What’s new?With this release, the value of Watson Knowledge Studio has been expanded to meet more needs related to language, cost and data isolation. Here’s a list of what’s new:
- Use the visual rule editor: Now you can create custom text extractors more quickly using business rules in Watson Knowledge Studio. You can use the visual rule editor to accelerate machine-learning model training, then deploy it to AlchemyLanguage, Watson Discovery Service or Watson Explorer for text extraction.
- Work with more languages: Support is now available so you can work with documents in Italian, Brazilian Portuguese, French and Korean, adding to the languages that were already supported (English, German, Japanese, Arabic, French, Korean and Spanish).
- Accelerate training: To speed up training, you can pre-annotate documents with Watson’s AlchemyLanguage entity extraction service, which finds mentions of entities in documents automatically. Pre-annotation helps you train custom models more quickly and with less effort than annotating manually.
- Fine-tune results: You can iteratively fine-tune the results to meet your requirements. A new statistical tokenizer is introduced as the default. The previous dictionary-based tokenizer is available as an advanced option when you create a project.
- Watson Knowledge Studio Standard edition reduces the cost of entry by offering more flexible pricing options that can be tailored to your needs.
- Watson Knowledge Studio Premium edition offers the same capabilities as the Standard edition with added data isolation. The premium edition also supports enterprise-wide deployments.