Baidu Open-Sources and Releases ERNIE Unlimited OCR 2 Document Parsing Model, Supporting Unlimited Page Counts
On the 27th of this month, Baidu officially released and open-sourced the ERNIE Unlimited OCR 2 document parsing model, pushing the document parsing limit from dozens of pages to "unlimited," and can parse all 7 works of the entire Harry Potter series, totaling more than 3,600 pages, in a single pass. The model natively supports layout element segmentation and recognition, and has cross-page text merging and table recognition merging capabilities. It scored 84.6 on MPDocBench and 77.1 on MarathonDocBench, achieving end-to-end performance SOTA on both.
Why read this
AI score 56
The original text provides the page limit, cross-page merging capability, and two benchmark scores, allowing readers to judge the progress in long-document parsing.
Topics
Body · AI translation
Baidu Open-Sources and Releases ERNIE Unlimited OCR 2 Document Parsing Model, Supporting "Unlimited" Page Counts
English text is being prepared.
English text is being prepared.
Unlimited OCR 2 natively supports layout element segmentation and recognition, and has cross-page text merging and table recognition and merging capabilities, processing more, faster, and more economically under the same compute power.
Baidu stated that ERNIE Unlimited OCR 2 scored 84.6 on the MPDocBench benchmark for multi-page document parsing and 77.1 on the MarathonDocBench benchmark, which specifically evaluates the parsing capability of hundred-page-level ultra-long documents, achieving end-to-end performance SOTA on both.
Reference
English text is being prepared.