SlideShare a Scribd company logo
1 of 19
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
Fine –grained Interest Matching
For Neural News Recommendation
펀다멘탈팀
김지연, 김동희, 김창연, 송헌, 이근배, 이재윤
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
• 새로 생성되는 방대한 뉴스의 양
• 각 개인의 다양한 흥미 분야
• 기존 추천시스템의 구조적인 한계
개인 맞춤 뉴스 추천 시스템
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
Related Work
Part
2
Conventional Methods Deep Learning Methods
• User-News Feature engineering
(Phelan et al 2011)
• Topic category and Feature by Bayesian
(Liu et al 2013 etc.)
• location based news recommendation
(Son et al 2013)
• Distiling Semantic Feature through auto-
encoder + RNN
( Okura et al)
• Extract entity thorugh knowledge graph
(Wu et al 2018 )
• GRU network to long0term user
preference
(An et al.)
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
기존 추천 시스템
• 뉴스 검색 기록의 1차원 벡터화
• 뉴스 기록에 잠재된 사용자의 흥미를 후보 뉴
스군에 매칭 하기 어려움
• Okura et al 2017, Wu et al 2019,
FIM
• 기존 추천 시스템의 문제 해결
1. 1차원의 벡터대신 convolution 사용으로
사용자에 대한 관심에 알맞는 뉴스 추천
가능
2. 각 뉴스와 후보 뉴스를 단어 , 문장 대한
더 많은 정보 학습
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
사용자의 특성을 추출하는 대신, 뉴스를 다양한 레벨에서
Matching시켜, 다양한측면에서비교하여더욱정확한정
보를추려낼수있다.
“
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
Overview
>> >> >>
Step 1 Step 2 Step 3 Step 4
Problem
Definition
• 사용자별뉴스검
색기록추출
• WordEmbeeding
News
Representation
• Hierarchical
dilated
convolution
• 3D matrix 형태뉴
스 변형
Part
1
Cross
Matching
Matrices
• 후보뉴스 X 뉴
스 기록
Click
Prediction
Module
• Convolution
Aggregate
• 3D CNN
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
Step 1 : 문제 정의
Part
1
1 사용자 u 에대한뉴스검색기록 𝑆𝑢= {𝑑1,…𝑑𝑛}
3 후보영화𝐶𝑖,예측값 : 𝑦𝑖 ⊆{0,1}정의
4
g:𝑆𝑢,𝐶 𝑦̂
사용자의뉴스탐색기록u와,후보영화를입력했을때,예측값이나올함수g
제목, Category, Subcategory  d = emb([x1,…𝑥𝑛])
2
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
Dataset Setting
Microsoft News dataset
Glove Embedding
20 length of sent + cat + subcat
50개의 뉴스 검색 리스트
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
• d-dimension embedding d_i
• Heirarchcial dilated convolution Layers
• 텍스트에서 다양한 의미를 찾을수 있다
• Standard Convolution 과 차이점 :
• 𝛿 만큼의 element 를 filed에서 스킵하
면서 학습 , 다양한 의미파악을 위해
Multi level 𝛿 사용
• 각 layer 마다 Normal Batch 적용
• 넓은 View , 적은 계산 비용 , no loss in
information
Step 2-1 :
Hierarchical dilated convolution
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
• 각Layer에다양한level의Mutileveldilation사용
• 각각Layer에NormalBatch사용
• 각Layer을쌓아줌
• 단어,문장,cateogory등다양한의미를학습이가능
• Max-pooling과같은downsampling이없어서정보소실가능
성이적음
Step2-2:Multi-grainedNews
Representation
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
• K개의History뉴스와후보뉴스C의scaleddotproduct
• <d_k,c>각각History와후보뉴스의곱을통해각채
널별(문장군,단어군등)중요한정보의곱으로구현
Step3:CrossMatchingModule
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
• 앞서 내적한 문서 I X 후보뉴스 의 3D convolutions 들
을요약하기위해,모두 조합하여3Dmatching image
Q로만들어줌
Step4:Convolution Aggregate
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
• 3D convolution
• filters: 32-[3,3,3], 16-[3,3,3]
• Stride : [1,1,1]
• max pooling network 로 전체 이미지에서 의미
있는 (특이한) 시그널을 찾음 [3,3,3]
• Output : 사용자의 기록 리스트와 후보 뉴스에
대한 Matching 벡터
• 추천시스템의 결과 : 후보 뉴스의 추천 랭킹
• 해당 후보 뉴스의 Click probability 계산
• Optimizer : Adam , mini-batch 100 , initial
learning rate 1e-3
Step 2-1 :
Click Prediction Module
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
ComparisonMethods
Part
2
Manually Feature-based Methods Neural Recommendation Methods
LibFm(Rendel2012):matrixfactorization DFM(Lian2018):denselayer+Attention
DSSM(Huang2013):
trigram+multidenselayer
DKN(2018):Knoledgegraph+CNN
Wide&Deep(Cheng2016):
matrixfactorization+denselayer
GRU(Okura2017):Auto-encoder+GRU
DeepFM(Guo2017):
factorizationmachine+DNN
NRU(Wu2019):Multi-headAttention
NPA(Wu2019):PersonalizeAttention
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
ComparisonMethods
Part
3
• Neural > Traditional
• Deep Neural Model 이사용자와뉴스사이
의의미있는Feature을더잘분석
• FIM > Neural > Taditional
• SOTA
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
Quantity&InputAnalysis
Part
2
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
Quantity&InputAnalysis
Part
2
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
Part 5 Visualization
ⓒSaebyeol Yu. Saebyeol’s PowerPoint
감사합니다

