R11 #6104
Merged
R11 #6104
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This reverts commit 709fb56.
tsuwandy
approved these changes
Nov 12, 2020
| ## References | ||
| **Intent Recognizer**: You can use Orchestrator as an intent recognizer with [Adaptive dialogs][6]. Using the same approach as in the dispatch scenario above in order to route to responses within your bot logic. | ||
|
|
||
| **Entity Extraction** is not supported yet. It is on the planning roadmap to add entity extraction in the future. |
Contributor
There was a problem hiding this comment.
Entity Extraction is not supported yet but it is on the roadmap.
| * **Code First**: Orchestrator can be integrated into your code project by replacing LUIS for intent recognition such as for skill delegation or dispatching to subsequent language understanding services. See [Runtime Integration](#runtime-integration) section for more. | ||
| * [Bot Framework Composer][19]: Orchestrator can be selected as a recognizer within Bot Framework Composer. At this point there are limitations to using Orchestrator in Composer primarily around importing of existing models and tuning up recognition performance (* currently available only if the feature flag is enabled with Composer). | ||
|
|
||
| Thus, use of [BF command line tool][7] to prepare and optimize the model for your domain is required in most, if not all, use cases. To illustrate the workflow, here is a sample the end to end authoring experience: |
Contributor
There was a problem hiding this comment.
here is a sample of end to end authoring experience experience:
| 1. Author Intent-utterances example based .lu definition referred to as a *label file* using the Language Understanding practices as described in [Language Understanding][2] for dispatch (e.g. author .lu file or within the [Composer][3] GUI experience). | ||
| * Alternatively, [export][8] your LUIS application and [convert][9] to .lu format or [export][10] your QnA Maker KB to .qna format. | ||
| * See also the [.lu file format][21] to author a .lu file from scratch. | ||
| 2. Download Natural Language Representation ([NLR][20]) base Model (will be referred to as the *basemodel*) using the `bf orchestrator:basemodel:get` command. |
Contributor
There was a problem hiding this comment.
Download Orchestrator base model using 'bf orchestrator:basemodel:get' ...
We no longer use NLR term..
| * Alternatively, [export][8] your LUIS application and [convert][9] to .lu format or [export][10] your QnA Maker KB to .qna format. | ||
| * See also the [.lu file format][21] to author a .lu file from scratch. | ||
| 2. Download Natural Language Representation ([NLR][20]) base Model (will be referred to as the *basemodel*) using the `bf orchestrator:basemodel:get` command. | ||
| * See `bf orchestrator:basemodel:list` for alternate models. You may need to experiment with the different models to find which performs best for your language domain. |
Contributor
There was a problem hiding this comment.
Might want to link to aka.ms/nlrmodels (the page Cez worked on with description to different models)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #
Proposed Changes
Testing