ABBYY empowers organizations with AI-ready data, improving outcomes from advanced LLM and agentic-based automation pipelines
On the heels of the announcement by the Linux AI & Data Foundation about the new DocLang AI native document standard founded by ABBYY, IBM, HumanSignal, Nvidia, and RedHat, ABBYY released ABBYY FineReader Engine 12.8.0 that exports to DocLang.
ABBYY FineReader Engine with DocLang support provides developers a unified, AI-readable format to represent documents for language model and agentic AI consumption, saving them time and increasing document processing performance.
ABBYY FineReader Engine with DocLang support provides developers a unified, AI-readable format to represent documents for language model and agentic AI consumption, saving them time and increasing document processing performance.
Marketing Technology News: MarTech Interview with Theresa Pham, Head of Product @ Wayvia
FineReader Engine with DocLang Improves Document Processing Performance
ABBYY recently demonstrated FineReader Engine processing unprecedented speeds of 2,160,000 pages per hour at its ABBYY Ascend event. Additionally, in a side-by-side benchmark, ABBYY compared the processing of a PDF and DocLang document. In the controlled experiment, the same document for the same complex task using the same AI model was configured identically. The only variable was the document representation in PDF and DocLang. FineReader Engine with DocLang significantly improved output quality, increased structural accuracy, decreased token usage, and reduced latency.
The controlled benchmark tested three types of enterprise documents: an annual report, a clinical study, and a vendor contract. These documents, designed for human interpretation yet complex for machines to process, demonstrated successful results during testing.
“ABBYY FineReader Engine is already used by thousands of organizations processing billions of documents every year,” commented Max Vermeir, VP of AI Strategy at ABBYY. “Now with DocLang as an AI native format, more companies will be able to accelerate innovation and have faster access to their business data to make smarter, more impactful decisions.”
Marketing Technology News: Idle data is as good as no data
Why the DocLang Standard is Needed
ABBYY, IBM, HumanSignal, Nvidia and Red Hat, formed the DocLang working group to revolutionize AI document parsing. Current document formats such as PDF, HTML, Markdown, and others, were designed for human consumption rather than for AI interpretation. The result is a patchwork of partial solutions requiring custom parsing at every integration point that burdens developers with building custom parsers, is prone to hallucinations, and complicates regulatory compliance.
DocLang creates a reliable abstraction layer between unstructured data and intelligent AI systems. It standardizes the cacophony of digital document formats that enterprises operate on and gives AI systems the deterministic structure they need to perform reliably at enterprise scale.
Continued Vermeir, “DocLang is specifically engineered to address industry challenges with a minimal, standardized, and AI-native method for representing document structure, meaning, layout, and governance. FineReader Engine with DocLang support was designed for efficient machine processing and a predictable structure optimized for modern AI tokenization and modeling techniques. Organizations will see a significant difference with more reliable interpretation, increased accuracy, and lower computational costs.”
