Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
What understood about that we've used LUIS through the year
Search
NAVITIME JAPAN
PRO
January 16, 2018
Technology
0
18
What understood about that we've used LUIS through the year
What understood that we've used LUIS through the year.
NAVITIME JAPAN
PRO
January 16, 2018
Tweet
Share
More Decks by NAVITIME JAPAN
See All by NAVITIME JAPAN
見えないユーザの声はログに埋もれている! ~ログから具体的なユーザの体験を数値化した事例紹介~
navitimejapan
PRO
6
1.7k
ユーザーのためなら 『デザイン』 以外にも手を伸ばせる
navitimejapan
PRO
2
1k
フツーのIT女子が、 Engineering Managerになるまで
navitimejapan
PRO
3
130
不確実性に打ち勝つOKR戦略/How to manage uncertainty with OKR strategy
navitimejapan
PRO
4
3k
アジャイルを小さいままで 組織に広める 二周目 / Agile Transformation in NAVITIME JAPAN iteration 2
navitimejapan
PRO
4
1.2k
変更障害率0%よりも「継続的な学習と実験」を価値とする 〜障害を「起こってはならないもの」としていた組織がDirtの実施に至るまで〜 / DevOps Transformation in NAVITIME JAPAN
navitimejapan
PRO
7
4.8k
こうしてふりかえりは終わってしまった / A Demise of a retrospective
navitimejapan
PRO
44
27k
もーひとつの時間がない症候群 / Yet Another SOT Syndrome
navitimejapan
PRO
1
2.1k
シーズン2〜スクラムチームのバトンを渡す〜 / Season 2 -pass the button of a scrum team-
navitimejapan
PRO
2
2.9k
Other Decks in Technology
See All in Technology
サービス開発を前に進めるために 新米リードエンジニアが 取り組んだこと / Steps Taken by a Novice Lead Engineer to Advance Service Development
nologyance
0
180
OSSコミットしてZennの課題を解決した話
dyoshikawa1993
0
150
ここがすごいよ! AWS Systems Manager!
saichan11
0
1.8k
「我々はどこに向かっているのか」を問い続けるための仕組みづくり / Establishing a System for Continuous Inquiry about where we are
daitasu
0
170
成長期に歩みを止めないための創業期の開発文化形成
mayah
6
420
エンジニアリングマネージャーはどう学んでいくのか #devsumi / How Do Engineering Managers Continue to Learn and Grow?
expajp
4
1.3k
20240724_cm_odyssey_hibiyatech
hiashisan
0
110
推薦システムを本番導入する上で一番優先すべきだったこと~NewsPicks記事推薦機能の改善事例を元に~
morinota
0
130
運用改善、不都合な真実 / 20240722-ssmjp-kaizen
opelab
17
8.4k
DDDにおける認可の扱いとKotlinにおける実装パターン / authorization-for-ddd-and-kotlin-implement-pattern
urmot
4
390
データ分析基盤を作ってみよう~設計編~
nrinetcom
PRO
1
110
Azure Pipelinesを使用したCICDベースラインアーキテクチャ実践
yuriemori
0
190
Featured
See All Featured
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
325
21k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
26
1.8k
GraphQLとの向き合い方2022年版
quramy
36
13k
What the flash - Photography Introduction
edds
65
11k
Building Effective Engineering Teams - LeadDev
addyosmani
47
2.2k
Designing on Purpose - Digital PM Summit 2013
jponch
113
6.6k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
224
21k
Rebuilding a faster, lazier Slack
samanthasiow
78
8.5k
Documentation Writing (for coders)
carmenintech
63
4.2k
Bootstrapping a Software Product
garrettdimon
PRO
304
110k
Creatively Recalculating Your Daily Design Routine
revolveconf
214
11k
Why Our Code Smells
bkeepers
PRO
332
56k
Transcript
What understood about that we’ve used LUIS through the year
Shinichi Tanabe January 12, 2018 Minami Aoyama Night #5
Speaker Shinichi Tanabe (田邊 晋一/たなべ しんいち) • NAVITIME JAPAN
Co., Ltd. ◦ Joined in 2008 ◦ Cogbot project ◦ Programmer
Products
None
Encounter
September 15, 2016
None
None
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
None
Step2. Add intent
None
Step3. Add utterances
None
Step4. Add entities
None
None
Step5. Train
None
Step6. Test
None
None
None
None
None
Step7. Publish
None
None
That’s all!
Furthermore...
You can get a happy bonus.
Versioning
None
None
None
None
Runs fast and smart
Comparison between and LUIS Dialogflow
Test model
Test model Intent Places.FindPlace Utterances 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 sec Dialogflow 4 - 8 sec
The training speed result of test model
Precision and recall
Test utterance LUIS Dialogflow Intent 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 utterance LUIS Dialogflow Intent 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.
Questions 1. 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 pattern Utterance : Intent ≒ 1 : 1
Use or copy pre-build model positively.
None
None
2. How do we know accuracy and precision?
Comprehensive test on model
Batch testing
Test result details in a visualized view.
Error matrix
True positive True negative Green zone indicates correct prediction
False negative False positive Red zone indicates incorrect prediction
3. When will he go GA?
LUIS is now GA!!
How to get along with LUIS
Points 1. 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!