BEGIN:VCALENDAR VERSION:2.0 PRODID:-//swoogo.com//NONSGML kigkonsult.se iCalcreator 2.41.90// CALSCALE:GREGORIAN UID:34373739-6537-4533-a634-613234346539 BEGIN:VEVENT UID:eacdf0a9dfc134fd5875bd651b38c37760a4ff5e@swoogo.com DTSTAMP:20260817T145544Z DESCRIPTION:This paper explores a novel procedure for creating Knowledge Gr aphs (KGs) from unstructured text to improve the management of news story data. The method leverages iterative few-shot Large Language Model (LLM) p rompting and unsupervised clustering models\, combined with state-of-the-a rt text embedding techniques\, to disambiguate entities and predicates. It also incorporates node and edge attributes to enhance graph analytics. Th e approach addresses multi-language text handling and provides KGs in vari ous languages. By translating natural language queries into graph queries\ , this method improves user interactions and information retrieval. An eva luation protocol is introduced to assess the effectiveness of this procedu re\, aiming to enrich news content by identifying and contextualizing rela tionships between entities\, thus enhancing data insights. DTSTART:20241023T173000Z DTEND:20241023T180000Z LAST-MODIFIED:20260817T145544Z LOCATION:Session Room 2 SEQUENCE:0 STATUS:CONFIRMED SUMMARY:Leveraging Large Language Models and Knowledge Graphs to Enhance Me tadata Extraction for News Media Production TRANSP:OPAQUE X-ALT-DESC;FMTTYPE=text/html:

This paper explores a novel procedure for c reating Knowledge Graphs (KGs) from unstructured text to improve the manag ement of news story data. The method leverages iterative few-shot Large La nguage Model (LLM) prompting and unsupervised clustering models\, combined with state-of-the-art text embedding techniques\, to disambiguate entitie s and predicates. It also incorporates node and edge attributes to enhance graph analytics. The approach addresses multi-language text handling and provides KGs in various languages. By translating natural language queries into graph queries\, this method improves user interactions and informati on retrieval. An evaluation protocol is introduced to assess the effective ness of this procedure\, aiming to enrich news content by identifying and contextualizing relationships between entities\, thus enhancing data insig hts.

BEGIN:VALARM UID:62623762-6434-4166-b436-643139303538 ACTION:DISPLAY DESCRIPTION:This paper explores a novel procedure for creating Knowledge Gr aphs (KGs) from unstructured text to improve the management of news story data. The method leverages iterative few-shot Large Language Model (LLM) p rompting and unsupervised clustering models\, combined with state-of-the-a rt text embedding techniques\, to disambiguate entities and predicates. It also incorporates node and edge attributes to enhance graph analytics. Th e approach addresses multi-language text handling and provides KGs in vari ous languages. By translating natural language queries into graph queries\ , this method improves user interactions and information retrieval. An eva luation protocol is introduced to assess the effectiveness of this procedu re\, aiming to enrich news content by identifying and contextualizing rela tionships between entities\, thus enhancing data insights. TRIGGER:-PT15M END:VALARM END:VEVENT END:VCALENDAR