{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multimodal-machine-learning-for-extraction-of","title":"Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)","arxiv_id":"2307.09047","date":"2023-07-18","proceeding":null,"authors":["Shrey Mishra","Antoine Gauquier","Pierre Senellart"],"abstract":"We address the extraction of mathematical statements and their proofs from scholarly PDF articles as a multimodal classification problem, utilizing text, font features, and bitmap image renderings of PDFs as distinct modalities. We propose a modular sequential multimodal machine learning approach specifically designed for extracting theorem-like environments and proofs. This is based on a cross-modal attention mechanism to generate multimodal paragraph embeddings, which are then fed into our novel multimodal sliding window transformer architecture to capture sequential information across paragraphs. Our document AI methodology stands out as it eliminates the need for OCR preprocessing, LaTeX sources during inference, or custom pre-training on specialized losses to understand cross-modality relationships. Unlike many conventional approaches that operate at a single-page level, ours can be directly applied to multi-page PDFs and seamlessly handles the page breaks often found in lengthy scientific mathematical documents. Our approach demonstrates performance improvements obtained by transitioning from unimodality to multimodality, and finally by incorporating sequential modeling over paragraphs.","url_abs":"https://arxiv.org/abs/2307.09047v2","url_pdf":"https://arxiv.org/pdf/2307.09047v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"multimodal-machine-learning-for-extraction-of","repo_url":"https://github.com/mv96/mm_extraction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multimodal-machine-learning-for-extraction-of","repo_url":"https://github.com/PierreSenellart/theoremkb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"document-ai","task_name":"Document AI"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"crf","method_name":"CRF"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"efficientnetv2","method_name":"EfficientNetV2"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}