More Related Content

What's hot

Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningSujit Pal
 
Learning deep structured semantic models for web search
Learning deep structured semantic models for web searchLearning deep structured semantic models for web search
Learning deep structured semantic models for web searchhyunsung lee
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine LearningShahar Cohen
 
Boosting probabilistic graphical model inference by incorporating prior knowl...
Boosting probabilistic graphical model inference by incorporating prior knowl...Boosting probabilistic graphical model inference by incorporating prior knowl...
Boosting probabilistic graphical model inference by incorporating prior knowl...Hakky St
 
Deep Learning Enabled Question Answering System to Automate Corporate Helpdesk
Deep Learning Enabled Question Answering System to Automate Corporate HelpdeskDeep Learning Enabled Question Answering System to Automate Corporate Helpdesk
Deep Learning Enabled Question Answering System to Automate Corporate HelpdeskSaurabh Saxena
 
H2O World - Top 10 Deep Learning Tips & Tricks - Arno Candel
H2O World - Top 10 Deep Learning Tips & Tricks - Arno CandelH2O World - Top 10 Deep Learning Tips & Tricks - Arno Candel
H2O World - Top 10 Deep Learning Tips & Tricks - Arno CandelSri Ambati
 
GAN-based statistical speech synthesis (in Japanese)
GAN-based statistical speech synthesis (in Japanese)GAN-based statistical speech synthesis (in Japanese)
GAN-based statistical speech synthesis (in Japanese)Yuki Saito
 
【DL輪読会】Efficiently Modeling Long Sequences with Structured State Spaces
【DL輪読会】Efficiently Modeling Long Sequences with Structured State Spaces【DL輪読会】Efficiently Modeling Long Sequences with Structured State Spaces
【DL輪読会】Efficiently Modeling Long Sequences with Structured State SpacesDeep Learning JP
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningAmr Rashed
 
Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?Manuel Martín
 
Le Machine Learning de A à Z
Le Machine Learning de A à ZLe Machine Learning de A à Z
Le Machine Learning de A à ZAlexia Audevart
 
Topic extraction using machine learning
Topic extraction using machine learningTopic extraction using machine learning
Topic extraction using machine learningSanjib Basak
 
What is Machine Learning?
What is Machine Learning?What is Machine Learning?
What is Machine Learning?SwiftKeyComms
 
NLP Classifier Models & Metrics
NLP Classifier Models & MetricsNLP Classifier Models & Metrics
NLP Classifier Models & MetricsSanghamitra Deb
 
Making Machine Learning Work in Practice - StampedeCon 2014
Making Machine Learning Work in Practice - StampedeCon 2014Making Machine Learning Work in Practice - StampedeCon 2014
Making Machine Learning Work in Practice - StampedeCon 2014StampedeCon
 
Brief introduction to Machine Learning
Brief introduction to Machine LearningBrief introduction to Machine Learning
Brief introduction to Machine LearningCodeForFrankfurt
 
Masquerader Detection
Masquerader DetectionMasquerader Detection
Masquerader DetectionArquam Md
 
Deep Dive into Hyperparameter Tuning
Deep Dive into Hyperparameter TuningDeep Dive into Hyperparameter Tuning
Deep Dive into Hyperparameter TuningShubhmay Potdar
 

What's hot (20)

Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep Learning
 
Learning deep structured semantic models for web search
Learning deep structured semantic models for web searchLearning deep structured semantic models for web search
Learning deep structured semantic models for web search
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Boosting probabilistic graphical model inference by incorporating prior knowl...
Boosting probabilistic graphical model inference by incorporating prior knowl...Boosting probabilistic graphical model inference by incorporating prior knowl...
Boosting probabilistic graphical model inference by incorporating prior knowl...
 
