SlideShare uma empresa Scribd logo
1 de 43
Build Message Bot
With Neural Network
2016/08/22
Billy Yang
Register New Bot
• The callback URL must use HTTPS
• Channel ID, Secret and MID
• Server IP Whitelist
• Dummy friend for testing.
• Trial bot can send/receive
message.
• Business account support Mission
Sticker, Link Message, Make
browsing your website from the
LINE app seamless for users.
Mission Sticker Example :
Tokyo Disney
http://official-blog.line.me/tw-biz/archives/57396837.html
Send/Receive Message
Send message
method=POST
url=https://trialbot-api.line.me/event
Receive message
method=POST
url=YOUR CALLBACK URL
{'result': [
{'content': {
'contentType': 1,
'createdTime': 1469373366186,
'deliveredTime': 0,
'from': USER_MID,
'id': ‘4656604667064’,
'text': 'Hello LINE Bot API',
'to': [MID],
'toType': 1},…..
Message Bot
• ELIZA(1966, http://nlp-addiction.com/eliza/)
• seemed to be able to fool users into believing that they
were conversing with a real human
• recognition of cue words or phrases in the input, and the
output of corresponding pre-prepared or pre-programmed
responses
Message Bot
" " Plurk Plurk YAHOO
. .
Message Bot
Viv Techcrunch demo
Microsoft Tay
Recurrent Neural
Network(RNN)
ht-1 +
xt
wi
wh
sigmoid ht
wo
softmax
yt
RNN
RNN
x
y
h
RNN
x0
y0
RNN
x1
y1
RNN
x2
y2
h0 h1
time
Recurrent Neural
Network(RNN)
Backpropagation
though time
Long Short-Term Memory
Network(LSTM)
Output Layer
Input Layer
Forget
Layermemory
LSTM
signal
signal
signal
x
y
LSTM : Forget Layer
ht-1
xt
ht
yt
LSTM
Ct-1 x Ct
Forget
Gate
w1 w2
LSTM : Input Layer
ht-1
xt
ht
yt
LSTM
tanh
w4w3
+
w6w5
Ct-1 x
x
Ct
Forget
Gate
w1 w2
Input
Gate
LSTM :
Forget Layer + Input Layer
ht-1
xt
ht
yt
LSTM
tanh
w4w3
+
w6w5
Ct-1 x
x
+ Ct
Forget
Gate
w1 w2
Input
Gate
Long Short-Term Memory
Network(LSTM)
Output Gate
Input Gate
Forget
Gatememory
LSTM
signal
signal
signal
LSTM :
Forget Layer + Input Layer
ht-1
xt
ht
yt
LSTM
tanh
w4w3
+
w6w5
Ct-1 x
x
+ Ct
Forget
Gate
w1 w2
Input
Gate
LSTM : Output Layer
ht-1
xt
ht
yt
LSTM
tanh
w4w3
+
w6w5
Ct-1 x
x
+ Ct
w8w7
xtanh
Forget
Gate
w1 w2
Input
Gate
Output
Gate
LSTM : All Layers
ht-1
xt
ht
yt
LSTM
tanh
w4w3
+
w6w5
Ct-1 x
x
+ Ct
w8w7
xtanh
softmax
Forget
Gate
w1 w2
Input
Gate
Output
Gate
LSTM : All Layers
ht-1
+
xt
w2w1
sigmoid
ht
yt
LSTM
sigmoid tanh
+
w4w3
+
w6w5
Ct-1 x
x
+ Ct
+
w8w7
sigmoid
xtanh
softmax
Long Short-Term Memory
Network(LSTM)
LSTM
x
y
h,c
LSTM
x0
y0
LSTM
x1
y1
LSTM
x2
y2
h0 h1
time
c0 c1
LSTM reduce vanishing gradient problem
Recurrent Neural
Network(RNN)
ht-1 +
xt
wi
wh
sigmoid ht
wo
softmax
yt
RNN
RNN
x
y
h
RNN
x0
y0
RNN
x1
y1
RNN
x2
y2
h0 h1
time
Gated Recurrent
Network(GRU)
ht-1
xt
yt
GRU
tanh
w4w3
+
w6w5
x
x
+ ht
softmax
Update
Gate
w1 w2
Reset
Gate
x
1-
GRU :
Don’t Update Memory!
ht-1
xt
yt
GRU
tanh
w4w3
+
w6w5
x
x
+ ht
softmax
Don’t
Update
w1 w2
Reset
Gate
x
1-
0
1
GRU : Update Memory
ht-1
xt
yt
GRU
tanh
w4w3
+
w6w5
x
x
+ ht
softmax
Update
w1 w2
Don’t
Reset
x
1-
1
0
1
GRU : Reset Memory
ht-1
xt
yt
GRU
tanh
w4w3
+
w6w5
x
x
+ ht
softmax
Update
w1 w2
Reset x
1-
1
0
0
0
Application
? ? ...
Show and Tell: A Neural
Image Caption Generator
Google
Inception
Network
+
Batch
Normalization
http://nic.droppages.com/
Sequence to sequence
Neural Network
* On the WMT’14 English to French translation task,we obtained a
BLEU score of 34.81
* This is by far the best result achieved by direct translation with large
