SlideShare a Scribd company logo
Neural Question Generation
CSS 801
Seminar Presentation
ARIJIT MUKHERJEE
17305T0021
● Sequence Processing With Neural Network
● Question Answering Tasks
● Memory Networks
● Match-LSTM + Pointer Networks
● R-NET S-NET
● Neural Question Generation
● Question-Generation Question-Answering Duality
● Natural Language Generation with GANs
● Way-Forward
2
Sequence Processing with Neural Networks
● A ‘n’ length sequence can be encoded to ‘nxd’ dimensional vector and then
passed to a feed-forward network whose input is ‘nxd’ but doing so we lose the
temporal property of the sequence. What we do ?
● We share the same feed-forward network for all our time step recurrently,
instead of taking only the ‘d’ size input at each time step we also pass the
previous timestep’s output as input.
3
Input0
h0 h1
Input1
hn
Inputn
...
Recurrent Neural Network Training Problem
4
Loss(y,o)Loss(y,o)Loss(y,o)
Vanishing Gradients or Exploding Gradients !!
Image source : François Deloche (CCASAI)
Long-Short Term Memory
5
Image source : Understanding LSTMs
My name is Arijit
Context
<SOS>
What is your name
What is your
Encoder
Decoder
6
Encoder
Decoder
Attention
7
My name is Arijit
<SOS>
What is your name
What is your
Encoder Hidden States
+
Decoder
Hidden
State (t-1)
● Sequence Processing With Neural Network
● Question Answering Tasks
● Memory Networks
● Match-LSTM + Pointer Networks
● R-NET S-NET
● Neural Question Generation
● Question-Generation Question-Answering Duality
● Natural Language Generation with GANs
● Way-Forward
8
Question Answering Task
The (20) QA bAbI tasks
● It is available for hindi and english
● The stories are generated by a
simulator
● It have two variants of 1k and 10k
samples.
● There are 20 tasks with different
difficulty levels
9
Stanford Question Answering Dataset
● 536 Wikipedia Articles.
● 23,215 total paragraphs.
● 100,000+ question-answer pairs.
● Evaluation metrics
○ Exact Match Score
○ F1 Score
● Sequence Processing With Neural Network
● Question Answering Tasks
● Memory Networks
● Match-LSTM + Pointer Networks
● R-NET S-NET
● Neural Question Generation
● Question-Generation Question-Answering Duality
● Natural Language Generation with GANs
● Way-Forward
10
Memory Network
11
I
Input
G
Generalizer O
Output
R
Response
Memory
Input X
I(X)
I(X)
Update
memory
given I(X)
M
O(M,X)
Generated
Response
Story
Question
Memory Neural Network MemNN
12
I
Input
G
Generalizer O
Output
R
Response
Memory
Input X
I(X)
I(X)
Update
memory
given I(X)
M
O(M,X)
Generated
Response
Embedding
Copy input Xi to memory Xi
End to End Memory Network MemN2N Single Layer
13
Image source : End to End Memory Network
End-to-End Memory Networks MemN2N Multi Layer
14
Image source : End to End Memory Network
15
Image source : End to End Memory Network
● Sequence Processing With Neural Network
● Question Answering Tasks
● Memory Networks
● Match-LSTM + Pointer Networks
● R-NET S-NET
● Neural Question Generation
● Question-Generation Question-Answering Duality
● Natural Language Generation with GANs
● Way-Forward
16
17
Natural Language
Inference
P Premise H Hypothesis
Y Label {Entrailment, Contradiction, Neutral}
18
Match LSTM
Match LSTM
Match LSTM Performance
19
Image source : Wange et al.
Pointer
Network
20X1 X2 X3 X4
<SOS>
C1 C2 C3 C4
C1 C2 C3
Encoder Hidden States
+
Decoder
Hidden
State (t-1)
Match LSTM + Pointer Network
21
Hq
a1
Q1 Q2 Q3 Q4 Qn P1 P2 P3 Pm
a2 a3 am
hr
1 hr
2 hr
3 hr
m
MATCH-LSTM
LAYER
LSTM
PREPROCESSING
LAYER
Match-LSTM + Pointer Network Answer Pointer Layer
hr
1 hr
2 hr
3 hr
m
Sequence
Model
hr
1 hr
2 hr
3 hr
m
as ae
Boundary
Model
23Image source : Wange & Jiang.
● Sequence Processing With Neural Network
● Question Answering Tasks
● Memory Networks
● Match-LSTM + Pointer Networks
● R-NET S-NET
● Neural Question Generation
● Question-Generation Question-Answering Duality
● Natural Language Generation with GANs
● Way-Forward
24
Changes From Wang & Jiang
● Instead of LSTM use BiDirectional GRUs, GRUs have less training params that
of LSTMs
● In the last pointer layer ha
0 will play a vital role, so we need a proper
initialization, here they used attention pooling to initialize.
