Eric Rozell
Eric Rozell
If I have a test case like: ``` { "text": "contact info for carole", "intent": "ContactInfo", "entities": [ { "matchText": "carole", "entityType": "builtin.personName" } ] } ``` And through speech...
Table should include intents and entity types, precision, recall, and F1 score, and deltas for each from a specified build. Should be able to sort by any table heading.
Change NLU.DevOps.ModelPerformance to a configurable JSON compare library such that any two JSON values can be compared. We could have a simple interface like `IConfusionMatrixEvaluator`: ```cs public interface IConfusionMatrixEvaluator {...
For example, if a test includes text: "show me my schedule a week from tomorrow", likely we'll want to assert that "a week from tomorrow" is matched as a date...
With the upcoming changes to NLU.DevOps.ModelPerformace, we'll be able to support arbitrary testing of JSON results from NLU. We should add a providers, NLU.DevOps.BotService, that supports both direct line via...
While we don't currently support any NLU providers that include multi-intent, we should document how multi-intent providers could be testing using the existing tools.
The `NLU Results` tab we are building to visualize confusion matrix results for NLU may be useful for a number of information retrieval problems. We should aim to generalize the...
Current documentation covers variable setting and CLI usage, but scenario driven documentation would be more useful. E.g., adding a doc that talks about when it's worth using the generic utterance...
You can use other tools for importing NLU models to LUIS or Lex, and only use NLU.DevOps to test your model. We should add a doc that discusses how to...
Similar to other packages (react-native-svg, @react-native-picker/picker, etc.), this change adds WinAppSDK support for apps that compile react-native-windows from source targeting WinAppSDK.