neural net-works. For comparison, the BLEU score of an SMT
baseline on this dataset is 33.30
venturebeat.com
“Google Translate could become more accurate soon thanks to deep
learning” 2016/03
engadget.com
“Google is using neural network to improve Translate” 2016/03
Sequence to sequence
Neural Network
* Each box in the picture most commonly a GRU cell or an LSTM cell.
RNN
x
RNN RNN RNN
time
RNN
y
RNN
EOF
encoder decoder
Good
RNN
Job
context
vector
Sequence to sequence
Neural Network
• Reversing source words improve test BLEU scores
time
EOF
Good Job
context
vector
layer 1
layer 3
layer 4
32M 32M
• Made sure that all sentences in a minibatch are roughly of the same length
Sequence to sequence
Neural Network
• We can use this model for machine translation, question/
answering, and conversations without major changes in
the architecture
• A potential issue with this encoder–decoder approach is
that a neural network needs to be able to compress all the
necessary information of a source sentence into a fixed-
length vector. This may make it difficult for the neural
network to cope with long sentences,
Application
. IT Helpdesk
Troubleshooting dataset
Google Inbox App
Smart Reply
announce at 2015/11
Machine:hi
Human:hello
Machine:could you please let me know
what are the operating systems you are
using ?
Human:i am using linux
Machine:ok it was in the ssl vpn on which
you stated it was broken
….
Image Recognition
announce at 2015/07, Not Seq2Seq
Sequence to sequence Neural
Network+Attention(RNNSearch)
RNN
x0
RNN
x1
RNN
x2
h0
f h1
f
RNN
x2
RNN
x1
RNN
x0
h0
bh1
b
time
RNN
EOF
Good
RNN
Job
[h1
b,h1
f]
[h0
b,h0
f]
c0 c1
+ +
a00
a01
a10
a11
context
vector
annotation
bi-directional RNN
Facebook Research :
Question/Answering
* All NLP/AI tasks can be reduced to question answering
* The bAbI project(Artificial Tasks for Artificial Intelligence)
End-to-End Memory Network :
Single Hop
input story
weighted sum{c1,c2,c3}
{a1,a2,a3}
softmax
{0.2, 0.1, 0.7}
dot product
input question
WC
WA
?
u1
WB
+o1 u2
softmax
WO
{ :0.9, :0.1}
constructing memory vectors with Bag-of-Words
m1=V +V +V +V
Memory Module Controller
weighted sum
End-to-End Memory Network :
Two Hops
input story
softmax
dot product
input question
WC2
WA1
?
u1
WB
+o2 u3
softmax
WO
{ :0.9, :0.1}
Memory Module Controller
+o1
u2
weighted sum
softmax
dot product
weight sharing methods
1. Ak+1=Ck,
2. A1=A2=…=AK and C1=C2=…=CK
WA2
WC1
http://cims.nyu.edu/~sainbar/memnn_nips_pdf.pdf
Memory Network
Compare with RNNSearch, memory network
can be considered as
an attention model with multiple hops(lookup) and out of order
Ask Me Anything: Dynamic Memory
Networks for Natural Language
Processing
http://cs224d.stanford.edu/lectures/CS224d-Lecture17.pdf
Reference
Sequence to Sequence Learning with Neural Networks.
Ilya Sutskever(OpenAI Research Director, Andrew Ng PostDoc), Oriol Vinyals &
Quoc V. Le
2014/09
Neural Machine Translation by Jointly Learning to Align and Translate.
Dzmitry Bahdanau(Theano Contributor), Kyunghyun Cho &Yoshua Bengio
2014/09
A Neural Conversational Model
Oriol Vinyals(Tensorflow Contributor) & Quoc Le
2015/01
Memory Networks
Jason Weston, Sumit Chopra & Antoine Bordes
2014/10
End-To-End Memory Networks
Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston & Rob Fergus
2015/01
Thank You :)

