SlideShare a Scribd company logo
@cataldomusto @ale_suglia
@cld_greco @SWAP_research
A Deep Architecture for
Content-based Recommendations
Exploiting Recurrent Neural Networks
ALESSANDRO SUGLIA, CLAUDIO GRECO, CATALDO MUSTO, MARCO DE GEMMIS, PASQUALE
LOPS, GIOVANNI SEMERARO
UNIVERSITÀ DEGLI STUDI DI BARI ‘ALDO MORO’ - ITALY
25th International Conference on User
Modeling, Adaptation and Personalization
Bratislava, Slovakia
July 12, 2017
cataldo.musto@uniba.it
Recurrent Neural Networks (RNNs)
Widespread Deep Learning Architecture
◦ Based on Neural Networks
◦ The connections between the units may contain loops which let consider past states in the
learning process
◦ Very suitable to model variable-length sequential data
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Recurrent Neural Networks (RNNs)
Widespread Deep Learning Architecture
◦ Based on Neural Networks
◦ The connections between the units may contain loops which let consider past states in the
learning process
◦ Very suitable to model variable-length sequential data
PROS CONS
◦ Very good performance in different tasks
◦ Can learn short-term and long-term (temporal) dependencies
◦ Vanishing/exploding gradient problem
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Recurrent Neural Networks (RNNs)
Widespread Deep Learning Architecture
◦ Based on Neural Networks
◦ The connections between the units may contain loops which let consider past states in the
learning process
◦ Very suitable to model variable-length sequential data
PROS CONS
◦ Very good performance in different tasks
◦ Can learn short-term and long-term (temporal) dependencies
◦ Vanishing/exploding gradient problem
LONG-SHORT TERM MEMORY NETWORKS (LSTMS)
◦ Introduced to solve the vanishing/exploding gradient problem
Each cell presents a complex structure which is more powerful than simple RNN cells.
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Motivations
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
?
In content-based recommender systems
suggestions are generated by matching
the features stored in the user profile
with those describing the items to be
recommended
Motivations
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
user profile
?
items
In content-based recommender systems
suggestions are generated by matching
the features stored in the user profile
with those describing the items to be
recommended
Motivations
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
user profile
?
items
In content-based recommender systems
suggestions are generated by matching
the features stored in the user profile
with those describing the items to be
recommended
Content Representation
plays a key role!
Motivations
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
user profile
?
items
In content-based recommender systems
suggestions are generated by matching
the features stored in the user profile
with those describing the items to be
recommended
RNNs are very suitable!
Content can be considered as a
sequence of terms
Research Question
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Research Question
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Our contribution
AMAR (Ask Me Any Rating)
Deep Architecture inspired by a neural
network model used to solve Question
Answering toy tasks [*]
[*] J. Weston et al. “Towards AI-Complete Question
Answering: A Set of Prerequisite Toy Tasks”.
In: CoRR abs/1502.05698 (2015)
Research Question
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Our contribution
AMAR (Ask Me Any Rating)
Deep Architecture inspired by a neural
network model used to solve Question
Answering toy tasks [*]
[*] J. Weston et al. “Towards AI-Complete Question
Answering: A Set of Prerequisite Toy Tasks”.
In: CoRR abs/1502.05698 (2015)
Analogy
Question:Answers = User Profile:Items
AMAR: Ask Me Any Rating
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
AMAR: Ask Me Any Rating
User and Item are modeled through two embeddings
EMBEDDINGS ARE JOINTLY LEARNED
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
AMAR: Ask Me Any Rating
User and Item are modeled through two embeddings
EMBEDDINGS ARE JOINTLY LEARNED
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Given an item, its textual description w1 , ... ,wn is
represented through a RNN with LSTM cells
Each LSTM generates a latent representation h(wi)
for each word wi
The final representation of the item is obtained
through a MEAN POOLING LAYER
AMAR: Ask Me Any Rating
User and Item are modeled through two embeddings
EMBEDDINGS ARE JOINTLY LEARNED
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
The resulting embeddings are merged through a
CONCATENATION LAYER
Given an item, its textual description w1 , ... ,wn is
represented through a RNN with LSTM cells
Each LSTM generates a latent representation h(wi)
for each word wi
The final representation of the item is obtained
through a MEAN POOLING LAYER
AMAR: Ask Me Any Rating
User and Item are modeled through two embeddings
EMBEDDINGS ARE JOINTLY LEARNED
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
A LOGISTIC REGRESSION LAYER estimates user interest in
the item and builds the recommendation list.
Given an item, its textual description w1 , ... ,wn is
represented through a RNN with LSTM cells
Each LSTM generates a latent representation h(wi)
for each word wi
The final representation of the item is obtained
through a MEAN POOLING LAYER
The resulting embeddings are merged through a
CONCATENATION LAYER
AMAR+
AMAR has a very modular and extensible
architecture
It is possible to add extra modules to encode
more information beyond the simple description
of the item
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
AMAR+
AMAR has a very modular and extensible
architecture
It is possible to add extra modules to encode
more information beyond the simple description
of the item
AMAR+ introduces A GENRE EMBEDDING,which
represents the genre associated to the item to
be recommended
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
AMAR+
AMAR has a very modular and extensible
architecture
It is possible to add extra modules to encode
more information beyond the simple description
of the item
AMAR+ introduces A GENRE EMBEDDING,which
represents the genre associated to the item to
be recommended
For each genre g1, … , gm associated to an item
a genre embedding is learnt. All the embeddings
are averaged through a MEAN POOLING LAYER.
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
AMAR+
AMAR has a very modular and extensible
architecture
It is possible to add extra modules to encode
more information beyond the simple description
of the item
AMAR+ introduces A GENRE EMBEDDING,which
represents the genre associated to the item to
be recommended
For each genre g1, … , gm associated to an item
a genre embedding is learnt. All the embeddings
are averaged through a MEAN POOLING LAYER.
The new information is merged and the pipeline
estimates again the user preference in the item
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Experiments
How does our deep architecture
perform when compared to other
content-based recommender
systems or state-of-the-art
baselines?
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Datasets
MovieLens 1M (ML1M)
6,040 users
3,883 movies
1,000,209 ratings
57.51% positive ratings
165.59 ratings/user (avg.)
269.88 ratings/item (avg.)
99.4% sparsity
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Datasets
DBbook
6,181 users
6,733 movies
72,732 ratings
45.86% positive ratings
11.71 ratings/user (avg.)
10.74 ratings/item (avg.)
99.8% sparsity
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Experimental Settings
Top-N recommendation task
Metric
◦ F1@5
AMAR parameters
◦ RMSprop optimizer, 25 epochs
◦ a=0.9, learning rate 0.001
◦ Batch size 1536 (ML1M) and 512 (DBbook)
◦ Binary cross entropy as cost function
◦ User, Item and Genre embedding size = 10
Item Processing
◦ Mapping item names with Wikipedia pages
◦ Extraction of textual content from plots
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Baselines
Word Embedding techniques
◦ Word2Vec
◦ Glove
◦ Doc2Vec
◦ In Word2Vec and Glove, items/profile are represented
as the centroid vector of the representation of the word
occurring in the textual descriptions
Collaborative Filtering and Matrix Factorization
techniques
U2U-CF, I2I-CF
BPRMF, BPRSlim, WRMF
Optimal parameters. All available in MyMediaLite toolkit
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Baselines
Word Embedding techniques
◦ Word2Vec
◦ Glove
◦ Doc2Vec
◦ In Word2Vec and Glove, items/profile are represented
as the centroid vector of the representation of the word
occurring in the textual descriptions
Collaborative Filtering and Matrix Factorization
techniques
◦ U2U-CF, I2I-CF
◦ BPRMF[*], BPRSlim[+], WRMF
◦ Optimal parameters.
◦ All available in MyMediaLite toolkit
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
[*] S. Rendle, C.Freudenthaler, Z. Gantner, L. Schmidt-Thieme:
BPR: Bayesian Personalized Ranking from Implicit Feedback. UAI 2009.
[+] X. Ning, G. Karypis: Slim: Sparse linear methods for top-n recommender systems. ICDM 2011.
Results – MovieLens data
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
0.5550.558
0.49 0.482 0.485
0.427 0.431 0.425 0.423
0.446
MovieLens
AMAR AMAR+ Word2Vec Doc2Vec Glove U2U I2I BPRMF WRMF BPRSlim
0.5550.558
0.49 0.482 0.485
0.427 0.431 0.425 0.423
0.446
MovieLens
AMAR AMAR+ Word2Vec Doc2Vec Glove U2U I2I BPRMF WRMF BPRSlim
Results – MovieLens data
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Word
Embedding
techniques
0.5550.558
0.49 0.482 0.485
0.427 0.431 0.425 0.423
0.446
MovieLens
AMAR AMAR+ Word2Vec Doc2Vec Glove U2U I2I BPRMF WRMF BPRSlim
Results – MovieLens data
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Word
Embedding
techniques
Collaborative Filtering and
Matrix Factorization
techniques
Results – DBbook data
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
0.5640.565
0.542 0.54
0.552
0.536 0.536
0.508
0.519 0.511
MovieLens
AMAR AMAR+ Word2Vec Doc2Vec Glove U2U I2I BPRMF WRMF BPRSlim
0.5640.565
0.542 0.54
0.552
0.536 0.536
0.508
0.519 0.511
MovieLens
AMAR AMAR+ Word2Vec Doc2Vec Glove U2U I2I BPRMF WRMF BPRSlim
Results – DBbook data
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
AMAR and AMAR+
overcome all the
baselines
Recap
AMAR: a deep architecture for content-based recommendation exploiting RNNs
◦ Neural Network predicts the likelihood that a user would like a certain item
◦ User and Item embeddings are jointly learned.
◦ LSTMs to model textual description of the items.
Results
 AMAR and AMAR+ significantly improve all the baselines
 Modular and Extensible Architecture: AMAR+ introduces a genre embedding
 High training time (ML1M=90’ per epoch , DBbook=50’ per epoch)
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
Thanks!
Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro.
A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
cataldo.musto@uniba.it
@cataldomusto, @ale_suglia
@cld_greco, @SWAP_research

