What understood that we've used LUIS through the year.
What understood about thatwe’ve used LUIS through the yearShinichi TanabeJanuary 12, 2018 Minami Aoyama Night #5
View Slide
SpeakerShinichi Tanabe (田邊 晋一/たなべ しんいち)● NAVITIME JAPAN Co., Ltd.○ Joined in 2008○ Cogbot project○ Programmer
Products
Encounter
September 15, 2016
First impression
Easy to use, runs fast and smart.
Easy to use
Let’s go to the portal site!https://www.luis.ai
Step1. Create new app
Step2. Add intent
Step3. Add utterances
Step4. Add entities
Step5. Train
Step6. Test
Step7. Publish
That’s all!
Furthermore...
You can get a happy bonus.
Versioning
Runs fast and smart
Comparison betweenandLUIS Dialogflow
Test model
Test modelIntent Places.FindPlaceUtterances おいしいカレーが食べたいなどこか近くでおすすめのレストランを教えてEntities Cuisine カレーPlaceType レストラン
Training speed
LUIS 2 - 4 secDialogflow 4 - 8 secThe training speed result of test model
Precision and recall
Test utteranceLUIS DialogflowIntent Entity Intent Entityおいしいカレーが食べたいな 〇 〇 〇 〇どこか近くでおすすめのレストランを教えて〇 〇 〇 〇Precision result of test model
Test utteranceLUIS DialogflowIntent Entity Intent Entityおすすめのバーを教えて 〇 〇 × ×おすすめのバー教えて 〇 × × ×おいしいうどんが食べたい 〇 〇 〇 ×おいしいうどん食べたい 〇 × 〇 ×Recall result of test model
Yes, he was perfect!
Getting started
But, we had some questions.
Questions1. How should we defines intents and entities?2. How do we know accuracy and precision?3. When will he go GA(General Availability)?
1. How should we defines intents and entities?
Anti patternUtterance : Intent ≒ 1 : 1
Use or copy pre-build model positively.
2. How do we know accuracy and precision?
Comprehensive test on model
Batch testing
Test result details in a visualized view.
Error matrix
True positiveTrue negativeGreen zone indicates correct prediction
False negativeFalse positiveRed zone indicates incorrect prediction
3. When will he go GA?
LUIS is now GA!!
How to get along with LUIS
Points1. Start small model which has few intents.2. Use or copy pre-build model positively.3. Raise requests before do something about that yourself.
Thank you!