Mais conteúdo relacionado

Destaque

Cellular network
Cellular networkCellular network
Cellular network
Mr SMAK
 
Synodiance > Recherche Vocale - SEO Campus Paris - 07/04/2016
Synodiance > Recherche Vocale - SEO Campus Paris - 07/04/2016Synodiance > Recherche Vocale - SEO Campus Paris - 07/04/2016
Synodiance > Recherche Vocale - SEO Campus Paris - 07/04/2016
Search Foresight
 

Destaque (20)

RNN & LSTM
RNN & LSTMRNN & LSTM
RNN & LSTM
 
Word2vec (中文)
Word2vec (中文)Word2vec (中文)
Word2vec (中文)
 
Introduction For seq2seq(sequence to sequence) and RNN
Introduction For seq2seq(sequence to sequence) and RNNIntroduction For seq2seq(sequence to sequence) and RNN
Introduction For seq2seq(sequence to sequence) and RNN
 
Tutorial on Question Answering Systems
Tutorial on Question Answering Systems Tutorial on Question Answering Systems
Tutorial on Question Answering Systems
 
Conversational interfaces - beyond the hype
Conversational interfaces - beyond the hypeConversational interfaces - beyond the hype
Conversational interfaces - beyond the hype
 
Machine Learning : comparing neural network methods
Machine Learning : comparing neural network methodsMachine Learning : comparing neural network methods
Machine Learning : comparing neural network methods
 
The Great Customer Experience
The Great Customer ExperienceThe Great Customer Experience
The Great Customer Experience
 
『밑바닥부터 시작하는 딥러닝』 - 미리보기
『밑바닥부터 시작하는 딥러닝』 - 미리보기『밑바닥부터 시작하는 딥러닝』 - 미리보기
『밑바닥부터 시작하는 딥러닝』 - 미리보기
 
Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model (UP...
Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model (UP...Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model (UP...
Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model (UP...
 
GPU Accelerated Natural Language Processing by Guillermo Molini
GPU Accelerated Natural Language Processing by Guillermo MoliniGPU Accelerated Natural Language Processing by Guillermo Molini
GPU Accelerated Natural Language Processing by Guillermo Molini
 
Understanding RNN and LSTM
Understanding RNN and LSTMUnderstanding RNN and LSTM
Understanding RNN and LSTM
 
Réseaux de neurones
Réseaux de neurones Réseaux de neurones
Réseaux de neurones
 
Deep Learning Models for Question Answering
Deep Learning Models for Question AnsweringDeep Learning Models for Question Answering
Deep Learning Models for Question Answering
 
淺談HTTP發展趨勢與SPDY
淺談HTTP發展趨勢與SPDY淺談HTTP發展趨勢與SPDY
淺談HTTP發展趨勢與SPDY
 
HDFS與MapReduce架構研討
HDFS與MapReduce架構研討HDFS與MapReduce架構研討
HDFS與MapReduce架構研討
 
Chat bots: what, why and (a bit of) how?
Chat bots: what, why and (a bit of) how?Chat bots: what, why and (a bit of) how?
Chat bots: what, why and (a bit of) how?
 
