languages is challenging due to the scarcity of high-quality datasets, compounded by the dominance of English training data, raising concerns about potential cultural misrepresentation. To address these challenges, we introduce SEACrowd, a collaborative initiative that consolidates a comprehensive resource hub that fills the resource gap by providing standardized corpora in nearly 1,000 SEA languages across three modalities. Through our SEACrowd benchmarks, we assess the quality of AI models on 36 indigenous languages across 13 tasks, offering valuable insights into the current AI landscape in SEA. Furthermore, we propose strategies to facilitate greater AI advancements, maximizing potential utility and resource equity for the future of AI in SEA.