Webinar: Customization with Rosette
When applied to novel domains such as legal, medical, and hacker chatter, the out-of-box accuracy of NLP systems trained on news and other general-purpose datasets leaves much to be desired. What matters is how well a system performs on your</em data, and how easy it is to extract the information you need with minimal developer effort. In this webinar, we’ll introduce three new customization techniques for achieving your specific text processing goals with Rosette:
- Rapid development of custom entity & event extraction models with active learning, which reduces the number of annotated samples needed by about 75%.
- Resolving entity mentions to your knowledge base. With our custom database connector, leverage the power of contextual disambiguation for domain-specific entities of any type.
- Building custom text processing workflows to weave together multiple NLP functions with custom logic. For example, run entity extraction on an Arabic document to pull out key people, places, and organizations, then subsequently translate these entity names into English, all via a single API call.
June 10, 2020 at 11:30 am ET
8:30 am: PT
11:30 am: ET
4:30 pm: London
6:30 pm: Tel Aviv
Director of Product Management
Heather oversees the product roadmap — from nuts and bolts implementation, to strategy and vision — for the Rosette text analytics platform from Basis Technology. Rosette spans a wide range of natural language processing (NLP) capabilities and human languages, supporting both SaaS and on-premise deployments. A technologist by training with a passion for human language, Heather has been with Basis Technology for over a decade in a variety of roles from software development to field engineering to business development. Heather completed her undergraduate degree at MIT, where she studied both computer science and Spanish literature.
Loves building products that make a difference in the real world • Creatively-minded with a passion for design and art • Data and language nerd
Hannah MacKenzie-Margulies is the product manager for text analytics at Basis Technology where she is responsible for bringing cutting-edge research in Artificial Intelligence, Deep Learning, and Natural Language Processing to market, providing the world’s largest financial institutions with software that allows them to detect anomalies, evaluate risk, and fight crime. An expert on exploiting unstructured, multilingual content for resonant signals, Hannah has developed tailored engines for over 120 different languages and dialects, most recently North Korean. She is a graduate of Reed College in Portland, OR.