More Related Content

What's hot

Introduction to question answering for linked data & big data
Introduction to question answering for linked data & big dataIntroduction to question answering for linked data & big data
Introduction to question answering for linked data & big dataAndre Freitas
 
LUCERO - Building the Open University Web of Linked Data
LUCERO - Building the Open University Web of Linked DataLUCERO - Building the Open University Web of Linked Data
LUCERO - Building the Open University Web of Linked Data
Mathieu d'Aquin
 
Extracting Relevant Questions to an RDF Dataset Using Formal Concept Analysis
Extracting Relevant Questions to an RDF Dataset Using Formal Concept AnalysisExtracting Relevant Questions to an RDF Dataset Using Formal Concept Analysis
Extracting Relevant Questions to an RDF Dataset Using Formal Concept Analysis
Mathieu d'Aquin
 
Question Answering over Linked Data: Challenges, Approaches & Trends (Tutoria...
Question Answering over Linked Data: Challenges, Approaches & Trends (Tutoria...Question Answering over Linked Data: Challenges, Approaches & Trends (Tutoria...
Question Answering over Linked Data: Challenges, Approaches & Trends (Tutoria...Andre Freitas
 
Semantic Web Landscape 2009
Semantic Web Landscape 2009Semantic Web Landscape 2009
Semantic Web Landscape 2009
LeeFeigenbaum
 
Why should semantic technologies pay more attention to privacy... and vice-ve...
Why should semantic technologies pay more attention to privacy... and vice-ve...Why should semantic technologies pay more attention to privacy... and vice-ve...
Why should semantic technologies pay more attention to privacy... and vice-ve...
Mathieu d'Aquin
 
Question answering in linked data
Question answering in linked dataQuestion answering in linked data
Question answering in linked data
Reza Ramezani
 
Knowledge Graph Maintenance
Knowledge Graph MaintenanceKnowledge Graph Maintenance
Knowledge Graph Maintenance
Paul Groth
 
Oop principles a good book
Oop principles a good bookOop principles a good book
Oop principles a good booklahorisher
 
Managing Metadata for Science and Technology Studies: the RISIS case
Managing Metadata for Science and Technology Studies: the RISIS caseManaging Metadata for Science and Technology Studies: the RISIS case
Managing Metadata for Science and Technology Studies: the RISIS case
Rinke Hoekstra
 
Metadata Provenance Tutorial at SWIB 13, Part 1
Metadata Provenance Tutorial at SWIB 13, Part 1Metadata Provenance Tutorial at SWIB 13, Part 1
Metadata Provenance Tutorial at SWIB 13, Part 1
Kai Eckert
 