● Match-LSTM layer performs matching between question and paragraph, we
can add another layer and match the paragraph with the paragraph.
● Scrap Sequence Model.
● Adding Gates to intermediate hidden states in between layers.
25
26Image source : R-Net
Experiments R-Net
27
Image source : R-Net
S-Net
28
● R-Net Only predicts the starting and ending index of an continous answer while
S-Net tries to synthesize answer.
● S-Net have to main components
○ Evidence Extraction
○ Answer Synthesis
● Evidence Extraction uses R-Net without Passage matching and Adds another
output as passage ranking.
● Answer Synthesis Model Generates answer given paragraph and start and end
token.
● Two components are trained separately.
Evidence
Extraction
29Image source : S-Net
Answer Synthesis
30
Image source : S-Net
● Sequence Processing With Neural Network
● Question Answering Tasks
● Memory Networks
● Match-LSTM + Pointer Networks
● R-NET S-NET
● Neural Question Generation
● Question-Generation Question-Answering Duality
● Natural Language Generation with GANs
● Way-Forward
31
32
Learning to Ask Neural Question Generation
● This paper proposes a Question Generation System powered by the
Seq2Seq architecture and Attention Mechanism .
● Which Encodes the Passage and the Answer to generate a Question .
● The Evaluation is done on the basis of Machine Translation Metrics like
BLEU , METEOR , ROUGE-L
Neural Question Generation
33
S1 S2 S3 S4
<SOS>
Q1 Q2 Q3 Q4
Q1 Q2 Q3
Sentence Hidden States
+Decoder
Hidden
State (t-1)
P1 P2 P3 P4
Paragraph Final
Hidden State
Experiments
34
Image source : Learning to Ask
● Sequence Processing With Neural Network
● Question Answering Tasks
● Memory Networks
● Match-LSTM + Pointer Networks
● R-NET S-NET
● Neural Question Generation
● Question-Generation Question-Answering Duality
● Natural Language Generation with GANs
● Way-Forward
35
Question-Answering Question-Generation Duality
36
Question
Generation
Question
Answering
Question
Answering
Loss
Question
Generation
Loss
Regularization Term to Connect both Tasks
Experiments
● QA model is defined by two
GRUs encoding question and
answer.
● Then creating a vector as
then pppppppppppassing to a
linear layer followed by a
sigmoid.
● The QG is an encoder decoder
model with attention.
37
Image source : QA QG dual task
● Sequence Processing With Neural Network
● Question Answering Tasks
● Memory Networks
● Match-LSTM + Pointer Networks
● R-NET S-NET
● Neural Question Generation
● Question-Generation Question-Answering Duality
● Natural Language Generation with GANs
● Way-Forward
38
Adversarial Generation of Language with GANs
39
Image source : KDnuggents
Blog, From GAN to WGA
Wasserstein GAN
40
Image source : WGAN Paper
Adversarial Generation of Natural Language
41Image source : Learning to Ask Paper
Experiment Language Generation Tasks
TASK CFG
● 248 production rules
● generate two sets of data one
consisting of samples of
length 5 and another
consisting of samples of
length 11.
● Each contains 100,000
samples.
● Set 1 vocabulary of size 36
tokens while the second have
45 tokens. 42Image source : Learning to Ask Paper
Chinese Poetry
● each line as a training example
with lines of length 5 (poem-5)
and length 7 (poem 7).
● BLEU-2 and BLEU-3 score on
corpus level for evaluation
Language Generation
● CMU-SE, PTB English
Language Modeling, Google
1billion sentences.
Conditional Language Generation
● Generate sentences
conditioned on Wh word and
sentiment
● Sequence Processing With Neural Network
● Question Answering Tasks
● Memory Networks
● Match-LSTM + Pointer Networks
● R-NET S-NET
● Neural Question Generation
● Question-Generation Question-Answering Duality
● Natural Language Generation with GANs
● Way-Forward
43
Way Forward
● Exploring Memory Networks for Question-Generation
● Incorporating Structured knowledge-bases in question-generation framework.
● Exploring Conditional GANs for Sequence to Sequence tasks.
● Improving the Learning to ask baseline and adding match-LSTMs to it.
● Conditional generation of questions with specific WH words and scores.
● Applying Question-Generation for Hindi Textbooks.
44
THANKS
45

