A Multi-Modal Multilingual Benchmark for Document Image Classification

Yoshinari Fujinuma, Siddharth Varia, Nishant Sankaran, Srikar Appalaraju, Bonan Min, Yogarshi Vyas

Submission Type: Regular Long Paper

Submission Track: Multilinguality and Linguistic Diversity

Submission Track 2: Resources and Evaluation

Keywords: Document AI, layout-aware models, visually-rich document understanding, multilingual document image classification

Abstract: Document image classification is different from plain-text document classification and consists of classifying a document by understanding the content and structure of documents such as forms, emails, and other such documents. We show that the only existing dataset for this task (Lewis et al., 2006) has several limitations and we introduce two newly curated multilingual datasets WIKI-DOC and MULTIEURLEX-DOC that overcome these limitations. We further undertake a comprehensive study of popular visually-rich document understanding or Document AI models in previously untested setting in document image classification such as 1) multi-label classification, and 2) zero-shot cross-lingual transfer setup. Experimental results show limitations of multilingual Document AI models on cross-lingual transfer across typologically distant languages. Our datasets and findings open the door for future research into improving Document AI models.

Submission Number: 2121