Knowledge discoverylaurahollink
Knowledge discoverylaurahollinkKnowledge discoverylaurahollink
Knowledge discoverylaurahollink
SSSW
 
Semantic Web / Linked Data Technologies
Semantic Web / Linked Data TechnologiesSemantic Web / Linked Data Technologies
Semantic Web / Linked Data Technologies
Mathieu d'Aquin
 
Doing Clever Things with the Semantic Web
Doing Clever Things with the Semantic WebDoing Clever Things with the Semantic Web
Doing Clever Things with the Semantic Web
Mathieu d'Aquin
 
Hala skafkeynote@conferencedata2021
Hala skafkeynote@conferencedata2021Hala skafkeynote@conferencedata2021
Hala skafkeynote@conferencedata2021
hala Skaf
 
Knowledge Graph Futures
Knowledge Graph FuturesKnowledge Graph Futures
Knowledge Graph Futures
Paul Groth
 
Data4Ed - How data sharing, curation and analytics support innovation in educ...
Data4Ed - How data sharing, curation and analytics support innovation in educ...Data4Ed - How data sharing, curation and analytics support innovation in educ...
Data4Ed - How data sharing, curation and analytics support innovation in educ...
Mathieu d'Aquin
 
Decentralized Data Management for the Semantic Web
Decentralized Data Management for the Semantic WebDecentralized Data Management for the Semantic Web
Decentralized Data Management for the Semantic Web
hala Skaf
 
Ziegler Open Data in Special Collections Libraries
Ziegler Open Data in Special Collections LibrariesZiegler Open Data in Special Collections Libraries
Ziegler Open Data in Special Collections Libraries
National Information Standards Organization (NISO)
 
Experience from 10 months of University Linked Data
Experience from 10 months of University Linked Data Experience from 10 months of University Linked Data
Experience from 10 months of University Linked Data
Mathieu d'Aquin
 

What's hot (20)

Introduction to question answering for linked data & big data
Introduction to question answering for linked data & big dataIntroduction to question answering for linked data & big data
Introduction to question answering for linked data & big data
 
LUCERO - Building the Open University Web of Linked Data
LUCERO - Building the Open University Web of Linked DataLUCERO - Building the Open University Web of Linked Data
LUCERO - Building the Open University Web of Linked Data
 
Extracting Relevant Questions to an RDF Dataset Using Formal Concept Analysis
Extracting Relevant Questions to an RDF Dataset Using Formal Concept AnalysisExtracting Relevant Questions to an RDF Dataset Using Formal Concept Analysis
Extracting Relevant Questions to an RDF Dataset Using Formal Concept Analysis
 
Question Answering over Linked Data: Challenges, Approaches & Trends (Tutoria...
Question Answering over Linked Data: Challenges, Approaches & Trends (Tutoria...Question Answering over Linked Data: Challenges, Approaches & Trends (Tutoria...
Question Answering over Linked Data: Challenges, Approaches & Trends (Tutoria...
 
Semantic Web Landscape 2009
Semantic Web Landscape 2009Semantic Web Landscape 2009
Semantic Web Landscape 2009
 
Why should semantic technologies pay more attention to privacy... and vice-ve...
Why should semantic technologies pay more attention to privacy... and vice-ve...Why should semantic technologies pay more attention to privacy... and vice-ve...
Why should semantic technologies pay more attention to privacy... and vice-ve...
 
Question answering in linked data
Question answering in linked dataQuestion answering in linked data
Question answering in linked data
 
Knowledge Graph Maintenance
Knowledge Graph MaintenanceKnowledge Graph Maintenance
Knowledge Graph Maintenance
 
Oop principles a good book
Oop principles a good bookOop principles a good book
Oop principles a good book
 
Managing Metadata for Science and Technology Studies: the RISIS case
Managing Metadata for Science and Technology Studies: the RISIS caseManaging Metadata for Science and Technology Studies: the RISIS case
Managing Metadata for Science and Technology Studies: the RISIS case
 
Metadata Provenance Tutorial at SWIB 13, Part 1
Metadata Provenance Tutorial at SWIB 13, Part 1Metadata Provenance Tutorial at SWIB 13, Part 1
Metadata Provenance Tutorial at SWIB 13, Part 1
 
Knowledge discoverylaurahollink
Knowledge discoverylaurahollinkKnowledge discoverylaurahollink
Knowledge discoverylaurahollink
 
Semantic Web / Linked Data Technologies
Semantic Web / Linked Data TechnologiesSemantic Web / Linked Data Technologies
Semantic Web / Linked Data Technologies
 
Doing Clever Things with the Semantic Web
Doing Clever Things with the Semantic WebDoing Clever Things with the Semantic Web
Doing Clever Things with the Semantic Web
 
Hala skafkeynote@conferencedata2021
Hala skafkeynote@conferencedata2021Hala skafkeynote@conferencedata2021
Hala skafkeynote@conferencedata2021
 
Knowledge Graph Futures
Knowledge Graph FuturesKnowledge Graph Futures
Knowledge Graph Futures
 
Data4Ed - How data sharing, curation and analytics support innovation in educ...
Data4Ed - How data sharing, curation and analytics support innovation in educ...Data4Ed - How data sharing, curation and analytics support innovation in educ...
Data4Ed - How data sharing, curation and analytics support innovation in educ...
 
Decentralized Data Management for the Semantic Web
Decentralized Data Management for the Semantic WebDecentralized Data Management for the Semantic Web
Decentralized Data Management for the Semantic Web
 
Ziegler Open Data in Special Collections Libraries
Ziegler Open Data in Special Collections LibrariesZiegler Open Data in Special Collections Libraries
Ziegler Open Data in Special Collections Libraries
 
Experience from 10 months of University Linked Data
Experience from 10 months of University Linked Data Experience from 10 months of University Linked Data
Experience from 10 months of University Linked Data
 

Viewers also liked

Technical Introduction to IBM's Open Blockchain (OBC)
Technical Introduction to IBM's Open Blockchain (OBC)Technical Introduction to IBM's Open Blockchain (OBC)
Technical Introduction to IBM's Open Blockchain (OBC)
Altoros
 
Building decentralized apps: Battle of the tech stacks
Building decentralized apps: Battle of the tech stacksBuilding decentralized apps: Battle of the tech stacks
Building decentralized apps: Battle of the tech stacks
BlockStars.io
 