Cellular network
Cellular networkCellular network
Cellular network
 
MLP深層学習 LSTM
MLP深層学習 LSTMMLP深層学習 LSTM
MLP深層学習 LSTM
 
word2vec, LDA, and introducing a new hybrid algorithm: lda2vec
word2vec, LDA, and introducing a new hybrid algorithm: lda2vecword2vec, LDA, and introducing a new hybrid algorithm: lda2vec
word2vec, LDA, and introducing a new hybrid algorithm: lda2vec
 
Synodiance > Recherche Vocale - SEO Campus Paris - 07/04/2016
Synodiance > Recherche Vocale - SEO Campus Paris - 07/04/2016Synodiance > Recherche Vocale - SEO Campus Paris - 07/04/2016
Synodiance > Recherche Vocale - SEO Campus Paris - 07/04/2016
 

Semelhante a Build Message Bot With Neural Network

Php Inside - confoo 2011 - Derick Rethans
Php Inside -  confoo 2011 - Derick RethansPhp Inside -  confoo 2011 - Derick Rethans
Php Inside - confoo 2011 - Derick Rethans
Bachkoutou Toutou
 
Final ProjectFinal Project Details Description Given a spec.docx
Final ProjectFinal Project Details Description  Given a spec.docxFinal ProjectFinal Project Details Description  Given a spec.docx
Final ProjectFinal Project Details Description Given a spec.docx
AKHIL969626
 
Ogdc 2013 cross platform game development with html5
Ogdc 2013 cross platform game development with html5Ogdc 2013 cross platform game development with html5
Ogdc 2013 cross platform game development with html5
Son Aris
 

Semelhante a Build Message Bot With Neural Network (20)

Making PHP Smarter - Dutch PHP 2023.pptx
Making PHP Smarter - Dutch PHP 2023.pptxMaking PHP Smarter - Dutch PHP 2023.pptx
Making PHP Smarter - Dutch PHP 2023.pptx
 
[Connect(); // Japan 2016] Microsoft の AI 開発最新アップデート ~ Cognitive Services からA...
[Connect(); // Japan 2016] Microsoft の AI 開発最新アップデート ~ Cognitive Services からA...[Connect(); // Japan 2016] Microsoft の AI 開発最新アップデート ~ Cognitive Services からA...
[Connect(); // Japan 2016] Microsoft の AI 開発最新アップデート ~ Cognitive Services からA...
 
Php Inside - confoo 2011 - Derick Rethans
Php Inside -  confoo 2011 - Derick RethansPhp Inside -  confoo 2011 - Derick Rethans
Php Inside - confoo 2011 - Derick Rethans
 
Final ProjectFinal Project Details Description Given a spec.docx
Final ProjectFinal Project Details Description  Given a spec.docxFinal ProjectFinal Project Details Description  Given a spec.docx
Final ProjectFinal Project Details Description Given a spec.docx
 
Serverless Data Architecture at scale on Google Cloud Platform
Serverless Data Architecture at scale on Google Cloud PlatformServerless Data Architecture at scale on Google Cloud Platform
Serverless Data Architecture at scale on Google Cloud Platform
 
Microservices Antipatterns
Microservices AntipatternsMicroservices Antipatterns
Microservices Antipatterns
 
Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)Deep Dive on Deep Learning (June 2018)
Deep Dive on Deep Learning (June 2018)
 