Deep Learning Enabled Question Answering System to Automate Corporate Helpdesk
Deep Learning Enabled Question Answering System to Automate Corporate HelpdeskDeep Learning Enabled Question Answering System to Automate Corporate Helpdesk
Deep Learning Enabled Question Answering System to Automate Corporate Helpdesk
 
Meta-Learning Presentation
Meta-Learning PresentationMeta-Learning Presentation
Meta-Learning Presentation
 
H2O World - Top 10 Deep Learning Tips & Tricks - Arno Candel
H2O World - Top 10 Deep Learning Tips & Tricks - Arno CandelH2O World - Top 10 Deep Learning Tips & Tricks - Arno Candel
H2O World - Top 10 Deep Learning Tips & Tricks - Arno Candel
 
GAN-based statistical speech synthesis (in Japanese)
GAN-based statistical speech synthesis (in Japanese)GAN-based statistical speech synthesis (in Japanese)
GAN-based statistical speech synthesis (in Japanese)
 
【DL輪読会】Efficiently Modeling Long Sequences with Structured State Spaces
【DL輪読会】Efficiently Modeling Long Sequences with Structured State Spaces【DL輪読会】Efficiently Modeling Long Sequences with Structured State Spaces
【DL輪読会】Efficiently Modeling Long Sequences with Structured State Spaces
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?Automating Machine Learning - Is it feasible?
Automating Machine Learning - Is it feasible?
 
Le Machine Learning de A à Z
Le Machine Learning de A à ZLe Machine Learning de A à Z
Le Machine Learning de A à Z
 
Topic extraction using machine learning
Topic extraction using machine learningTopic extraction using machine learning
Topic extraction using machine learning
 
What is Machine Learning?
What is Machine Learning?What is Machine Learning?
What is Machine Learning?
 
NLP Classifier Models & Metrics
NLP Classifier Models & MetricsNLP Classifier Models & Metrics
NLP Classifier Models & Metrics
 
Making Machine Learning Work in Practice - StampedeCon 2014
Making Machine Learning Work in Practice - StampedeCon 2014Making Machine Learning Work in Practice - StampedeCon 2014
Making Machine Learning Work in Practice - StampedeCon 2014
 
Brief introduction to Machine Learning
Brief introduction to Machine LearningBrief introduction to Machine Learning
Brief introduction to Machine Learning
 
Masquerader Detection
Masquerader DetectionMasquerader Detection
Masquerader Detection
 
large scale Machine learning
large scale Machine learninglarge scale Machine learning
large scale Machine learning
 
Deep Dive into Hyperparameter Tuning
Deep Dive into Hyperparameter TuningDeep Dive into Hyperparameter Tuning
Deep Dive into Hyperparameter Tuning
 

Similar to Fine –grained interest matching for neural news recommendation

Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learningSushant Shrivastava
 
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)Thilo Stadelmann
 
Deep learning for real life applications
Deep learning for real life applicationsDeep learning for real life applications
Deep learning for real life applicationsAnas Arram, Ph.D
 
Neural Input Search for Large Scale Recommendation Models
Neural Input Search for Large Scale Recommendation ModelsNeural Input Search for Large Scale Recommendation Models
Neural Input Search for Large Scale Recommendation ModelsH W
 
Weave-D - 2nd Progress Evaluation Presentation
Weave-D - 2nd Progress Evaluation PresentationWeave-D - 2nd Progress Evaluation Presentation
Weave-D - 2nd Progress Evaluation Presentationlasinducharith
 
Centertrack and naver airush 2020 review
Centertrack and naver airush 2020 reviewCentertrack and naver airush 2020 review
Centertrack and naver airush 2020 review경훈 김
 