More Related Content

What's hot

Multidimensional RNN
Multidimensional RNNMultidimensional RNN
Multidimensional RNN
Grigory Sapunov
 
Implementation of RSA Algorithm with Chinese Remainder Theorem for Modulus N ...
Implementation of RSA Algorithm with Chinese Remainder Theorem for Modulus N ...Implementation of RSA Algorithm with Chinese Remainder Theorem for Modulus N ...
Implementation of RSA Algorithm with Chinese Remainder Theorem for Modulus N ...
CSCJournals
 
Deep Learning for Computer Vision: Recurrent Neural Networks (UPC 2016)
Deep Learning for Computer Vision: Recurrent Neural Networks (UPC 2016)Deep Learning for Computer Vision: Recurrent Neural Networks (UPC 2016)
Deep Learning for Computer Vision: Recurrent Neural Networks (UPC 2016)
Universitat Politècnica de Catalunya
 
LSTM Tutorial
LSTM TutorialLSTM Tutorial
LSTM Tutorial
Ralph Schlosser
 
Recurrent Neural Networks for Text Analysis
Recurrent Neural Networks for Text AnalysisRecurrent Neural Networks for Text Analysis
Recurrent Neural Networks for Text Analysis
odsc
 
Advanced Neural Machine Translation (D4L2 Deep Learning for Speech and Langua...
Advanced Neural Machine Translation (D4L2 Deep Learning for Speech and Langua...Advanced Neural Machine Translation (D4L2 Deep Learning for Speech and Langua...
Advanced Neural Machine Translation (D4L2 Deep Learning for Speech and Langua...
Universitat Politècnica de Catalunya
 
Lecture 7: Recurrent Neural Networks
Lecture 7: Recurrent Neural NetworksLecture 7: Recurrent Neural Networks
Lecture 7: Recurrent Neural Networks
Sang Jun Lee
 
Rnn & Lstm
Rnn & LstmRnn & Lstm
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...
Universitat Politècnica de Catalunya
 
Software Frameworks for Deep Learning (D1L7 2017 UPC Deep Learning for Comput...
Software Frameworks for Deep Learning (D1L7 2017 UPC Deep Learning for Comput...Software Frameworks for Deep Learning (D1L7 2017 UPC Deep Learning for Comput...
Software Frameworks for Deep Learning (D1L7 2017 UPC Deep Learning for Comput...
Universitat Politècnica de Catalunya
 
Deep Learning for Machine Translation
Deep Learning for Machine TranslationDeep Learning for Machine Translation
Deep Learning for Machine Translation
Matīss ‎‎‎‎‎‎‎  
 
Simple regenerating codes: Network Coding for Cloud Storage
Simple regenerating codes: Network Coding for Cloud StorageSimple regenerating codes: Network Coding for Cloud Storage
Simple regenerating codes: Network Coding for Cloud StorageKevin Tong
 
Canalyzation in mathematical modeling
Canalyzation in mathematical modelingCanalyzation in mathematical modeling
Canalyzation in mathematical modeling
KNOWeSCAPE2014
 
Attention mechanisms with tensorflow
Attention mechanisms with tensorflowAttention mechanisms with tensorflow
Attention mechanisms with tensorflow
Keon Kim
 
Deep Learning for Chatbot (3/4)
Deep Learning for Chatbot (3/4)Deep Learning for Chatbot (3/4)
Deep Learning for Chatbot (3/4)
Jaemin Cho
 
Modeling Electronic Health Records with Recurrent Neural Networks
Modeling Electronic Health Records with Recurrent Neural NetworksModeling Electronic Health Records with Recurrent Neural Networks
Modeling Electronic Health Records with Recurrent Neural Networks
Josh Patterson
 
Deep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistryDeep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistry
Kenta Oono
 
Synthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep LearningSynthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep Learning
S N
 
Transformer Zoo (a deeper dive)
Transformer Zoo (a deeper dive)Transformer Zoo (a deeper dive)
Transformer Zoo (a deeper dive)
Grigory Sapunov
 
Introduction to deep learning in python and Matlab
Introduction to deep learning in python and MatlabIntroduction to deep learning in python and Matlab
Introduction to deep learning in python and Matlab
Imry Kissos
 

What's hot (20)

Multidimensional RNN
Multidimensional RNNMultidimensional RNN
Multidimensional RNN
 
Implementation of RSA Algorithm with Chinese Remainder Theorem for Modulus N ...
Implementation of RSA Algorithm with Chinese Remainder Theorem for Modulus N ...Implementation of RSA Algorithm with Chinese Remainder Theorem for Modulus N ...
Implementation of RSA Algorithm with Chinese Remainder Theorem for Modulus N ...
 
