This course was developed by members of AWS Technical Field Communities (TFC), an AWS community of technical experts. The content is intended to complement our standard training curriculum and augment your AWS learning journey. We are aware some courses have accessibility limitations and are working to address. If you require accommodation, please contact AWS Training and Certification Customer Support.
Learners can gain insight into how IBS Software built a bilingual Named Entity Recognition system for cargo logistics using Amazon Bedrock. The course covers extracting 23 entity types -- such as air waybill numbers, flight details, and weights -- from English and Japanese emails. It details how managed distillation from Amazon Nova Pro to Amazon Nova Lite achieved 95% F1-Score accuracy while reducing costs by 14x. Participants will learn about token-based distillation, deployment architecture, and practical lessons for building cost-effective, scalable NER solutions for multilingual document processing.
