Search – talk-data.com

Title & Speakers	Event
Event Assessing Risk of Extreme Events & Knowledge Extraction for RAG Systems 2025-11-27
Autocurator: AI-Powered Knowledge Extraction for RAG Systems 2025-11-27 · 19:45 Marco P. Abrate – Visiting AI Engineer @ BCG X , Eleonora Vardè – Lead Data Scientist @ BCG X Milan In the era of information overload, organizations struggle to harness the vast amount of unstructured data stored across presentations, reports, images, and text documents. That's why we created the "Autocurator", an AI-powered tool designed to automatically extract, structure, and curate knowledge from heterogeneous document repositories to support Retrieval-Augmented Generation (RAG) systems. Autocurator integrates advanced document parsing pipelines, multimodal AI models, and semantic structuring techniques to convert diverse content - including text, slides, tables, and diagrams - into machine-readable knowledge. This enables downstream RAG systems to query not only text-based insights but also visual and conceptual knowledge that traditionally remained inaccessible. Our system employs a multi-stage pipeline: (1) document ingestion and format normalization, (2) de-duplication of redundant and conflicting information (3) multimodal content understanding using large language and vision models, (4) entity and relationship extraction with human-in-the-loop validation, and (5) generation of structured outputs optimized for retrieval. We will showcase Autocurator’s effectiveness on large enterprise document corpora, showcasing significant gains in retrieval precision and generative quality across several applied AI use cases. By bridging unstructured data and structured knowledge, Autocurator provides a scalable and transparent foundation for next-generation knowledge management and reasoning systems. AI/ML RAG
Extreme Hail Risk Estimation for Utility-scale Solar Parks 2025-11-27 · 19:00 Valerio Bonometti – Senior Data Scientist @ Lightsource bp Extreme hail events pose a serious risk not just for people but also for business and assets. Due to their nature this is particularly true for utility-scale solar parks. Accurately assessing the risk of extreme hail is therefore critical when planning, developing, and operating large-scale solar farms. Yet, the challenge is compounded by limited, noisy historical data and the unpredictable nature of severe weather events. In this talk, I will show how a range of statistical and simulation methods can be used to estimate hail risk—even in situations with limited or noisy data.

In the era of information overload, organizations struggle to harness the vast amount of unstructured data stored across presentations, reports, images, and text documents. That's why we created the "Autocurator", an AI-powered tool designed to automatically extract, structure, and curate knowledge from heterogeneous document repositories to support Retrieval-Augmented Generation (RAG) systems. Autocurator integrates advanced document parsing pipelines, multimodal AI models, and semantic structuring techniques to convert diverse content - including text, slides, tables, and diagrams - into machine-readable knowledge. This enables downstream RAG systems to query not only text-based insights but also visual and conceptual knowledge that traditionally remained inaccessible. Our system employs a multi-stage pipeline: (1) document ingestion and format normalization, (2) de-duplication of redundant and conflicting information (3) multimodal content understanding using large language and vision models, (4) entity and relationship extraction with human-in-the-loop validation, and (5) generation of structured outputs optimized for retrieval. We will showcase Autocurator’s effectiveness on large enterprise document corpora, showcasing significant gains in retrieval precision and generative quality across several applied AI use cases. By bridging unstructured data and structured knowledge, Autocurator provides a scalable and transparent foundation for next-generation knowledge management and reasoning systems.

talk-data.com

People (2 results)

Activities & events