Deep Learning for Computer Vision: Recurrent Neural Networks (UPC 2016)
Deep Learning for Computer Vision: Recurrent Neural Networks (UPC 2016)Deep Learning for Computer Vision: Recurrent Neural Networks (UPC 2016)
Deep Learning for Computer Vision: Recurrent Neural Networks (UPC 2016)
 
LSTM Tutorial
LSTM TutorialLSTM Tutorial
LSTM Tutorial
 
Recurrent Neural Networks for Text Analysis
Recurrent Neural Networks for Text AnalysisRecurrent Neural Networks for Text Analysis
Recurrent Neural Networks for Text Analysis
 
Advanced Neural Machine Translation (D4L2 Deep Learning for Speech and Langua...
Advanced Neural Machine Translation (D4L2 Deep Learning for Speech and Langua...Advanced Neural Machine Translation (D4L2 Deep Learning for Speech and Langua...
Advanced Neural Machine Translation (D4L2 Deep Learning for Speech and Langua...
 
Lecture 7: Recurrent Neural Networks
Lecture 7: Recurrent Neural NetworksLecture 7: Recurrent Neural Networks
Lecture 7: Recurrent Neural Networks
 
Rnn & Lstm
Rnn & LstmRnn & Lstm
Rnn & Lstm
 
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...
Video Analysis with Recurrent Neural Networks (Master Computer Vision Barcelo...
 
Software Frameworks for Deep Learning (D1L7 2017 UPC Deep Learning for Comput...
Software Frameworks for Deep Learning (D1L7 2017 UPC Deep Learning for Comput...Software Frameworks for Deep Learning (D1L7 2017 UPC Deep Learning for Comput...
Software Frameworks for Deep Learning (D1L7 2017 UPC Deep Learning for Comput...
 
Deep Learning for Machine Translation
Deep Learning for Machine TranslationDeep Learning for Machine Translation
Deep Learning for Machine Translation
 
Simple regenerating codes: Network Coding for Cloud Storage
Simple regenerating codes: Network Coding for Cloud StorageSimple regenerating codes: Network Coding for Cloud Storage
Simple regenerating codes: Network Coding for Cloud Storage
 
Canalyzation in mathematical modeling
Canalyzation in mathematical modelingCanalyzation in mathematical modeling
Canalyzation in mathematical modeling
 
Attention mechanisms with tensorflow
Attention mechanisms with tensorflowAttention mechanisms with tensorflow
Attention mechanisms with tensorflow
 
Deep Learning for Chatbot (3/4)
Deep Learning for Chatbot (3/4)Deep Learning for Chatbot (3/4)
Deep Learning for Chatbot (3/4)
 
Modeling Electronic Health Records with Recurrent Neural Networks
Modeling Electronic Health Records with Recurrent Neural NetworksModeling Electronic Health Records with Recurrent Neural Networks
Modeling Electronic Health Records with Recurrent Neural Networks
 
Deep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistryDeep learning for molecules, introduction to chainer chemistry
Deep learning for molecules, introduction to chainer chemistry
 
Synthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep LearningSynthetic dialogue generation with Deep Learning
Synthetic dialogue generation with Deep Learning
 
Transformer Zoo (a deeper dive)
Transformer Zoo (a deeper dive)Transformer Zoo (a deeper dive)
Transformer Zoo (a deeper dive)
 
Introduction to deep learning in python and Matlab
Introduction to deep learning in python and MatlabIntroduction to deep learning in python and Matlab
Introduction to deep learning in python and Matlab
 

Similar to Natural Question Generation using Deep Learning

Icon18revrec sudeshna
Icon18revrec sudeshnaIcon18revrec sudeshna
Icon18revrec sudeshna
Muthusamy Chelliah
 
Convolutional and Recurrent Neural Networks
Convolutional and Recurrent Neural NetworksConvolutional and Recurrent Neural Networks
Convolutional and Recurrent Neural Networks
Ramesh Ragala
 
Set Transfomer: A Framework for Attention-based Permutaion-Invariant Neural N...
Set Transfomer: A Framework for Attention-based Permutaion-Invariant Neural N...Set Transfomer: A Framework for Attention-based Permutaion-Invariant Neural N...
Set Transfomer: A Framework for Attention-based Permutaion-Invariant Neural N...
Thien Q. Tran
 
Hardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningHardware Acceleration for Machine Learning
Hardware Acceleration for Machine Learning
CastLabKAIST
 
Towards neuralprocessingofgeneralpurposeapproximateprograms
Towards neuralprocessingofgeneralpurposeapproximateprogramsTowards neuralprocessingofgeneralpurposeapproximateprograms
Towards neuralprocessingofgeneralpurposeapproximateprograms
Paridha Saxena
 