DevOps Introduction and the launch of DASA
DevOps Introduction and the launch of DASADevOps Introduction and the launch of DASA
DevOps Introduction and the launch of DASA
Jan-Willem Middelburg
 
Blockchain and Distributed Ledger Technologies: An EU Policy Perspective
Blockchain and Distributed Ledger Technologies: An EU Policy PerspectiveBlockchain and Distributed Ledger Technologies: An EU Policy Perspective
Blockchain and Distributed Ledger Technologies: An EU Policy Perspective
ITU
 
Blockchain + Streaming Analytics with Ethereum and TIBCO StreamBase
Blockchain + Streaming Analytics with Ethereum and TIBCO StreamBase Blockchain + Streaming Analytics with Ethereum and TIBCO StreamBase
Blockchain + Streaming Analytics with Ethereum and TIBCO StreamBase
Kai Wähner
 
HATech DevOps Services general introduction
HATech DevOps Services general introductionHATech DevOps Services general introduction
HATech DevOps Services general introduction
HATech LLC
 
Blockchain 2015: Analyzing the Blockchain in Financial Services
Blockchain 2015: Analyzing the Blockchain in Financial ServicesBlockchain 2015: Analyzing the Blockchain in Financial Services
Blockchain 2015: Analyzing the Blockchain in Financial Services
The Business Blockchain
 
CBGTBT - Part 1 - Workshop introduction & primer
CBGTBT - Part 1 - Workshop introduction & primerCBGTBT - Part 1 - Workshop introduction & primer
CBGTBT - Part 1 - Workshop introduction & primer
Blockstrap.com
 

Viewers also liked (8)

Technical Introduction to IBM's Open Blockchain (OBC)
Technical Introduction to IBM's Open Blockchain (OBC)Technical Introduction to IBM's Open Blockchain (OBC)
Technical Introduction to IBM's Open Blockchain (OBC)
 
Building decentralized apps: Battle of the tech stacks
Building decentralized apps: Battle of the tech stacksBuilding decentralized apps: Battle of the tech stacks
Building decentralized apps: Battle of the tech stacks
 
DevOps Introduction and the launch of DASA
DevOps Introduction and the launch of DASADevOps Introduction and the launch of DASA
DevOps Introduction and the launch of DASA
 
Blockchain and Distributed Ledger Technologies: An EU Policy Perspective
Blockchain and Distributed Ledger Technologies: An EU Policy PerspectiveBlockchain and Distributed Ledger Technologies: An EU Policy Perspective
Blockchain and Distributed Ledger Technologies: An EU Policy Perspective
 
Blockchain + Streaming Analytics with Ethereum and TIBCO StreamBase
Blockchain + Streaming Analytics with Ethereum and TIBCO StreamBase Blockchain + Streaming Analytics with Ethereum and TIBCO StreamBase
Blockchain + Streaming Analytics with Ethereum and TIBCO StreamBase
 
HATech DevOps Services general introduction
HATech DevOps Services general introductionHATech DevOps Services general introduction
HATech DevOps Services general introduction
 
Blockchain 2015: Analyzing the Blockchain in Financial Services
Blockchain 2015: Analyzing the Blockchain in Financial ServicesBlockchain 2015: Analyzing the Blockchain in Financial Services
Blockchain 2015: Analyzing the Blockchain in Financial Services
 
CBGTBT - Part 1 - Workshop introduction & primer
CBGTBT - Part 1 - Workshop introduction & primerCBGTBT - Part 1 - Workshop introduction & primer
CBGTBT - Part 1 - Workshop introduction & primer
 

Similar to A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksModel-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Yoonho Lee
 
Sequence learning and modern RNNs
Sequence learning and modern RNNsSequence learning and modern RNNs
Sequence learning and modern RNNs
Grigory Sapunov
 
Deep Learning for resource-contrained systems
Deep Learning for resource-contrained systemsDeep Learning for resource-contrained systems
Deep Learning for resource-contrained systems
inside-BigData.com
 
Recent developments in Deep Learning
Recent developments in Deep LearningRecent developments in Deep Learning
Recent developments in Deep Learning
Brahim HAMADICHAREF
 
Validation of hardness and tensile strength of al 7075 based hybrid composite...
Validation of hardness and tensile strength of al 7075 based hybrid composite...Validation of hardness and tensile strength of al 7075 based hybrid composite...
Validation of hardness and tensile strength of al 7075 based hybrid composite...
IAEME Publication
 
Image Steganography: An Inevitable Need for Data Security, Authors: Sneh Rach...
Image Steganography: An Inevitable Need for Data Security, Authors: Sneh Rach...Image Steganography: An Inevitable Need for Data Security, Authors: Sneh Rach...
Image Steganography: An Inevitable Need for Data Security, Authors: Sneh Rach...
Rajesh Kumar
 
Proposing a new method of image classification based on the AdaBoost deep bel...
Proposing a new method of image classification based on the AdaBoost deep bel...Proposing a new method of image classification based on the AdaBoost deep bel...
Proposing a new method of image classification based on the AdaBoost deep bel...
TELKOMNIKA JOURNAL
 
Image captioning using DL and NLP.pptx
Image captioning using DL and NLP.pptxImage captioning using DL and NLP.pptx
Image captioning using DL and NLP.pptx
MrUnknown820784
 
neuromorphic computing.pdf
neuromorphic computing.pdfneuromorphic computing.pdf
neuromorphic computing.pdf
kirti617012
 
July 2022: Top 10 Read Articles in Signal & Image Processing
July 2022: Top 10 Read Articles in Signal & Image ProcessingJuly 2022: Top 10 Read Articles in Signal & Image Processing
July 2022: Top 10 Read Articles in Signal & Image Processing
sipij
 
Deep Learning for X ray Image to Text Generation
Deep Learning for X ray Image to Text GenerationDeep Learning for X ray Image to Text Generation
Deep Learning for X ray Image to Text Generation
ijtsrd
 
April 2023: Top 10 Read Articles in Signal & Image Processing
April 2023: Top 10 Read Articles in Signal & Image ProcessingApril 2023: Top 10 Read Articles in Signal & Image Processing
April 2023: Top 10 Read Articles in Signal & Image Processing
sipij
 
September 2022: Top 10 Read Articles in Signal & Image Processing
September 2022: Top 10 Read Articles in Signal & Image ProcessingSeptember 2022: Top 10 Read Articles in Signal & Image Processing
September 2022: Top 10 Read Articles in Signal & Image Processing
sipij
 