Going open source with small teams
Going open source with small teamsGoing open source with small teams
Going open source with small teams
 
clicks2conversations.pdf
clicks2conversations.pdfclicks2conversations.pdf
clicks2conversations.pdf
 
New Business Models enabled by Blockchain
New Business Models enabled by BlockchainNew Business Models enabled by Blockchain
New Business Models enabled by Blockchain
 
OSMC 2023 | Experiments with OpenSearch and AI by Jochen Kressin & Leanne La...
OSMC 2023 | Experiments with OpenSearch and AI by Jochen Kressin &  Leanne La...OSMC 2023 | Experiments with OpenSearch and AI by Jochen Kressin &  Leanne La...
OSMC 2023 | Experiments with OpenSearch and AI by Jochen Kressin & Leanne La...
 
Building an Empire with PowerShell
Building an Empire with PowerShellBuilding an Empire with PowerShell
Building an Empire with PowerShell
 
The Digital Home: Developing Services and Applications for Media Center
The Digital Home: Developing Services and Applications for Media CenterThe Digital Home: Developing Services and Applications for Media Center
The Digital Home: Developing Services and Applications for Media Center
 
Overview Of Parallel Development - Ericnel
Overview Of Parallel Development -  EricnelOverview Of Parallel Development -  Ericnel
Overview Of Parallel Development - Ericnel
 
Netty @Apple: Large Scale Deployment/Connectivity
Netty @Apple: Large Scale Deployment/ConnectivityNetty @Apple: Large Scale Deployment/Connectivity
Netty @Apple: Large Scale Deployment/Connectivity
 
A Practical Road to SaaS in Python
A Practical Road to SaaS in PythonA Practical Road to SaaS in Python
A Practical Road to SaaS in Python
 
T-Mobile and Elastic
T-Mobile and ElasticT-Mobile and Elastic
T-Mobile and Elastic
 
Screencasting and Presenting for Engineers
Screencasting and Presenting for EngineersScreencasting and Presenting for Engineers
Screencasting and Presenting for Engineers
 
OGDC2013_ Cross platform game development with html5_ Mr Hoang Dinh Quang
OGDC2013_ Cross platform game development with html5_ Mr Hoang Dinh QuangOGDC2013_ Cross platform game development with html5_ Mr Hoang Dinh Quang
OGDC2013_ Cross platform game development with html5_ Mr Hoang Dinh Quang
 
Ogdc 2013 cross platform game development with html5
Ogdc 2013 cross platform game development with html5Ogdc 2013 cross platform game development with html5
Ogdc 2013 cross platform game development with html5
 

Último

Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
amitlee9823
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
amitlee9823
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
amitlee9823
 
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
only4webmaster01
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
amitlee9823
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
MarinCaroMartnezBerg
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
ZurliaSoop
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
amitlee9823
 
Probability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter LessonsProbability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter Lessons
JoseMangaJr1
 

Último (20)

BigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptxBigBuy dropshipping via API with DroFx.pptx
BigBuy dropshipping via API with DroFx.pptx
 
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
Call Girls Bannerghatta Road Just Call 👗 7737669865 👗 Top Class Call Girl Ser...
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
 
Week-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionWeek-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interaction
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men  🔝Bangalore🔝   Esc...
➥🔝 7737669865 🔝▻ Bangalore Call-girls in Women Seeking Men 🔝Bangalore🔝 Esc...
 
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Saket (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort ServiceBDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
 
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts ServiceCall Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
Call Girls In Shalimar Bagh ( Delhi) 9953330565 Escorts Service
 
CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptx
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
Escorts Service Kumaraswamy Layout ☎ 7737669865☎ Book Your One night Stand (B...
 