NeuralProcessingofGeneralPurposeApproximatePrograms
NeuralProcessingofGeneralPurposeApproximateProgramsNeuralProcessingofGeneralPurposeApproximatePrograms
NeuralProcessingofGeneralPurposeApproximateProgramsMohid Nabil
 
Artificial neural networks introduction
Artificial neural networks introductionArtificial neural networks introduction
Artificial neural networks introduction
SungminYou
 
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
MLconf
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Universitat Politècnica de Catalunya
 
Deep Learning Tutorial
Deep Learning Tutorial Deep Learning Tutorial
Deep Learning Tutorial
Ligeng Zhu
 
Deep Learning with Apache Spark: an Introduction
Deep Learning with Apache Spark: an IntroductionDeep Learning with Apache Spark: an Introduction
Deep Learning with Apache Spark: an Introduction
Emanuele Bezzi
 
Accelerating stochastic gradient descent using adaptive mini batch size3
Accelerating stochastic gradient descent using adaptive mini batch size3Accelerating stochastic gradient descent using adaptive mini batch size3
Accelerating stochastic gradient descent using adaptive mini batch size3
muayyad alsadi
 
Neural machine translation by jointly learning to align and translate.pptx
Neural machine translation by jointly learning to align and translate.pptxNeural machine translation by jointly learning to align and translate.pptx
Neural machine translation by jointly learning to align and translate.pptx
ssuser2624f71
 
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive S...
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive S...SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive S...
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive S...
Sharath TS
 
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020
Universitat Politècnica de Catalunya
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRU
ananth
 
The Effect of Hierarchical Memory on the Design of Parallel Algorithms and th...
The Effect of Hierarchical Memory on the Design of Parallel Algorithms and th...The Effect of Hierarchical Memory on the Design of Parallel Algorithms and th...
The Effect of Hierarchical Memory on the Design of Parallel Algorithms and th...
David Walker
 
A CGRA-based Approach for Accelerating Convolutional Neural Networks
A CGRA-based Approachfor Accelerating Convolutional Neural NetworksA CGRA-based Approachfor Accelerating Convolutional Neural Networks
A CGRA-based Approach for Accelerating Convolutional Neural Networks
Shinya Takamaeda-Y
 
Ire presentation
Ire presentationIre presentation
Ire presentation
Raj Patel
 
Understanding Large Social Networks | IRE Major Project | Team 57 | LINE
Understanding Large Social Networks | IRE Major Project | Team 57 | LINEUnderstanding Large Social Networks | IRE Major Project | Team 57 | LINE
Understanding Large Social Networks | IRE Major Project | Team 57 | LINE
Raj Patel
 

Similar to Natural Question Generation using Deep Learning (20)

Icon18revrec sudeshna
Icon18revrec sudeshnaIcon18revrec sudeshna
Icon18revrec sudeshna
 
Convolutional and Recurrent Neural Networks
Convolutional and Recurrent Neural NetworksConvolutional and Recurrent Neural Networks
Convolutional and Recurrent Neural Networks
 
Set Transfomer: A Framework for Attention-based Permutaion-Invariant Neural N...
Set Transfomer: A Framework for Attention-based Permutaion-Invariant Neural N...Set Transfomer: A Framework for Attention-based Permutaion-Invariant Neural N...
Set Transfomer: A Framework for Attention-based Permutaion-Invariant Neural N...
 
Hardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningHardware Acceleration for Machine Learning
Hardware Acceleration for Machine Learning
 
Towards neuralprocessingofgeneralpurposeapproximateprograms
Towards neuralprocessingofgeneralpurposeapproximateprogramsTowards neuralprocessingofgeneralpurposeapproximateprograms
Towards neuralprocessingofgeneralpurposeapproximateprograms
 
NeuralProcessingofGeneralPurposeApproximatePrograms
NeuralProcessingofGeneralPurposeApproximateProgramsNeuralProcessingofGeneralPurposeApproximatePrograms
NeuralProcessingofGeneralPurposeApproximatePrograms
 
Artificial neural networks introduction
Artificial neural networks introductionArtificial neural networks introduction
Artificial neural networks introduction
 
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
Corinna Cortes, Head of Research, Google, at MLconf NYC 2017
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
 
Deep Learning Tutorial
Deep Learning Tutorial Deep Learning Tutorial
Deep Learning Tutorial
 
Deep Learning with Apache Spark: an Introduction
Deep Learning with Apache Spark: an IntroductionDeep Learning with Apache Spark: an Introduction
Deep Learning with Apache Spark: an Introduction
 
Accelerating stochastic gradient descent using adaptive mini batch size3
Accelerating stochastic gradient descent using adaptive mini batch size3Accelerating stochastic gradient descent using adaptive mini batch size3
Accelerating stochastic gradient descent using adaptive mini batch size3
 
Neural machine translation by jointly learning to align and translate.pptx
Neural machine translation by jointly learning to align and translate.pptxNeural machine translation by jointly learning to align and translate.pptx
Neural machine translation by jointly learning to align and translate.pptx
 
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive S...
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive S...SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive S...
SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive S...
 
