Have you used IBM Watson Knowledge Studio to deploy models to Watson Natural Language Understanding or Watson Discovery Service? We have news for you.
Knowledge Studio is a cloud-based application that allows developers and domain experts to collaborate and create custom annotator components. These components are used to identify mentions and relations in unstructured text and analyze text specific to an industry.
For example, the word “virus” can be interpreted much differently between a cyber analyst and a medical doctor. The underlying technology of Watson Knowledge Studio allows for such nuanced distinctions with precision and speed. Plus, it works in tandem with other IBM offerings to handle all aspects of domain adaptation for unstructured text – from defining a type system to deployment of a fully trained model.
To make this domain adaptation more accessible to a wider audience, IBM has lowered the costs of using custom domain models. The price to deploy a custom model has been reduced by nearly 80 percent, from $3500 monthly to $800. Watson Knowledge Studio models are natively integrated with Natural Language Understanding and Watson Discovery Service. After the models are created, they can be deployed with just a few clicks.
Discover how deep into your data Watson Knowledge Studio can take you.
Start with a free plan of Watson Knowledge Studio and create one model you can then deploy to a trial version of Natural Language Understanding or Watson Discovery Service. As your usage grows, you can upgrade to a paid plan.
Key points: – Woodside Energy is working with Watson to make decades of expertise available to its engineers. – Watson ingested the equivalent of 600,000 pages of information, or 30 years of knowledge – Watson helped reduce the time spent searching for expert knowledge by 75% – To do this, Woodside Energy combined three different […]
In Salt Lake County, Utah, people were struggling with being re-arrested because they wouldn’t show up for court appearances. The county government teamed up with a Code for America team lead by 2016 Fellow Kuan Butts. They created a technological tool leveraging IBM Watson and Twilio to solve this problem. Code for America identified a […]
Modern day speech-to-text services are built using a corpus of general, everyday words and pronunciations. While this system works well for common conversation, it can fall short when it comes to accurately transcribing unique accents, industry specific words, or uncommon dialect. The majority of speech recognition services don’t offer tooling to train the system on […]