Probability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter LessonsProbability Grade 10 Third Quarter Lessons
Probability Grade 10 Third Quarter Lessons
 

Build Message Bot With Neural Network

  • 1. Build Message Bot With Neural Network 2016/08/22 Billy Yang
  • 2. Register New Bot • The callback URL must use HTTPS • Channel ID, Secret and MID • Server IP Whitelist • Dummy friend for testing. • Trial bot can send/receive message. • Business account support Mission Sticker, Link Message, Make browsing your website from the LINE app seamless for users.
  • 3. Mission Sticker Example : Tokyo Disney http://official-blog.line.me/tw-biz/archives/57396837.html
  • 4. Send/Receive Message Send message method=POST url=https://trialbot-api.line.me/event Receive message method=POST url=YOUR CALLBACK URL {'result': [ {'content': { 'contentType': 1, 'createdTime': 1469373366186, 'deliveredTime': 0, 'from': USER_MID, 'id': ‘4656604667064’, 'text': 'Hello LINE Bot API', 'to': [MID], 'toType': 1},…..
  • 5.
  • 6. Message Bot • ELIZA(1966, http://nlp-addiction.com/eliza/) • seemed to be able to fool users into believing that they were conversing with a real human • recognition of cue words or phrases in the input, and the output of corresponding pre-prepared or pre-programmed responses
  • 7. Message Bot " " Plurk Plurk YAHOO . .
  • 8. Message Bot Viv Techcrunch demo Microsoft Tay
  • 9. Recurrent Neural Network(RNN) ht-1 + xt wi wh sigmoid ht wo softmax yt RNN RNN x y h RNN x0 y0 RNN x1 y1 RNN x2 y2 h0 h1 time
  • 11. Long Short-Term Memory Network(LSTM) Output Layer Input Layer Forget Layermemory LSTM signal signal signal x y
  • 12. LSTM : Forget Layer ht-1 xt ht yt LSTM Ct-1 x Ct Forget Gate w1 w2
  • 13. LSTM : Input Layer ht-1 xt ht yt LSTM tanh w4w3 + w6w5 Ct-1 x x Ct Forget Gate w1 w2 Input Gate
  • 14. LSTM : Forget Layer + Input Layer ht-1 xt ht yt LSTM tanh w4w3 + w6w5 Ct-1 x x + Ct Forget Gate w1 w2 Input Gate
  • 15. Long Short-Term Memory Network(LSTM) Output Gate Input Gate Forget Gatememory LSTM signal signal signal
  • 16. LSTM : Forget Layer + Input Layer ht-1 xt ht yt LSTM tanh w4w3 + w6w5 Ct-1 x x + Ct Forget Gate w1 w2 Input Gate
  • 17. LSTM : Output Layer ht-1 xt ht yt LSTM tanh w4w3 + w6w5 Ct-1 x x + Ct w8w7 xtanh Forget Gate w1 w2 Input Gate Output Gate
  • 18. LSTM : All Layers ht-1 xt ht yt LSTM tanh w4w3 + w6w5 Ct-1 x x + Ct w8w7 xtanh softmax Forget Gate w1 w2 Input Gate Output Gate
  • 19. LSTM : All Layers ht-1 + xt w2w1 sigmoid ht yt LSTM sigmoid tanh + w4w3 + w6w5 Ct-1 x x + Ct + w8w7 sigmoid xtanh softmax
  • 21. Recurrent Neural Network(RNN) ht-1 + xt wi wh sigmoid ht wo softmax yt RNN RNN x y h RNN x0 y0 RNN x1 y1 RNN x2 y2 h0 h1 time
  • 23. GRU : Don’t Update Memory! ht-1 xt yt GRU tanh w4w3 + w6w5 x x + ht softmax Don’t Update w1 w2 Reset Gate x 1- 0 1
  • 24. GRU : Update Memory ht-1 xt yt GRU tanh w4w3 + w6w5 x x + ht softmax Update w1 w2 Don’t Reset x 1- 1 0 1
  • 25. GRU : Reset Memory ht-1 xt yt GRU tanh w4w3 + w6w5 x x + ht softmax Update w1 w2 Reset x 1- 1 0 0 0
  • 27. Show and Tell: A Neural Image Caption Generator Google Inception Network + Batch Normalization
