{"id":23177,"date":"2025-03-03T13:00:37","date_gmt":"2025-03-03T18:00:37","guid":{"rendered":"https:\/\/enterprise-knowledge.com\/?p=23177"},"modified":"2025-11-17T17:16:03","modified_gmt":"2025-11-17T22:16:03","slug":"extracting-knowledge-from-documents-enabling-semantic-search","status":"publish","type":"post","link":"https:\/\/enterprise-knowledge.com\/extracting-knowledge-from-documents-enabling-semantic-search\/","title":{"rendered":"Extracting Knowledge from Documents: Enabling Semantic Search for Pharmaceutical Research and Development"},"content":{"rendered":"\r\n
\r\n
\"\"<\/figure>\r\n
\r\n

The Challenge<\/h2>\r\n\r\n\r\nA major pharmaceutical research and development company faced difficulty creating regulatory reports and files based on years of drug experimentation data. Their regulatory intelligence teams and drug development chemists spent dozens of hours searching through hundreds of thousands of documents to <\/span>find past experiments and their results in order <\/span>to fill out regulatory compliance documentation. The company\u2019s internal search platform enabled users to look for documents, but required exact matches on specific keywords to surface relevant results, and lacked useful search filters. Additionally, due to the nature of chemistry and drug development, many documents were difficult to understand at a glance and required scientists to read through them in order to determine if they were relevant or not.<\/span> <\/div>\r\n<\/div>\r\n\r\n\r\n\r\n
\r\n
\"\"<\/figure>\r\n
\r\n

The Solution<\/h2>\r\n\r\n\r\nEK collaborated with the company to improve their internal search platform by enhancing Electronic Lab Notebook (ELN) metadata, thereby increasing the searchability and findability of critical research documents, and created a strategy for leveraging ELNs in AI-powered services such as chatbots and LLM-generated document summaries. EK worked with the business stakeholders to evaluate the most important information within ELNs and understand the document structure, and developed semantic models in their taxonomy management system with more than 960 relevant concepts designed to capture the way their expert chemists understand the experimental activities and molecules referenced in the ELNs. \"\"<\/a>With the help of the client\u2019s technical infrastructure team, EK developed a new corpus analysis and ELN autotagging pipeline that leveraged the taxonomy management system\u2019s built-in document analyzer and integrated the results with their data warehouse and search schema. Through three rounds of testing, EK iteratively improved the extraction of metadata from ELNs using the concepts in the semantic model to provide additional metadata on over 30,000 ELNs to be leveraged within the search platform. EK wireframed 6 new User Interface (UI) features and enhancements for the search platform designed to leverage the additional metadata provided by the autotagging pipeline, including search-as-you-type functionality and improved search filters, and socialized them with the client\u2019s UI\/ User Experience (UX) team. Finally, EK supported the client with strategic guidance for leveraging their internal LLM service to create accurate regulatory reports and AI summaries of ELNs within the search platform.<\/span>\r\n