June 2022: Top 10 Read Articles in Signal & Image Processing
June 2022: Top 10 Read Articles in Signal & Image   ProcessingJune 2022: Top 10 Read Articles in Signal & Image   Processing
June 2022: Top 10 Read Articles in Signal & Image Processing
sipij
 
Image Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine LearningImage Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine Learning
ijtsrd
 
How data science works and how can customers help
How data science works and how can customers helpHow data science works and how can customers help
How data science works and how can customers help
Danko Nikolic
 
Deep Video Object Segmentation - Xavier Giro - UPC Barcelona 2019
Deep Video Object Segmentation - Xavier Giro - UPC Barcelona 2019Deep Video Object Segmentation - Xavier Giro - UPC Barcelona 2019
Deep Video Object Segmentation - Xavier Giro - UPC Barcelona 2019
Universitat Politècnica de Catalunya
 
August 2022: Top 10 Read Articles in Signal & Image Processing
August 2022: Top 10 Read Articles in Signal & Image ProcessingAugust 2022: Top 10 Read Articles in Signal & Image Processing
August 2022: Top 10 Read Articles in Signal & Image Processing
sipij
 
May 2022: Top Read Articles in Signal & Image Processing
May 2022: Top Read Articles in Signal & Image ProcessingMay 2022: Top Read Articles in Signal & Image Processing
May 2022: Top Read Articles in Signal & Image Processing
sipij
 
October 2022: Top 10 Read Articles in Signal & Image Processing
October 2022: Top 10 Read Articles in Signal & Image ProcessingOctober 2022: Top 10 Read Articles in Signal & Image Processing
October 2022: Top 10 Read Articles in Signal & Image Processing
sipij
 

Similar to A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks (20)

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Model-Agnostic Meta-Learning for Fast Adaptation of Deep NetworksModel-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
 
Sequence learning and modern RNNs
Sequence learning and modern RNNsSequence learning and modern RNNs
Sequence learning and modern RNNs
 
Deep Learning for resource-contrained systems
Deep Learning for resource-contrained systemsDeep Learning for resource-contrained systems
Deep Learning for resource-contrained systems
 
Recent developments in Deep Learning
Recent developments in Deep LearningRecent developments in Deep Learning
Recent developments in Deep Learning
 
Validation of hardness and tensile strength of al 7075 based hybrid composite...
Validation of hardness and tensile strength of al 7075 based hybrid composite...Validation of hardness and tensile strength of al 7075 based hybrid composite...
Validation of hardness and tensile strength of al 7075 based hybrid composite...
 
Image Steganography: An Inevitable Need for Data Security, Authors: Sneh Rach...
Image Steganography: An Inevitable Need for Data Security, Authors: Sneh Rach...Image Steganography: An Inevitable Need for Data Security, Authors: Sneh Rach...
Image Steganography: An Inevitable Need for Data Security, Authors: Sneh Rach...
 
Proposing a new method of image classification based on the AdaBoost deep bel...
Proposing a new method of image classification based on the AdaBoost deep bel...Proposing a new method of image classification based on the AdaBoost deep bel...
Proposing a new method of image classification based on the AdaBoost deep bel...
 
Image captioning using DL and NLP.pptx
Image captioning using DL and NLP.pptxImage captioning using DL and NLP.pptx
Image captioning using DL and NLP.pptx
 
neuromorphic computing.pdf
neuromorphic computing.pdfneuromorphic computing.pdf
neuromorphic computing.pdf
 
July 2022: Top 10 Read Articles in Signal & Image Processing
July 2022: Top 10 Read Articles in Signal & Image ProcessingJuly 2022: Top 10 Read Articles in Signal & Image Processing
July 2022: Top 10 Read Articles in Signal & Image Processing
 
Deep Learning for X ray Image to Text Generation
Deep Learning for X ray Image to Text GenerationDeep Learning for X ray Image to Text Generation
Deep Learning for X ray Image to Text Generation
 
April 2023: Top 10 Read Articles in Signal & Image Processing
April 2023: Top 10 Read Articles in Signal & Image ProcessingApril 2023: Top 10 Read Articles in Signal & Image Processing
April 2023: Top 10 Read Articles in Signal & Image Processing
 
September 2022: Top 10 Read Articles in Signal & Image Processing
September 2022: Top 10 Read Articles in Signal & Image ProcessingSeptember 2022: Top 10 Read Articles in Signal & Image Processing
September 2022: Top 10 Read Articles in Signal & Image Processing
 
June 2022: Top 10 Read Articles in Signal & Image Processing
June 2022: Top 10 Read Articles in Signal & Image   ProcessingJune 2022: Top 10 Read Articles in Signal & Image   Processing
June 2022: Top 10 Read Articles in Signal & Image Processing
 
Image Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine LearningImage Captioning Generator using Deep Machine Learning
Image Captioning Generator using Deep Machine Learning
 
How data science works and how can customers help
How data science works and how can customers helpHow data science works and how can customers help
How data science works and how can customers help
 
Deep Video Object Segmentation - Xavier Giro - UPC Barcelona 2019
Deep Video Object Segmentation - Xavier Giro - UPC Barcelona 2019Deep Video Object Segmentation - Xavier Giro - UPC Barcelona 2019
Deep Video Object Segmentation - Xavier Giro - UPC Barcelona 2019
 
August 2022: Top 10 Read Articles in Signal & Image Processing
August 2022: Top 10 Read Articles in Signal & Image ProcessingAugust 2022: Top 10 Read Articles in Signal & Image Processing
August 2022: Top 10 Read Articles in Signal & Image Processing
 
May 2022: Top Read Articles in Signal & Image Processing
May 2022: Top Read Articles in Signal & Image ProcessingMay 2022: Top Read Articles in Signal & Image Processing
May 2022: Top Read Articles in Signal & Image Processing
 
October 2022: Top 10 Read Articles in Signal & Image Processing
October 2022: Top 10 Read Articles in Signal & Image ProcessingOctober 2022: Top 10 Read Articles in Signal & Image Processing
October 2022: Top 10 Read Articles in Signal & Image Processing
 

More from Cataldo Musto

MyrrorBot: a Digital Assistant Based on Holistic User Models for Personalize...
MyrrorBot: a Digital Assistant Based on Holistic User Models forPersonalize...MyrrorBot: a Digital Assistant Based on Holistic User Models forPersonalize...
MyrrorBot: a Digital Assistant Based on Holistic User Models for Personalize...
Cataldo Musto
 
Fairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical EvaluationFairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Cataldo Musto
 
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
Cataldo Musto
 
Exploring the Effects of Natural Language Justifications in Food Recommender ...
Exploring the Effects of Natural Language Justifications in Food Recommender ...Exploring the Effects of Natural Language Justifications in Food Recommender ...
Exploring the Effects of Natural Language Justifications in Food Recommender ...
Cataldo Musto
 
Exploiting Distributional Semantics Models for Natural Language Context-aware...
Exploiting Distributional Semantics Models for Natural Language Context-aware...Exploiting Distributional Semantics Models for Natural Language Context-aware...
Exploiting Distributional Semantics Models for Natural Language Context-aware...
Cataldo Musto
 
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
Cataldo Musto
 
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
Cataldo Musto
 
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph EmbeddingsHybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
Cataldo Musto
 
Natural Language Justifications for Recommender Systems Exploiting Text Summa...
Natural Language Justifications for Recommender Systems Exploiting Text Summa...Natural Language Justifications for Recommender Systems Exploiting Text Summa...
Natural Language Justifications for Recommender Systems Exploiting Text Summa...
Cataldo Musto
 
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA RispondeL'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
Cataldo Musto
 
Explanation Strategies - Advances in Content-based Recommender System
Explanation Strategies - Advances in Content-based Recommender SystemExplanation Strategies - Advances in Content-based Recommender System
Explanation Strategies - Advances in Content-based Recommender System
Cataldo Musto
 
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
Cataldo Musto
 
ExpLOD: un framework per la generazione di spiegazioni per recommender system...
ExpLOD: un framework per la generazione di spiegazioni per recommender system...ExpLOD: un framework per la generazione di spiegazioni per recommender system...
ExpLOD: un framework per la generazione di spiegazioni per recommender system...
Cataldo Musto
 
Myrror: una piattaforma per Holistic User Modeling e Quantified Self
Myrror: una piattaforma per Holistic User Modeling e Quantified SelfMyrror: una piattaforma per Holistic User Modeling e Quantified Self
Myrror: una piattaforma per Holistic User Modeling e Quantified Self
Cataldo Musto
 
Semantic Holistic User Modeling for Personalized Access to Digital Content an...
Semantic Holistic User Modeling for Personalized Access to Digital Content an...Semantic Holistic User Modeling for Personalized Access to Digital Content an...
Semantic Holistic User Modeling for Personalized Access to Digital Content an...
Cataldo Musto
 
Holistic User Modeling for Personalized Services in Smart Cities
Holistic User Modeling for Personalized Services in Smart CitiesHolistic User Modeling for Personalized Services in Smart Cities
Holistic User Modeling for Personalized Services in Smart Cities
Cataldo Musto
 
A Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
A Framework for Holistic User Modeling Merging Heterogeneous Digital FootprintsA Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
A Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
Cataldo Musto
 
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
Cataldo Musto
 
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
Cataldo Musto
 
Il Linguaggio dell'Odio sui Social Network
Il Linguaggio dell'Odio sui Social NetworkIl Linguaggio dell'Odio sui Social Network
Il Linguaggio dell'Odio sui Social Network
Cataldo Musto
 

More from Cataldo Musto (20)

MyrrorBot: a Digital Assistant Based on Holistic User Models for Personalize...
MyrrorBot: a Digital Assistant Based on Holistic User Models forPersonalize...MyrrorBot: a Digital Assistant Based on Holistic User Models forPersonalize...
MyrrorBot: a Digital Assistant Based on Holistic User Models for Personalize...
 
Fairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical EvaluationFairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
 
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
Intelligenza Artificiale e Social Media - Monitoraggio della Farnesina e La M...
 
Exploring the Effects of Natural Language Justifications in Food Recommender ...
Exploring the Effects of Natural Language Justifications in Food Recommender ...Exploring the Effects of Natural Language Justifications in Food Recommender ...
Exploring the Effects of Natural Language Justifications in Food Recommender ...
 
Exploiting Distributional Semantics Models for Natural Language Context-aware...
Exploiting Distributional Semantics Models for Natural Language Context-aware...Exploiting Distributional Semantics Models for Natural Language Context-aware...
Exploiting Distributional Semantics Models for Natural Language Context-aware...
 
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
Towards a Knowledge-aware Food Recommender System Exploiting Holistic User Mo...
 
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
Towards Queryable User Profiles: Introducing Conversational Agents in a Platf...
 
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph EmbeddingsHybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
Hybrid Semantics aware Recommendations Exploiting Knowledge Graph Embeddings
 
Natural Language Justifications for Recommender Systems Exploiting Text Summa...
Natural Language Justifications for Recommender Systems Exploiting Text Summa...Natural Language Justifications for Recommender Systems Exploiting Text Summa...
Natural Language Justifications for Recommender Systems Exploiting Text Summa...
 
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA RispondeL'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
L'IA per l'Empowerment del Cittadino: Hate Map, Myrror, PA Risponde
 
Explanation Strategies - Advances in Content-based Recommender System
Explanation Strategies - Advances in Content-based Recommender SystemExplanation Strategies - Advances in Content-based Recommender System
Explanation Strategies - Advances in Content-based Recommender System
 
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
Justifying Recommendations through Aspect-based Sentiment Analysis of Users R...
 
ExpLOD: un framework per la generazione di spiegazioni per recommender system...
ExpLOD: un framework per la generazione di spiegazioni per recommender system...ExpLOD: un framework per la generazione di spiegazioni per recommender system...
ExpLOD: un framework per la generazione di spiegazioni per recommender system...
 
Myrror: una piattaforma per Holistic User Modeling e Quantified Self
Myrror: una piattaforma per Holistic User Modeling e Quantified SelfMyrror: una piattaforma per Holistic User Modeling e Quantified Self
Myrror: una piattaforma per Holistic User Modeling e Quantified Self
 
Semantic Holistic User Modeling for Personalized Access to Digital Content an...
Semantic Holistic User Modeling for Personalized Access to Digital Content an...Semantic Holistic User Modeling for Personalized Access to Digital Content an...
Semantic Holistic User Modeling for Personalized Access to Digital Content an...
 