IRJET - An Robust and Dynamic Fire Detection Method using Convolutional N...
IRJET -  	  An Robust and Dynamic Fire Detection Method using Convolutional N...IRJET -  	  An Robust and Dynamic Fire Detection Method using Convolutional N...
IRJET - An Robust and Dynamic Fire Detection Method using Convolutional N...IRJET Journal
 
IMAGE SEGMENTATION AND ITS TECHNIQUES
IMAGE SEGMENTATION AND ITS TECHNIQUESIMAGE SEGMENTATION AND ITS TECHNIQUES
IMAGE SEGMENTATION AND ITS TECHNIQUESIRJET Journal
 
How can pre-training help to solve the cold start problem?
How can pre-training help to solve the cold start problem?How can pre-training help to solve the cold start problem?
How can pre-training help to solve the cold start problem?Lokesh Vadlamudi
 
The DemaWare Service-Oriented AAL Platform for People with Dementia
The DemaWare Service-Oriented AAL Platform for People with DementiaThe DemaWare Service-Oriented AAL Platform for People with Dementia
The DemaWare Service-Oriented AAL Platform for People with DementiaYiannis Kompatsiaris
 
auto-assistance system for visually impaired person
auto-assistance system for visually impaired personauto-assistance system for visually impaired person
auto-assistance system for visually impaired personshahsamkit73
 
Deep neural networks for Youtube recommendations
Deep neural networks for Youtube recommendationsDeep neural networks for Youtube recommendations
Deep neural networks for Youtube recommendationsAryan Khandal
 
App development with stable diffusion model Unlocking the power of generative...
App development with stable diffusion model Unlocking the power of generative...App development with stable diffusion model Unlocking the power of generative...
App development with stable diffusion model Unlocking the power of generative...StephenAmell4
 
sourabh_bajaj_resume
sourabh_bajaj_resumesourabh_bajaj_resume
sourabh_bajaj_resumeYipei Wang
 
Object Detetcion using SSD-MobileNet
Object Detetcion using SSD-MobileNetObject Detetcion using SSD-MobileNet
Object Detetcion using SSD-MobileNetIRJET Journal
 
Data warehouse design
Data warehouse designData warehouse design
Data warehouse designines beltaief
 

Similar to Fine –grained interest matching for neural news recommendation (20)

Object detection with deep learning
Object detection with deep learningObject detection with deep learning
Object detection with deep learning
 
Video+Language: From Classification to Description
Video+Language: From Classification to DescriptionVideo+Language: From Classification to Description
Video+Language: From Classification to Description
 
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)
Deep Learning @ ZHAW Datalab (with Mark Cieliebak & Yves Pauchard)
 
Deep learning for real life applications
Deep learning for real life applicationsDeep learning for real life applications
Deep learning for real life applications
 
Neural Input Search for Large Scale Recommendation Models
Neural Input Search for Large Scale Recommendation ModelsNeural Input Search for Large Scale Recommendation Models
Neural Input Search for Large Scale Recommendation Models
 
Weave-D - 2nd Progress Evaluation Presentation
Weave-D - 2nd Progress Evaluation PresentationWeave-D - 2nd Progress Evaluation Presentation
Weave-D - 2nd Progress Evaluation Presentation
 
Centertrack and naver airush 2020 review
Centertrack and naver airush 2020 reviewCentertrack and naver airush 2020 review
Centertrack and naver airush 2020 review
 
IRJET - An Robust and Dynamic Fire Detection Method using Convolutional N...
IRJET -  	  An Robust and Dynamic Fire Detection Method using Convolutional N...IRJET -  	  An Robust and Dynamic Fire Detection Method using Convolutional N...
IRJET - An Robust and Dynamic Fire Detection Method using Convolutional N...
 
Video + Language: Where Does Domain Knowledge Fit in?
Video + Language: Where Does Domain Knowledge Fit in?Video + Language: Where Does Domain Knowledge Fit in?
Video + Language: Where Does Domain Knowledge Fit in?
 
Video + Language: Where Does Domain Knowledge Fit in?
Video + Language: Where Does Domain Knowledge Fit in?Video + Language: Where Does Domain Knowledge Fit in?
Video + Language: Where Does Domain Knowledge Fit in?
 