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020
Recurrent Neural Networks RNN - Xavier Giro - UPC TelecomBCN Barcelona 2020
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRU
 
The Effect of Hierarchical Memory on the Design of Parallel Algorithms and th...
The Effect of Hierarchical Memory on the Design of Parallel Algorithms and th...The Effect of Hierarchical Memory on the Design of Parallel Algorithms and th...
The Effect of Hierarchical Memory on the Design of Parallel Algorithms and th...
 
A CGRA-based Approach for Accelerating Convolutional Neural Networks
A CGRA-based Approachfor Accelerating Convolutional Neural NetworksA CGRA-based Approachfor Accelerating Convolutional Neural Networks
A CGRA-based Approach for Accelerating Convolutional Neural Networks
 
Ire presentation
Ire presentationIre presentation
Ire presentation
 
Understanding Large Social Networks | IRE Major Project | Team 57 | LINE
Understanding Large Social Networks | IRE Major Project | Team 57 | LINEUnderstanding Large Social Networks | IRE Major Project | Team 57 | LINE
Understanding Large Social Networks | IRE Major Project | Team 57 | LINE
 

Recently uploaded

一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单
ewymefz
 
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
axoqas
 
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
vcaxypu
 
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdfSample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Linda486226
 
Opendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptxOpendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptx
Opendatabay
 
Investigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_CrimesInvestigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_Crimes
StarCompliance.io
 
Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project PresentationPredicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Boston Institute of Analytics
 
一比一原版(TWU毕业证)西三一大学毕业证成绩单
一比一原版(TWU毕业证)西三一大学毕业证成绩单一比一原版(TWU毕业证)西三一大学毕业证成绩单
一比一原版(TWU毕业证)西三一大学毕业证成绩单
ocavb
 
一比一原版(YU毕业证)约克大学毕业证成绩单
一比一原版(YU毕业证)约克大学毕业证成绩单一比一原版(YU毕业证)约克大学毕业证成绩单
一比一原版(YU毕业证)约克大学毕业证成绩单
enxupq
 
Q1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year ReboundQ1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year Rebound
Oppotus
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP
 
FP Growth Algorithm and its Applications
FP Growth Algorithm and its ApplicationsFP Growth Algorithm and its Applications
FP Growth Algorithm and its Applications
MaleehaSheikh2
 
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Subhajit Sahu
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
ewymefz
 
Empowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptxEmpowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptx
benishzehra469
 
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Subhajit Sahu
 
Tabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflowsTabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflows
alex933524
 
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
ewymefz
 
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
yhkoc
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单
ewymefz
 

Recently uploaded (20)

一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单一比一原版(BU毕业证)波士顿大学毕业证成绩单
一比一原版(BU毕业证)波士顿大学毕业证成绩单
 
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
做(mqu毕业证书)麦考瑞大学毕业证硕士文凭证书学费发票原版一模一样
 
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
 
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdfSample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
Sample_Global Non-invasive Prenatal Testing (NIPT) Market, 2019-2030.pdf
 
Opendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptxOpendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptx
 
Investigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_CrimesInvestigate & Recover / StarCompliance.io / Crypto_Crimes
Investigate & Recover / StarCompliance.io / Crypto_Crimes
 
Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project PresentationPredicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
 
一比一原版(TWU毕业证)西三一大学毕业证成绩单
一比一原版(TWU毕业证)西三一大学毕业证成绩单一比一原版(TWU毕业证)西三一大学毕业证成绩单
一比一原版(TWU毕业证)西三一大学毕业证成绩单
 
一比一原版(YU毕业证)约克大学毕业证成绩单
一比一原版(YU毕业证)约克大学毕业证成绩单一比一原版(YU毕业证)约克大学毕业证成绩单
一比一原版(YU毕业证)约克大学毕业证成绩单
 
Q1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year ReboundQ1’2024 Update: MYCI’s Leap Year Rebound
Q1’2024 Update: MYCI’s Leap Year Rebound
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
 
FP Growth Algorithm and its Applications
FP Growth Algorithm and its ApplicationsFP Growth Algorithm and its Applications
FP Growth Algorithm and its Applications
 
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证成绩单
 
Empowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptxEmpowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptx
 
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
Levelwise PageRank with Loop-Based Dead End Handling Strategy : SHORT REPORT ...
 
Tabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflowsTabula.io Cheatsheet: automate your data workflows
Tabula.io Cheatsheet: automate your data workflows
 
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
一比一原版(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
 
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
一比一原版(CU毕业证)卡尔顿大学毕业证成绩单
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单
 

Natural Question Generation using Deep Learning

  • 1. Neural Question Generation CSS 801 Seminar Presentation ARIJIT MUKHERJEE 17305T0021
  • 2. ● Sequence Processing With Neural Network ● Question Answering Tasks ● Memory Networks ● Match-LSTM + Pointer Networks ● R-NET S-NET ● Neural Question Generation ● Question-Generation Question-Answering Duality ● Natural Language Generation with GANs ● Way-Forward 2
  • 3. Sequence Processing with Neural Networks ● A ‘n’ length sequence can be encoded to ‘nxd’ dimensional vector and then passed to a feed-forward network whose input is ‘nxd’ but doing so we lose the temporal property of the sequence. What we do ? ● We share the same feed-forward network for all our time step recurrently, instead of taking only the ‘d’ size input at each time step we also pass the previous timestep’s output as input. 3 Input0 h0 h1 Input1 hn Inputn ...
  • 4. Recurrent Neural Network Training Problem 4 Loss(y,o)Loss(y,o)Loss(y,o) Vanishing Gradients or Exploding Gradients !! Image source : François Deloche (CCASAI)
  • 5. Long-Short Term Memory 5 Image source : Understanding LSTMs
  • 6. My name is Arijit Context <SOS> What is your name What is your Encoder Decoder 6
  • 7. Encoder Decoder Attention 7 My name is Arijit <SOS> What is your name What is your Encoder Hidden States + Decoder Hidden State (t-1)
  • 8. ● Sequence Processing With Neural Network ● Question Answering Tasks ● Memory Networks ● Match-LSTM + Pointer Networks ● R-NET S-NET ● Neural Question Generation ● Question-Generation Question-Answering Duality ● Natural Language Generation with GANs ● Way-Forward 8
  • 9. Question Answering Task The (20) QA bAbI tasks ● It is available for hindi and english ● The stories are generated by a simulator ● It have two variants of 1k and 10k samples. ● There are 20 tasks with different difficulty levels 9 Stanford Question Answering Dataset ● 536 Wikipedia Articles. ● 23,215 total paragraphs. ● 100,000+ question-answer pairs. ● Evaluation metrics ○ Exact Match Score ○ F1 Score
  • 10. ● Sequence Processing With Neural Network ● Question Answering Tasks ● Memory Networks ● Match-LSTM + Pointer Networks ● R-NET S-NET ● Neural Question Generation ● Question-Generation Question-Answering Duality ● Natural Language Generation with GANs ● Way-Forward 10
  • 11. Memory Network 11 I Input G Generalizer O Output R Response Memory Input X I(X) I(X) Update memory given I(X) M O(M,X) Generated Response Story Question
  • 12. Memory Neural Network MemNN 12 I Input G Generalizer O Output R Response Memory Input X I(X) I(X) Update memory given I(X) M O(M,X) Generated Response Embedding Copy input Xi to memory Xi
  • 13. End to End Memory Network MemN2N Single Layer 13 Image source : End to End Memory Network
  • 14. End-to-End Memory Networks MemN2N Multi Layer 14 Image source : End to End Memory Network
  • 15. 15 Image source : End to End Memory Network
  • 16. ● Sequence Processing With Neural Network ● Question Answering Tasks ● Memory Networks ● Match-LSTM + Pointer Networks ● R-NET S-NET ● Neural Question Generation ● Question-Generation Question-Answering Duality ● Natural Language Generation with GANs ● Way-Forward 16
  • 17. 17 Natural Language Inference P Premise H Hypothesis Y Label {Entrailment, Contradiction, Neutral}
  • 19. Match LSTM Performance 19 Image source : Wange et al.
  • 20. Pointer Network 20X1 X2 X3 X4 <SOS> C1 C2 C3 C4 C1 C2 C3 Encoder Hidden States + Decoder Hidden State (t-1)
  • 21. Match LSTM + Pointer Network 21 Hq a1 Q1 Q2 Q3 Q4 Qn P1 P2 P3 Pm a2 a3 am hr 1 hr 2 hr 3 hr m MATCH-LSTM LAYER LSTM PREPROCESSING LAYER
  • 22. Match-LSTM + Pointer Network Answer Pointer Layer hr 1 hr 2 hr 3 hr m Sequence Model hr 1 hr 2 hr 3 hr m as ae Boundary Model
  • 23. 23Image source : Wange & Jiang.
