English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

We address the extraction of mathematical statements and their proofs fromscholarly PDF articles as a multimodal classification problem, utilizing text,font features, and bitmap image renderings of PDFs as distinct modalities. Wepropose a modular sequential multimodal machine learning approach specificallydesigned for extracting theorem-like environments and proofs. This is based ona cross-modal attention mechanism to generate multimodal paragraph embeddings,which are then fed into our novel multimodal sliding window transformerarchitecture to capture sequential information across paragraphs. Our documentAI methodology stands out as it eliminates the need for OCR preprocessing,LaTeX sources during inference, or custom pre-training on specialized losses tounderstand cross-modality relationships. Unlike many conventional approachesthat operate at a single-page level, ours can be directly applied to multi-pagePDFs and seamlessly handles the page breaks often found in lengthy scientificmathematical documents. Our approach demonstrates performance improvementsobtained by transitioning from unimodality to multimodality, and finally byincorporating sequential modeling over paragraphs.

Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)