IMAGE SEGMENTATION AND ITS TECHNIQUES
IMAGE SEGMENTATION AND ITS TECHNIQUESIMAGE SEGMENTATION AND ITS TECHNIQUES
IMAGE SEGMENTATION AND ITS TECHNIQUES
 
How can pre-training help to solve the cold start problem?
How can pre-training help to solve the cold start problem?How can pre-training help to solve the cold start problem?
How can pre-training help to solve the cold start problem?
 
The DemaWare Service-Oriented AAL Platform for People with Dementia
The DemaWare Service-Oriented AAL Platform for People with DementiaThe DemaWare Service-Oriented AAL Platform for People with Dementia
The DemaWare Service-Oriented AAL Platform for People with Dementia
 
auto-assistance system for visually impaired person
auto-assistance system for visually impaired personauto-assistance system for visually impaired person
auto-assistance system for visually impaired person
 
Deep neural networks for Youtube recommendations
Deep neural networks for Youtube recommendationsDeep neural networks for Youtube recommendations
Deep neural networks for Youtube recommendations
 
App development with stable diffusion model Unlocking the power of generative...
App development with stable diffusion model Unlocking the power of generative...App development with stable diffusion model Unlocking the power of generative...
App development with stable diffusion model Unlocking the power of generative...
 
sourabh_bajaj_resume
sourabh_bajaj_resumesourabh_bajaj_resume
sourabh_bajaj_resume
 
Object Detetcion using SSD-MobileNet
Object Detetcion using SSD-MobileNetObject Detetcion using SSD-MobileNet
Object Detetcion using SSD-MobileNet
 
gn-160406200425 (1).pdf
gn-160406200425 (1).pdfgn-160406200425 (1).pdf
gn-160406200425 (1).pdf
 
Data warehouse design
Data warehouse designData warehouse design
Data warehouse design
 

More from taeseon ryu

OpineSum Entailment-based self-training for abstractive opinion summarization...
OpineSum Entailment-based self-training for abstractive opinion summarization...OpineSum Entailment-based self-training for abstractive opinion summarization...
OpineSum Entailment-based self-training for abstractive opinion summarization...taeseon ryu
 
3D Gaussian Splatting
3D Gaussian Splatting3D Gaussian Splatting
3D Gaussian Splattingtaeseon ryu
 
Hyperbolic Image Embedding.pptx
Hyperbolic  Image Embedding.pptxHyperbolic  Image Embedding.pptx
Hyperbolic Image Embedding.pptxtaeseon ryu
 
MCSE_Multimodal Contrastive Learning of Sentence Embeddings_변현정
MCSE_Multimodal Contrastive Learning of Sentence Embeddings_변현정MCSE_Multimodal Contrastive Learning of Sentence Embeddings_변현정
MCSE_Multimodal Contrastive Learning of Sentence Embeddings_변현정taeseon ryu
 
LLaMA Open and Efficient Foundation Language Models - 230528.pdf
LLaMA Open and Efficient Foundation Language Models - 230528.pdfLLaMA Open and Efficient Foundation Language Models - 230528.pdf
LLaMA Open and Efficient Foundation Language Models - 230528.pdftaeseon ryu
 
Dataset Distillation by Matching Training Trajectories
Dataset Distillation by Matching Training Trajectories Dataset Distillation by Matching Training Trajectories
Dataset Distillation by Matching Training Trajectories taeseon ryu
 
Packed Levitated Marker for Entity and Relation Extraction
Packed Levitated Marker for Entity and Relation ExtractionPacked Levitated Marker for Entity and Relation Extraction
Packed Levitated Marker for Entity and Relation Extractiontaeseon ryu
 
MOReL: Model-Based Offline Reinforcement Learning
MOReL: Model-Based Offline Reinforcement LearningMOReL: Model-Based Offline Reinforcement Learning
MOReL: Model-Based Offline Reinforcement Learningtaeseon ryu
 
Scaling Instruction-Finetuned Language Models
Scaling Instruction-Finetuned Language ModelsScaling Instruction-Finetuned Language Models
Scaling Instruction-Finetuned Language Modelstaeseon ryu
 
Visual prompt tuning
Visual prompt tuningVisual prompt tuning
Visual prompt tuningtaeseon ryu
 
variBAD, A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning.pdf
variBAD, A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning.pdfvariBAD, A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning.pdf
variBAD, A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning.pdftaeseon ryu
 