Holistic User Modeling for Personalized Services in Smart Cities
Holistic User Modeling for Personalized Services in Smart CitiesHolistic User Modeling for Personalized Services in Smart Cities
Holistic User Modeling for Personalized Services in Smart Cities
 
A Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
A Framework for Holistic User Modeling Merging Heterogeneous Digital FootprintsA Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
A Framework for Holistic User Modeling Merging Heterogeneous Digital Footprints
 
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
eHealth, mHealth in Otorinolaringoiatria: innovazioni dirompenti o disastrose?
 
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
Semantics-aware Recommender Systems Exploiting Linked Open Data and Graph-bas...
 
Il Linguaggio dell'Odio sui Social Network
Il Linguaggio dell'Odio sui Social NetworkIl Linguaggio dell'Odio sui Social Network
Il Linguaggio dell'Odio sui Social Network
 

Recently uploaded

Influence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business PlanInfluence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business Plan
jerlynmaetalle
 
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
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
Subhajit Sahu
 
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
 
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptxData_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
AnirbanRoy608946
 
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
oz8q3jxlp
 
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
 
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
v3tuleee
 
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
nscud
 
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
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
Timothy Spann
 
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
ukgaet
 
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
 
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...
John Andrews
 
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
ahzuo
 
Empowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptxEmpowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptx
benishzehra469
 
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
 
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
u86oixdj
 
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
slg6lamcq
 
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
 

Recently uploaded (20)

Influence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business PlanInfluence of Marketing Strategy and Market Competition on Business Plan
Influence of Marketing Strategy and Market Competition on Business Plan
 
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
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
 
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
 
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptxData_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
Data_and_Analytics_Essentials_Architect_an_Analytics_Platform.pptx
 
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
一比一原版(Deakin毕业证书)迪肯大学毕业证如何办理
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
 
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理一比一原版(UofS毕业证书)萨省大学毕业证如何办理
一比一原版(UofS毕业证书)萨省大学毕业证如何办理
 
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
一比一原版(CBU毕业证)不列颠海角大学毕业证成绩单
 
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
 
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
06-04-2024 - NYC Tech Week - Discussion on Vector Databases, Unstructured Dat...
 
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利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(UPenn毕业证)宾夕法尼亚大学毕业证成绩单
 
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...
Chatty Kathy - UNC Bootcamp Final Project Presentation - Final Version - 5.23...
 
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
一比一原版(UIUC毕业证)伊利诺伊大学|厄巴纳-香槟分校毕业证如何办理
 
Empowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptxEmpowering Data Analytics Ecosystem.pptx
Empowering Data Analytics Ecosystem.pptx
 
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
 
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
原版制作(Deakin毕业证书)迪肯大学毕业证学位证一模一样
 