  • 24. ● Sequence Processing With Neural Network ● Question Answering Tasks ● Memory Networks ● Match-LSTM + Pointer Networks ● R-NET S-NET ● Neural Question Generation ● Question-Generation Question-Answering Duality ● Natural Language Generation with GANs ● Way-Forward 24
  • 25. Changes From Wang & Jiang ● Instead of LSTM use BiDirectional GRUs, GRUs have less training params that of LSTMs ● In the last pointer layer ha 0 will play a vital role, so we need a proper initialization, here they used attention pooling to initialize. ● Match-LSTM layer performs matching between question and paragraph, we can add another layer and match the paragraph with the paragraph. ● Scrap Sequence Model. ● Adding Gates to intermediate hidden states in between layers. 25
  • 28. S-Net 28 ● R-Net Only predicts the starting and ending index of an continous answer while S-Net tries to synthesize answer. ● S-Net have to main components ○ Evidence Extraction ○ Answer Synthesis ● Evidence Extraction uses R-Net without Passage matching and Adds another output as passage ranking. ● Answer Synthesis Model Generates answer given paragraph and start and end token. ● Two components are trained separately.
  • 31. ● Sequence Processing With Neural Network ● Question Answering Tasks ● Memory Networks ● Match-LSTM + Pointer Networks ● R-NET S-NET ● Neural Question Generation ● Question-Generation Question-Answering Duality ● Natural Language Generation with GANs ● Way-Forward 31
  • 32. 32 Learning to Ask Neural Question Generation ● This paper proposes a Question Generation System powered by the Seq2Seq architecture and Attention Mechanism . ● Which Encodes the Passage and the Answer to generate a Question . ● The Evaluation is done on the basis of Machine Translation Metrics like BLEU , METEOR , ROUGE-L
  • 33. Neural Question Generation 33 S1 S2 S3 S4 <SOS> Q1 Q2 Q3 Q4 Q1 Q2 Q3 Sentence Hidden States +Decoder Hidden State (t-1) P1 P2 P3 P4 Paragraph Final Hidden State
  • 34. Experiments 34 Image source : Learning to Ask
  • 35. ● Sequence Processing With Neural Network ● Question Answering Tasks ● Memory Networks ● Match-LSTM + Pointer Networks ● R-NET S-NET ● Neural Question Generation ● Question-Generation Question-Answering Duality ● Natural Language Generation with GANs ● Way-Forward 35
  • 37. Experiments ● QA model is defined by two GRUs encoding question and answer. ● Then creating a vector as then pppppppppppassing to a linear layer followed by a sigmoid. ● The QG is an encoder decoder model with attention. 37 Image source : QA QG dual task
  • 38. ● Sequence Processing With Neural Network ● Question Answering Tasks ● Memory Networks ● Match-LSTM + Pointer Networks ● R-NET S-NET ● Neural Question Generation ● Question-Generation Question-Answering Duality ● Natural Language Generation with GANs ● Way-Forward 38
  • 39. Adversarial Generation of Language with GANs 39 Image source : KDnuggents Blog, From GAN to WGA
  • 41. Adversarial Generation of Natural Language 41Image source : Learning to Ask Paper
  • 42. Experiment Language Generation Tasks TASK CFG ● 248 production rules ● generate two sets of data one consisting of samples of length 5 and another consisting of samples of length 11. ● Each contains 100,000 samples. ● Set 1 vocabulary of size 36 tokens while the second have 45 tokens. 42Image source : Learning to Ask Paper Chinese Poetry ● each line as a training example with lines of length 5 (poem-5) and length 7 (poem 7). ● BLEU-2 and BLEU-3 score on corpus level for evaluation Language Generation ● CMU-SE, PTB English Language Modeling, Google 1billion sentences. Conditional Language Generation ● Generate sentences conditioned on Wh word and sentiment
  • 43. ● Sequence Processing With Neural Network ● Question Answering Tasks ● Memory Networks ● Match-LSTM + Pointer Networks ● R-NET S-NET ● Neural Question Generation ● Question-Generation Question-Answering Duality ● Natural Language Generation with GANs ● Way-Forward 43
  • 44. Way Forward ● Exploring Memory Networks for Question-Generation ● Incorporating Structured knowledge-bases in question-generation framework. ● Exploring Conditional GANs for Sequence to Sequence tasks. ● Improving the Learning to ask baseline and adding match-LSTMs to it. ● Conditional generation of questions with specific WH words and scores. ● Applying Question-Generation for Hindi Textbooks. 44