Reinforced Genetic Algorithm Learning For Optimizing Computation Graphs.pdf
Reinforced Genetic Algorithm Learning For Optimizing Computation Graphs.pdfReinforced Genetic Algorithm Learning For Optimizing Computation Graphs.pdf
Reinforced Genetic Algorithm Learning For Optimizing Computation Graphs.pdftaeseon ryu
 
The Forward-Forward Algorithm
The Forward-Forward AlgorithmThe Forward-Forward Algorithm
The Forward-Forward Algorithmtaeseon ryu
 
Towards Robust and Reproducible Active Learning using Neural Networks
Towards Robust and Reproducible Active Learning using Neural NetworksTowards Robust and Reproducible Active Learning using Neural Networks
Towards Robust and Reproducible Active Learning using Neural Networkstaeseon ryu
 
BRIO: Bringing Order to Abstractive Summarization
BRIO: Bringing Order to Abstractive SummarizationBRIO: Bringing Order to Abstractive Summarization
BRIO: Bringing Order to Abstractive Summarizationtaeseon ryu
 

More from taeseon ryu (20)

VoxelNet
VoxelNetVoxelNet
VoxelNet
 
OpineSum Entailment-based self-training for abstractive opinion summarization...
OpineSum Entailment-based self-training for abstractive opinion summarization...OpineSum Entailment-based self-training for abstractive opinion summarization...
OpineSum Entailment-based self-training for abstractive opinion summarization...
 
3D Gaussian Splatting
3D Gaussian Splatting3D Gaussian Splatting
3D Gaussian Splatting
 
JetsonTX2 Python
 JetsonTX2 Python  JetsonTX2 Python
JetsonTX2 Python
 
Hyperbolic Image Embedding.pptx
Hyperbolic  Image Embedding.pptxHyperbolic  Image Embedding.pptx
Hyperbolic Image Embedding.pptx
 
MCSE_Multimodal Contrastive Learning of Sentence Embeddings_변현정
MCSE_Multimodal Contrastive Learning of Sentence Embeddings_변현정MCSE_Multimodal Contrastive Learning of Sentence Embeddings_변현정
MCSE_Multimodal Contrastive Learning of Sentence Embeddings_변현정
 
LLaMA Open and Efficient Foundation Language Models - 230528.pdf
LLaMA Open and Efficient Foundation Language Models - 230528.pdfLLaMA Open and Efficient Foundation Language Models - 230528.pdf
LLaMA Open and Efficient Foundation Language Models - 230528.pdf
 
YOLO V6
YOLO V6YOLO V6
YOLO V6
 
Dataset Distillation by Matching Training Trajectories
Dataset Distillation by Matching Training Trajectories Dataset Distillation by Matching Training Trajectories
Dataset Distillation by Matching Training Trajectories
 
RL_UpsideDown
RL_UpsideDownRL_UpsideDown
RL_UpsideDown
 
Packed Levitated Marker for Entity and Relation Extraction
Packed Levitated Marker for Entity and Relation ExtractionPacked Levitated Marker for Entity and Relation Extraction
Packed Levitated Marker for Entity and Relation Extraction
 
MOReL: Model-Based Offline Reinforcement Learning
MOReL: Model-Based Offline Reinforcement LearningMOReL: Model-Based Offline Reinforcement Learning
MOReL: Model-Based Offline Reinforcement Learning
 
Scaling Instruction-Finetuned Language Models
Scaling Instruction-Finetuned Language ModelsScaling Instruction-Finetuned Language Models
Scaling Instruction-Finetuned Language Models
 
Visual prompt tuning
Visual prompt tuningVisual prompt tuning
Visual prompt tuning
 
mPLUG
mPLUGmPLUG
mPLUG
 
variBAD, A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning.pdf
variBAD, A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning.pdfvariBAD, A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning.pdf
variBAD, A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning.pdf
 
Reinforced Genetic Algorithm Learning For Optimizing Computation Graphs.pdf
Reinforced Genetic Algorithm Learning For Optimizing Computation Graphs.pdfReinforced Genetic Algorithm Learning For Optimizing Computation Graphs.pdf
Reinforced Genetic Algorithm Learning For Optimizing Computation Graphs.pdf
 
The Forward-Forward Algorithm
The Forward-Forward AlgorithmThe Forward-Forward Algorithm
The Forward-Forward Algorithm
 
Towards Robust and Reproducible Active Learning using Neural Networks
Towards Robust and Reproducible Active Learning using Neural NetworksTowards Robust and Reproducible Active Learning using Neural Networks
Towards Robust and Reproducible Active Learning using Neural Networks
 