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
 
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
 

A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks

  • 1. @cataldomusto @ale_suglia @cld_greco @SWAP_research A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks ALESSANDRO SUGLIA, CLAUDIO GRECO, CATALDO MUSTO, MARCO DE GEMMIS, PASQUALE LOPS, GIOVANNI SEMERARO UNIVERSITÀ DEGLI STUDI DI BARI ‘ALDO MORO’ - ITALY 25th International Conference on User Modeling, Adaptation and Personalization Bratislava, Slovakia July 12, 2017 cataldo.musto@uniba.it
  • 2. Recurrent Neural Networks (RNNs) Widespread Deep Learning Architecture ◦ Based on Neural Networks ◦ The connections between the units may contain loops which let consider past states in the learning process ◦ Very suitable to model variable-length sequential data Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 3. Recurrent Neural Networks (RNNs) Widespread Deep Learning Architecture ◦ Based on Neural Networks ◦ The connections between the units may contain loops which let consider past states in the learning process ◦ Very suitable to model variable-length sequential data PROS CONS ◦ Very good performance in different tasks ◦ Can learn short-term and long-term (temporal) dependencies ◦ Vanishing/exploding gradient problem Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 4. Recurrent Neural Networks (RNNs) Widespread Deep Learning Architecture ◦ Based on Neural Networks ◦ The connections between the units may contain loops which let consider past states in the learning process ◦ Very suitable to model variable-length sequential data PROS CONS ◦ Very good performance in different tasks ◦ Can learn short-term and long-term (temporal) dependencies ◦ Vanishing/exploding gradient problem LONG-SHORT TERM MEMORY NETWORKS (LSTMS) ◦ Introduced to solve the vanishing/exploding gradient problem Each cell presents a complex structure which is more powerful than simple RNN cells. Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 5. Motivations Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 ? In content-based recommender systems suggestions are generated by matching the features stored in the user profile with those describing the items to be recommended
  • 6. Motivations Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 user profile ? items In content-based recommender systems suggestions are generated by matching the features stored in the user profile with those describing the items to be recommended
  • 7. Motivations Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 user profile ? items In content-based recommender systems suggestions are generated by matching the features stored in the user profile with those describing the items to be recommended Content Representation plays a key role!
  • 8. Motivations Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 user profile ? items In content-based recommender systems suggestions are generated by matching the features stored in the user profile with those describing the items to be recommended RNNs are very suitable! Content can be considered as a sequence of terms
  • 9. Research Question Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 10. Research Question Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 Our contribution AMAR (Ask Me Any Rating) Deep Architecture inspired by a neural network model used to solve Question Answering toy tasks [*] [*] J. Weston et al. “Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks”. In: CoRR abs/1502.05698 (2015)
  • 11. Research Question Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 Our contribution AMAR (Ask Me Any Rating) Deep Architecture inspired by a neural network model used to solve Question Answering toy tasks [*] [*] J. Weston et al. “Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks”. In: CoRR abs/1502.05698 (2015) Analogy Question:Answers = User Profile:Items
  • 12. AMAR: Ask Me Any Rating Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 13. AMAR: Ask Me Any Rating User and Item are modeled through two embeddings EMBEDDINGS ARE JOINTLY LEARNED Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 14. AMAR: Ask Me Any Rating User and Item are modeled through two embeddings EMBEDDINGS ARE JOINTLY LEARNED Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 Given an item, its textual description w1 , ... ,wn is represented through a RNN with LSTM cells Each LSTM generates a latent representation h(wi) for each word wi The final representation of the item is obtained through a MEAN POOLING LAYER
  • 15. AMAR: Ask Me Any Rating User and Item are modeled through two embeddings EMBEDDINGS ARE JOINTLY LEARNED Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 The resulting embeddings are merged through a CONCATENATION LAYER Given an item, its textual description w1 , ... ,wn is represented through a RNN with LSTM cells Each LSTM generates a latent representation h(wi) for each word wi The final representation of the item is obtained through a MEAN POOLING LAYER
  • 16. AMAR: Ask Me Any Rating User and Item are modeled through two embeddings EMBEDDINGS ARE JOINTLY LEARNED Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 A LOGISTIC REGRESSION LAYER estimates user interest in the item and builds the recommendation list. Given an item, its textual description w1 , ... ,wn is represented through a RNN with LSTM cells Each LSTM generates a latent representation h(wi) for each word wi The final representation of the item is obtained through a MEAN POOLING LAYER The resulting embeddings are merged through a CONCATENATION LAYER
  • 17. AMAR+ AMAR has a very modular and extensible architecture It is possible to add extra modules to encode more information beyond the simple description of the item Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 18. AMAR+ AMAR has a very modular and extensible architecture It is possible to add extra modules to encode more information beyond the simple description of the item AMAR+ introduces A GENRE EMBEDDING,which represents the genre associated to the item to be recommended Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 19. AMAR+ AMAR has a very modular and extensible architecture It is possible to add extra modules to encode more information beyond the simple description of the item AMAR+ introduces A GENRE EMBEDDING,which represents the genre associated to the item to be recommended For each genre g1, … , gm associated to an item a genre embedding is learnt. All the embeddings are averaged through a MEAN POOLING LAYER. Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 20. AMAR+ AMAR has a very modular and extensible architecture It is possible to add extra modules to encode more information beyond the simple description of the item AMAR+ introduces A GENRE EMBEDDING,which represents the genre associated to the item to be recommended For each genre g1, … , gm associated to an item a genre embedding is learnt. All the embeddings are averaged through a MEAN POOLING LAYER. The new information is merged and the pipeline estimates again the user preference in the item Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 21. Experiments How does our deep architecture perform when compared to other content-based recommender systems or state-of-the-art baselines? Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 22. Datasets MovieLens 1M (ML1M) 6,040 users 3,883 movies 1,000,209 ratings 57.51% positive ratings 165.59 ratings/user (avg.) 269.88 ratings/item (avg.) 99.4% sparsity Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 23. Datasets DBbook 6,181 users 6,733 movies 72,732 ratings 45.86% positive ratings 11.71 ratings/user (avg.) 10.74 ratings/item (avg.) 99.8% sparsity Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 24. Experimental Settings Top-N recommendation task Metric ◦ F1@5 AMAR parameters ◦ RMSprop optimizer, 25 epochs ◦ a=0.9, learning rate 0.001 ◦ Batch size 1536 (ML1M) and 512 (DBbook) ◦ Binary cross entropy as cost function ◦ User, Item and Genre embedding size = 10 Item Processing ◦ Mapping item names with Wikipedia pages ◦ Extraction of textual content from plots Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 25. Baselines Word Embedding techniques ◦ Word2Vec ◦ Glove ◦ Doc2Vec ◦ In Word2Vec and Glove, items/profile are represented as the centroid vector of the representation of the word occurring in the textual descriptions Collaborative Filtering and Matrix Factorization techniques U2U-CF, I2I-CF BPRMF, BPRSlim, WRMF Optimal parameters. All available in MyMediaLite toolkit Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 26. Baselines Word Embedding techniques ◦ Word2Vec ◦ Glove ◦ Doc2Vec ◦ In Word2Vec and Glove, items/profile are represented as the centroid vector of the representation of the word occurring in the textual descriptions Collaborative Filtering and Matrix Factorization techniques ◦ U2U-CF, I2I-CF ◦ BPRMF[*], BPRSlim[+], WRMF ◦ Optimal parameters. ◦ All available in MyMediaLite toolkit Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 [*] S. Rendle, C.Freudenthaler, Z. Gantner, L. Schmidt-Thieme: BPR: Bayesian Personalized Ranking from Implicit Feedback. UAI 2009. [+] X. Ning, G. Karypis: Slim: Sparse linear methods for top-n recommender systems. ICDM 2011.
  • 27. Results – MovieLens data Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 0.5550.558 0.49 0.482 0.485 0.427 0.431 0.425 0.423 0.446 MovieLens AMAR AMAR+ Word2Vec Doc2Vec Glove U2U I2I BPRMF WRMF BPRSlim
  • 28. 0.5550.558 0.49 0.482 0.485 0.427 0.431 0.425 0.423 0.446 MovieLens AMAR AMAR+ Word2Vec Doc2Vec Glove U2U I2I BPRMF WRMF BPRSlim Results – MovieLens data Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 Word Embedding techniques
  • 29. 0.5550.558 0.49 0.482 0.485 0.427 0.431 0.425 0.423 0.446 MovieLens AMAR AMAR+ Word2Vec Doc2Vec Glove U2U I2I BPRMF WRMF BPRSlim Results – MovieLens data Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 Word Embedding techniques Collaborative Filtering and Matrix Factorization techniques
  • 30. Results – DBbook data Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 0.5640.565 0.542 0.54 0.552 0.536 0.536 0.508 0.519 0.511 MovieLens AMAR AMAR+ Word2Vec Doc2Vec Glove U2U I2I BPRMF WRMF BPRSlim
  • 31. 0.5640.565 0.542 0.54 0.552 0.536 0.536 0.508 0.519 0.511 MovieLens AMAR AMAR+ Word2Vec Doc2Vec Glove U2U I2I BPRMF WRMF BPRSlim Results – DBbook data Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 AMAR and AMAR+ overcome all the baselines
  • 32. Recap AMAR: a deep architecture for content-based recommendation exploiting RNNs ◦ Neural Network predicts the likelihood that a user would like a certain item ◦ User and Item embeddings are jointly learned. ◦ LSTMs to model textual description of the items. Results  AMAR and AMAR+ significantly improve all the baselines  Modular and Extensible Architecture: AMAR+ introduces a genre embedding  High training time (ML1M=90’ per epoch , DBbook=50’ per epoch) Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017
  • 33. Thanks! Alessandro Suglia, Claudio Greco, Cataldo Musto, Marco de Gemmis, Pasquale Lops, Giovanni Semeraro. A Deep Architecture for Content-based Recommendations Exploiting Recurrent Neural Networks. UMAP 2017. Bratislava, Slovakia. July 12, 2017 cataldo.musto@uniba.it @cataldomusto, @ale_suglia @cld_greco, @SWAP_research