  • 29. Sequence to sequence Neural Network * On the WMT’14 English to French translation task,we obtained a BLEU score of 34.81 * This is by far the best result achieved by direct translation with large neural net-works. For comparison, the BLEU score of an SMT baseline on this dataset is 33.30 venturebeat.com “Google Translate could become more accurate soon thanks to deep learning” 2016/03 engadget.com “Google is using neural network to improve Translate” 2016/03
  • 30. Sequence to sequence Neural Network * Each box in the picture most commonly a GRU cell or an LSTM cell. RNN x RNN RNN RNN time RNN y RNN EOF encoder decoder Good RNN Job context vector
  • 31. Sequence to sequence Neural Network • Reversing source words improve test BLEU scores time EOF Good Job context vector layer 1 layer 3 layer 4 32M 32M • Made sure that all sentences in a minibatch are roughly of the same length
  • 32. Sequence to sequence Neural Network • We can use this model for machine translation, question/ answering, and conversations without major changes in the architecture • A potential issue with this encoder–decoder approach is that a neural network needs to be able to compress all the necessary information of a source sentence into a fixed- length vector. This may make it difficult for the neural network to cope with long sentences,
  • 33. Application . IT Helpdesk Troubleshooting dataset Google Inbox App Smart Reply announce at 2015/11 Machine:hi Human:hello Machine:could you please let me know what are the operating systems you are using ? Human:i am using linux Machine:ok it was in the ssl vpn on which you stated it was broken …. Image Recognition announce at 2015/07, Not Seq2Seq
  • 34.
  • 35. Sequence to sequence Neural Network+Attention(RNNSearch) RNN x0 RNN x1 RNN x2 h0 f h1 f RNN x2 RNN x1 RNN x0 h0 bh1 b time RNN EOF Good RNN Job [h1 b,h1 f] [h0 b,h0 f] c0 c1 + + a00 a01 a10 a11 context vector annotation bi-directional RNN
  • 36. Facebook Research : Question/Answering * All NLP/AI tasks can be reduced to question answering * The bAbI project(Artificial Tasks for Artificial Intelligence)
  • 37. End-to-End Memory Network : Single Hop input story weighted sum{c1,c2,c3} {a1,a2,a3} softmax {0.2, 0.1, 0.7} dot product input question WC WA ? u1 WB +o1 u2 softmax WO { :0.9, :0.1} constructing memory vectors with Bag-of-Words m1=V +V +V +V Memory Module Controller
  • 38. weighted sum End-to-End Memory Network : Two Hops input story softmax dot product input question WC2 WA1 ? u1 WB +o2 u3 softmax WO { :0.9, :0.1} Memory Module Controller +o1 u2 weighted sum softmax dot product weight sharing methods 1. Ak+1=Ck, 2. A1=A2=…=AK and C1=C2=…=CK WA2 WC1 http://cims.nyu.edu/~sainbar/memnn_nips_pdf.pdf
  • 39. Memory Network Compare with RNNSearch, memory network can be considered as an attention model with multiple hops(lookup) and out of order
  • 40.
  • 41. Ask Me Anything: Dynamic Memory Networks for Natural Language Processing http://cs224d.stanford.edu/lectures/CS224d-Lecture17.pdf
  • 42. Reference Sequence to Sequence Learning with Neural Networks. Ilya Sutskever(OpenAI Research Director, Andrew Ng PostDoc), Oriol Vinyals & Quoc V. Le 2014/09 Neural Machine Translation by Jointly Learning to Align and Translate. Dzmitry Bahdanau(Theano Contributor), Kyunghyun Cho &Yoshua Bengio 2014/09 A Neural Conversational Model Oriol Vinyals(Tensorflow Contributor) & Quoc Le 2015/01 Memory Networks Jason Weston, Sumit Chopra & Antoine Bordes 2014/10 End-To-End Memory Networks Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston & Rob Fergus 2015/01