BRIO: Bringing Order to Abstractive Summarization
BRIO: Bringing Order to Abstractive SummarizationBRIO: Bringing Order to Abstractive Summarization
BRIO: Bringing Order to Abstractive Summarization
 

Recently uploaded

dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptSonatrach
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptxthyngster
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPramod Kumar Srivastava
 
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...ThinkInnovation
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...Pooja Nehwal
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFAAndrei Kaleshka
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationshipsccctableauusergroup
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改atducpo
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfLars Albertsson
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home ServiceSapana Sha
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdfHuman37
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort servicejennyeacort
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfJohn Sterrett
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingNeil Barnes
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts ServiceSapana Sha
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...dajasot375
 

Recently uploaded (20)

dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
 
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
Predictive Analysis - Using Insight-informed Data to Determine Factors Drivin...
 
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...{Pooja:  9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
{Pooja: 9892124323 } Call Girl in Mumbai | Jas Kaur Rate 4500 Free Hotel Del...
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFA
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships
 
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
代办国外大学文凭《原版美国UCLA文凭证书》加州大学洛杉矶分校毕业证制作成绩单修改
 
Industrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdfIndustrialised data - the key to AI success.pdf
Industrialised data - the key to AI success.pdf
 
9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service9654467111 Call Girls In Munirka Hotel And Home Service
9654467111 Call Girls In Munirka Hotel And Home Service
 
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf
 
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
9711147426✨Call In girls Gurgaon Sector 31. SCO 25 escort service
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdf
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data Storytelling
 
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
꧁❤ Aerocity Call Girls Service Aerocity Delhi ❤꧂ 9999965857 ☎️ Hard And Sexy ...
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts Service
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
 

Fine –grained interest matching for neural news recommendation

  • 1. ⓒSaebyeol Yu. Saebyeol’s PowerPoint Fine –grained Interest Matching For Neural News Recommendation 펀다멘탈팀 김지연, 김동희, 김창연, 송헌, 이근배, 이재윤
  • 2. ⓒSaebyeol Yu. Saebyeol’s PowerPoint • 새로 생성되는 방대한 뉴스의 양 • 각 개인의 다양한 흥미 분야 • 기존 추천시스템의 구조적인 한계 개인 맞춤 뉴스 추천 시스템
  • 3. ⓒSaebyeol Yu. Saebyeol’s PowerPoint Related Work Part 2 Conventional Methods Deep Learning Methods • User-News Feature engineering (Phelan et al 2011) • Topic category and Feature by Bayesian (Liu et al 2013 etc.) • location based news recommendation (Son et al 2013) • Distiling Semantic Feature through auto- encoder + RNN ( Okura et al) • Extract entity thorugh knowledge graph (Wu et al 2018 ) • GRU network to long0term user preference (An et al.)
  • 4. ⓒSaebyeol Yu. Saebyeol’s PowerPoint 기존 추천 시스템 • 뉴스 검색 기록의 1차원 벡터화 • 뉴스 기록에 잠재된 사용자의 흥미를 후보 뉴 스군에 매칭 하기 어려움 • Okura et al 2017, Wu et al 2019, FIM • 기존 추천 시스템의 문제 해결 1. 1차원의 벡터대신 convolution 사용으로 사용자에 대한 관심에 알맞는 뉴스 추천 가능 2. 각 뉴스와 후보 뉴스를 단어 , 문장 대한 더 많은 정보 학습
  • 5. ⓒSaebyeol Yu. Saebyeol’s PowerPoint 사용자의 특성을 추출하는 대신, 뉴스를 다양한 레벨에서 Matching시켜, 다양한측면에서비교하여더욱정확한정 보를추려낼수있다. “
  • 6. ⓒSaebyeol Yu. Saebyeol’s PowerPoint Overview >> >> >> Step 1 Step 2 Step 3 Step 4 Problem Definition • 사용자별뉴스검 색기록추출 • WordEmbeeding News Representation • Hierarchical dilated convolution • 3D matrix 형태뉴 스 변형 Part 1 Cross Matching Matrices • 후보뉴스 X 뉴 스 기록 Click Prediction Module • Convolution Aggregate • 3D CNN
  • 7. ⓒSaebyeol Yu. Saebyeol’s PowerPoint Step 1 : 문제 정의 Part 1 1 사용자 u 에대한뉴스검색기록 𝑆𝑢= {𝑑1,…𝑑𝑛} 3 후보영화𝐶𝑖,예측값 : 𝑦𝑖 ⊆{0,1}정의 4 g:𝑆𝑢,𝐶 𝑦̂ 사용자의뉴스탐색기록u와,후보영화를입력했을때,예측값이나올함수g 제목, Category, Subcategory  d = emb([x1,…𝑥𝑛]) 2
  • 8. ⓒSaebyeol Yu. Saebyeol’s PowerPoint Dataset Setting Microsoft News dataset Glove Embedding 20 length of sent + cat + subcat 50개의 뉴스 검색 리스트
  • 9. ⓒSaebyeol Yu. Saebyeol’s PowerPoint • d-dimension embedding d_i • Heirarchcial dilated convolution Layers • 텍스트에서 다양한 의미를 찾을수 있다 • Standard Convolution 과 차이점 : • 𝛿 만큼의 element 를 filed에서 스킵하 면서 학습 , 다양한 의미파악을 위해 Multi level 𝛿 사용 • 각 layer 마다 Normal Batch 적용 • 넓은 View , 적은 계산 비용 , no loss in information Step 2-1 : Hierarchical dilated convolution
  • 10. ⓒSaebyeol Yu. Saebyeol’s PowerPoint • 각Layer에다양한level의Mutileveldilation사용 • 각각Layer에NormalBatch사용 • 각Layer을쌓아줌 • 단어,문장,cateogory등다양한의미를학습이가능 • Max-pooling과같은downsampling이없어서정보소실가능 성이적음 Step2-2:Multi-grainedNews Representation
  • 11. ⓒSaebyeol Yu. Saebyeol’s PowerPoint • K개의History뉴스와후보뉴스C의scaleddotproduct • <d_k,c>각각History와후보뉴스의곱을통해각채 널별(문장군,단어군등)중요한정보의곱으로구현 Step3:CrossMatchingModule
  • 12. ⓒSaebyeol Yu. Saebyeol’s PowerPoint • 앞서 내적한 문서 I X 후보뉴스 의 3D convolutions 들 을요약하기위해,모두 조합하여3Dmatching image Q로만들어줌 Step4:Convolution Aggregate
  • 13. ⓒSaebyeol Yu. Saebyeol’s PowerPoint • 3D convolution • filters: 32-[3,3,3], 16-[3,3,3] • Stride : [1,1,1] • max pooling network 로 전체 이미지에서 의미 있는 (특이한) 시그널을 찾음 [3,3,3] • Output : 사용자의 기록 리스트와 후보 뉴스에 대한 Matching 벡터 • 추천시스템의 결과 : 후보 뉴스의 추천 랭킹 • 해당 후보 뉴스의 Click probability 계산 • Optimizer : Adam , mini-batch 100 , initial learning rate 1e-3 Step 2-1 : Click Prediction Module
  • 14. ⓒSaebyeol Yu. Saebyeol’s PowerPoint ComparisonMethods Part 2 Manually Feature-based Methods Neural Recommendation Methods LibFm(Rendel2012):matrixfactorization DFM(Lian2018):denselayer+Attention DSSM(Huang2013): trigram+multidenselayer DKN(2018):Knoledgegraph+CNN Wide&Deep(Cheng2016): matrixfactorization+denselayer GRU(Okura2017):Auto-encoder+GRU DeepFM(Guo2017): factorizationmachine+DNN NRU(Wu2019):Multi-headAttention NPA(Wu2019):PersonalizeAttention
  • 15. ⓒSaebyeol Yu. Saebyeol’s PowerPoint ComparisonMethods Part 3 • Neural > Traditional • Deep Neural Model 이사용자와뉴스사이 의의미있는Feature을더잘분석 • FIM > Neural > Taditional • SOTA
  • 16. ⓒSaebyeol Yu. Saebyeol’s PowerPoint Quantity&InputAnalysis Part 2
  • 17. ⓒSaebyeol Yu. Saebyeol’s PowerPoint Quantity&InputAnalysis Part 2
  • 18. ⓒSaebyeol Yu. Saebyeol’s PowerPoint Part 5 Visualization
  • 19. ⓒSaebyeol Yu. Saebyeol’s PowerPoint 감사합니다