extraction Articles - Enterprise Knowledge https://enterprise-knowledge.com/tag/extraction/ Thu, 04 Sep 2025 15:35:14 +0000 en-US hourly 1 https://wordpress.org/?v=6.8.2 https://enterprise-knowledge.com/wp-content/uploads/2022/04/EK_Icon_512x512.svg extraction Articles - Enterprise Knowledge https://enterprise-knowledge.com/tag/extraction/ 32 32 How KM Leverages Semantics for AI Success https://enterprise-knowledge.com/how-km-leverages-semantics-for-ai-success/ Wed, 03 Sep 2025 19:08:31 +0000 https://enterprise-knowledge.com/?p=25271 This infographic highlights how KM incorporates semantic technologies and practices across scenarios to enhance AI capabilities.

The post How KM Leverages Semantics for AI Success appeared first on Enterprise Knowledge.

]]> This infographic highlights how KM incorporates semantic technologies and practices across scenarios to enhance AI capabilities.

To get the most out of Large Language Model (LLM)-driven AI solutions, you need to provide them with structured, context-rich knowledge that is unique to your organization. Without purposeful access to proprietary terminology, clearly articulated business logic, and consistent interpretation of enterprise-wide data, LLMs risk delivering incomplete or misleading insights. This infographic highlights how KM incorporates semantic technologies and practices across scenarios to  enhance AI capabilities and when they're foundational — empowering your organization to strategically leverage semantics for more accurate, actionable outcomes while cultivating sound knowledge intelligence practices and investing in your enterprise's knowledge assets. Use Case: Expert Elicitation - Semantics used for AI Enhancement Efficiently capture valuable knowledge and insights from your organization's experts about past experiences and lessons learned, especially when these insights have not yet been formally documented.  By using ontologies to spot knowledge gaps and taxonomies to clarify terms, an LLM can capture and structure undocumented expertise—storing it in a knowledge graph for future reuse. Example:  Capturing a senior engineer's undocumented insights on troubleshooting past system failures to streamline future maintenance. Use Case: Discovery & Extraction - Semantics used for AI Enhancement Quickly locate key insights or important details within a large collection of documents and data, synthesizing them into meaningful, actionable summaries, and delivering these directly back to the user. Ontologies ensure concepts are recognized and linked consistently across wording and format, enabling insights to be connected, reused, and verified outside an LLM's opaque reasoning process. Example: Scanning thousands of supplier agreements to locate variations of key contract clauses—despite inconsistent wording—then compiling a cross-referenced summary for auditors to accelerate compliance verification and identify high-risk deviations. Use Case: Context Aggregation - Semantics for AI Foundations Gather fragmented information from diverse sources and combine it into a unified, comprehensive view of your business processes or critical concepts, enabling deeper analysis, more informed decisions, and previously unattainable insights. Knowledge graphs unify fragmented information from multiple sources into a persistent, coherent model that both humans and systems can navigate. Ontologies make relationships explicit, enabling the inference of new knowledge that reveals connections and patterns not visible in isolated data. Example: Integrating financial, operational, HR, and customer support data to predict resource needs and reveal links between staffing, service quality, and customer retention for smarter planning. Use Case: Cleanup and Optimization - Semantics for AI Enhancement Analyze and optimize your organization's knowledge base by detecting redundant, outdated, or trivial (ROT) content—then recommend targeted actions or automatically archive and remove irrelevant material to keep information fresh, accurate, and valuable. Leverage taxonomies and ontologies to recognize conceptually related information even when expressed in different terms, formats, or contexts; allowing the AI to uncover hidden redundancies, spot emerging patterns, and make more precise recommendations than could be justified by keyword or RAG search alone. Example: Automatically detecting and flagging outdated or duplicative policy documents—despite inconsistent titles or formats—across an entire intranet, streamlining reviews and ensuring only current, authoritative content remains accessible. Use Case: Situated Insight - Semantics used for AI Enhancement Proactively deliver targeted answers and actionable suggestions uniquely aligned with each user's expressed preferences, behaviors, and needs, enabling swift, confident decision-making. Use taxonomies to standardize and reconcile data from diverse systems, and apply knowledge graphs to connect and contextualize a user's preferences, behaviors, and history; creating a unified, dynamic profile that drives precise, timely, and highly relevant recommendations. Example: Instantly curating a personalized learning path (complete with recommended modules, mentors, and practice projects) based on an employee's recent performance trends, skill gaps, and long-term career goals, accelerating both individual growth and organizational capability. Use Case: Context Mediation and Resolution - Semantics for AI Foundations Bridge disparate contexts across people, processes, technologies, etc., into a common, resolved machine readable understanding that preserves nuance while eliminating ambiguity. Semantics establish a shared, machine-readable understanding that bridges differences in language, structure, and context across people, processes, and systems. Taxonomies unify terminology from diverse sources, while ontologies and knowledge graphs capture and clarify the nuanced relationships between concepts—eliminating ambiguity without losing critical detail. Example: Reconciling varying medical terminologies, abbreviations, and coding systems from multiple healthcare providers into a single, consistent patient record—ensuring that every clinician sees the same unambiguous history, enabling faster diagnosis, safer treatment decisions, and more effective care coordination. Learn more about our work with AI and semantics to help your organization make the most out of these investments, don't hesitate to reach out at:  https://enterprise-knowledge.com/contact-us/

The post How KM Leverages Semantics for AI Success appeared first on Enterprise Knowledge.

]]> Scaling Knowledge Graph Architectures with AI https://enterprise-knowledge.com/scaling-knowledge-graph-architectures-with-ai/ Thu, 30 Nov 2023 16:45:28 +0000 https://enterprise-knowledge.com/?p=19340 Sara Nash and Urmi Majumder, Principal Consultants at Enterprise Knowledge, presented “Scaling Knowledge Graph Architectures with AI” on November 9th, 2023 at KM World in Washington D.C. In this presentation, Nash and Majumder defined a Knowledge Graph architecture and reviewed … Continue reading

The post Scaling Knowledge Graph Architectures with AI appeared first on Enterprise Knowledge.

]]> Sara Nash and Urmi Majumder, Principal Consultants at Enterprise Knowledge, presented “Scaling Knowledge Graph Architectures with AI” on November 9th, 2023 at KM World in Washington D.C. In this presentation, Nash and Majumder defined a Knowledge Graph architecture and reviewed how AI can support the creation and growth of Knowledge Graphs. Drawing from their experience in designing enterprise Knowledge Graphs based on knowledge embedded in unstructured content, Nash and Majumder defined approaches for entity and relationship extraction depending on Enterprise AI maturity and highlighted other key considerations to incorporate AI capabilities into the development of a Knowledge Graph. Check out the presentation below to learn how to: 

  • Assess entity and relationship extraction readiness according to EK’s Extraction Maturity Spectrum and Relationship Extraction Maturity Spectrum.
  • Utilize knowledge extraction from content to translate important insights into organizational data.
  • Extract knowledge with three approaches:
    • RedEx Rule
    • Auto-Classification Rule
    • Custom ML Model
  • Examine key factors such as how to leverage SMEs, iterate AI processes, define use cases, and invest in establishing robust AI models.

The post Scaling Knowledge Graph Architectures with AI appeared first on Enterprise Knowledge.

]]>