IBM Watson Benchmark
The IBM Watson Natural Language Understanding service is a cloud offering that is capable of extracting metadata from text. For speech input, Watson Speech to Text can be used to transcribe audio files. For domain-specific contexts, the customization interface can be used to create a custom language model to improve speech recognition performance.
- Ubuntu 20.04 (x86_64)
- IBM Watson Account
- Clone the repository:
- Install the dependencies:
Create a NLU service.
Create a standard plan Speech to Text service.
Create a Knowledge Studio service and create a new Workspace.
In your new Workspace, upload the previously created type system
Rule-based Model, create a class for each entity type.
data/watson/barista_dictionaries.zip. Select the corresponding entity type and corresponding rule-class for each dictionary.
Versionspage, go to the
Rule-based Model Type Mappingtab and map each entity type to the corresponding class.
Return to the
Rule-based Modelpage and save for deployment. You should see a model with version number
1.0. Deploy this model to Natural Language Understanding, and take note of your
Run the benchmark: