SlideShare a Scribd company logo
1 of 42
Download to read offline
On the Reproducibility of the
TAGME Entity Linking System
Faegheh Hasibi, Krisztian Balog, Svein Erik Bratsberg
ECIR conference, March 2016
England national football
team
1966 FIFA World Cup Argentina national football
team
Entity linking
British expatriates brought football to Argentina in the 19th
century. 

The rivalry between the England and Argentina national
football teams, however, is generally traced back to the 

1966 FIFA World Cup.
TAGME
TAGME
• Cited:
‣ >50 times based on ACM DL
‣ > 200 based on Google scholar
• One of the must-have baselines
• Delivers competitive results
‣ 1st and 2nd ranked systems of the ERD
challenge used TAGME
- P. Ferragina and U. Scaiella. TAGME: On-the-fly annotation of short text fragments (by Wikipedia
entities). In Proc. of CIKM ’10, pages 1625–1628, 2010.
- P. Ferragina and U. Scaiella. Fast and accurate annotation of short texts with Wikipedia pages. CoRR,
abs/1006.3498, 2010.
Offers invaluable sources for reproducibility:
• Test collections
• Source code
• RESTful API
• GUI demo
TAGME
In this talk …
✓ Repeatability
✓ Reproducibility
✓ Generalizability
J. Arguello, F. Diaz, J. Lin, and A. Trotman. SIGIR 2015 Workshop on Reproducibility, Inexplicability,
and Generalizability of Results (RIGOR). In Proc. of SIGIR '15, pages1147-1148.
In this talk …
✓ Repeatability
✓ Reproducibility
✓ Generalizability
“Repeating a previous result under the original conditions
(e.g., same dataset and system configuration).”
“Reproducing a previous result under different, but comparable
conditions (e.g., different, but comparable dataset).”
“Applying an existing, empirically validated technique to a different IR
task/domain than the original.”
J. Arguello, F. Diaz, J. Lin, and A. Trotman. SIGIR 2015 Workshop on Reproducibility, Inexplicability,
and Generalizability of Results (RIGOR). In Proc. of SIGIR '15, pages1147-1148.
Question
• Does the code actually implement what is described in the paper?
• We need to (re)implement the entity linking method
• Integrating in a larger framework
• Making a (fair) comparison between different entity linking
approaches
What is the point of reproducibility experiments
when the source code is made available?
Our goal is …
• Learn about reproducibility
• Verification
• Criticism
Agenda
• Overview of TAGME
• Repeatability
• Reproducibility
• Generalizability
• Lessons to be learned
Agenda
• Overview of TAGME
• Repeatability
• Reproducibility
• Generalizability
• Lessons to be learned
Approach
British expatriates brought football to
Argentina in the 19th century.
The rivalry between the England and
Argentina national …
- England
- England National Football Team
- England Cricket Team
…
British: United Kingdom
expatriates: Expatriate
century: Century (song)
England: England
…
British: United Kingdom
expatriates: Expatriate
century: Century (song)
England: England
…
Parsing Disambiguation PruningText
Annotated
text
Test collections
• Wiki-Disamb30
‣ For evaluating disambiguation phase
‣ Each snippet is linked to single entity
• Wiki-Annot30
‣ For evaluating end-to-end performance
‣ All entity mentions are annotated

☞ Number of snippets deviate from what is reported in the paper
#Snippets Original Paper
Wiki-Disamb30 2M 1.4M
Wiki-Annot30 185K 180K
Repeatability
Repeating previous results under the original conditions
Repeatability challenges
• Unavailability of Wikipedia dump Nov. 2009
‣ Could not be provided by the TAGME authors
• Unavailability of training and test set splits
• Discrepancies between the number of snippets
Repeatability
‣ Weka could load 1.4M snippets of Wiki-Disamb30
‣ Whole Wiki-Annot30 is used; difference is a matter of approximation
TAGME results are not repeatable due to
unavailability of data
Post-acceptance responses:
Reproducibility
Reproducing results under different, but comparable conditions
Reproducibility
TAGME paper results are compared with:
• TAGME API (similar to running the source code)
• implementation of TAGME
• Our implementation
D. Ceccarelli, C. Lucchese, S. Orlando, R. Perego, and S. Trani. Dexter: An open source framework for
entity linking. In Proc. of the Sixth International Workshop on Exploiting Semantic Annotations in
Information Retrieval, pages 17–20, 2013.
Implementation
• Implementation is based on the paper
• Whenever in doubt: checking the source code
• The closet available Wikipedia dump: April 2010
Implementation
Link probability:
Number of times mention m appears as a link
Number of times mention m occurs in Wikipedia (as a link or not)
Implementation
Link probability:
‣ Due to efficiency reasons TAGME makes estimations
Number of articles containing the mention m
➝
Implementation
Link probability:
‣ Due to efficiency reasons TAGME makes estimations
Number of articles containing the mention m
➝
Number of articles mention m is linked to an entity
(Wikipedia creates link for the first occurrence of an entity)
≈
Implementation
Link probability:
‣ Due to efficiency reasons TAGME makes estimations
‣ In fact, TAGME implements Keyphraseness:
Implementation
Relatedness:
• Defined as:
Implementation
Relatedness:
• Defined as:• Implemented as:
Implementation
Relatedness:
• Defined as:• Implemented as:
Pruning based on commonness:
• TAGME performs and extra pruning in the parsing step
• We followed TAGME, as it makes the system considerably faster
Table 1
Results to be reproduced:
Approach:
• Submit Wiki-Disamb30 snippets to the TAGME API
• Set the pruning threshold to 0
Table 1-Evaluation metrics
Several questions are left unanswered:
• Are the metrics micro- or macro-averaged?
• What are the matching criteria for the mentions?
‣ E.g. “New York City” = “New York”
?
Table 1-Evaluation metrics
We computed the upper bound:
• If any of the entities matches the ground truth:
‣ Precision =1 Recall = 1
• Otherwise:
‣ Precision =0 Recall = 0
Other interpretation of precision or recall would result in a lower number.
Table 1- Results
Given the magnitude of the differences, even against their own API,
we did not get the results for our implementation.
Reproducing of the disambiguation phase:
Table 1- Results
Our initial guess:
• Discrepancy between the number of snippets made differences
Post-acceptance responses:
‣ TAGME performs extra (undocumented) filtering before pruning
‣ Computation of evaluation metrics are explained
Table 2
Results to be reproduced:
Table 2- Results
TAGME results are reproducible through
its own API.
Table 2- Results
Post-acceptance responses:
‣ TAGME uses wiki page-to-page link records, while our (and Dexter’s)
implementation extracts links from the body of the pages.
‣ TAGME API and Source code corresponds to a newer version (v.2)
‣ Several optimizations has been performed in v.2
‣ The evaluation metrics are micro-averaged
Generalizability
Applying an existing technique to a different IR task/domain
Entity Linking in Queries
(ELQ)
Entity linking Entity linking in queries
“new york pizza manhattan” {New York City, Manhattan}
{New York City, Manhattan}
{New York-style Pizza, Manhattan}
“cambridge population” {Cambridge}
{Cambridge}
{Cambridge, Massachusetts}
- F. Hasibi, K. Balog, and S. E. Bratsberg. Entity Linking in Queries: Tasks and Evaluation. In Proc. of the
ICTIR ’15, pages 171–180, 2015.
- D. Carmel, M.-W. Chang, E. Gabrilovich,B.-J.P. Hsu, and K. Wang. ERD’14: Entity recognition and
disambiguation challenge. SIGIR Forum, 48(2):63–77, 2014.
Why ELQ?
TAGME has great potential to be used for ELQ
✓ Designed to operate with short texts
✓ On-fly-annotation
Generalizability
TAGME results are generalizable to the task of
entity linking in queries.
TAGME API > Dexter > TAGME-wp12 > TAGME-wp10
Lessons learned
Lessons learned 1/2
• All technical details that affect performance should
be mentioned in the paper
• Differences between the published approach and
publicly API/code should be made explicit
Lessons learned 2/2
• Evaluation metrics should be explained in detail
• Keep all data sources used in a published paper
Maintain an “online appendix” to a publication
• Extra details can be explained there
• Can be easily edited and extended
Thanks!
Questions?
Check our online appendix
http://bit.ly/tagme-rep

More Related Content

What's hot

An Empirical Comparison of Knowledge Graph Embeddings for Item Recommendation
An Empirical Comparison of Knowledge Graph Embeddings for Item RecommendationAn Empirical Comparison of Knowledge Graph Embeddings for Item Recommendation
An Empirical Comparison of Knowledge Graph Embeddings for Item RecommendationEnrico Palumbo
 
NEEL2015 challenge summary
NEEL2015 challenge summaryNEEL2015 challenge summary
NEEL2015 challenge summaryGiuseppe Rizzo
 
Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Andre Freitas
 
Strategies for Processing and Explaining Distributed Queries on Linked Data
Strategies for Processing and Explaining Distributed Queries on Linked DataStrategies for Processing and Explaining Distributed Queries on Linked Data
Strategies for Processing and Explaining Distributed Queries on Linked DataRakebul Hasan
 
EARL: Joint Entity and Relation Linking for Question Answering over Knowledge...
EARL: Joint Entity and Relation Linking for Question Answering over Knowledge...EARL: Joint Entity and Relation Linking for Question Answering over Knowledge...
EARL: Joint Entity and Relation Linking for Question Answering over Knowledge...Holistic Benchmarking of Big Linked Data
 
Linkanalysis handout
Linkanalysis handoutLinkanalysis handout
Linkanalysis handoutcsedays
 
Executing SPARQL Queries over Mapped Document Stores with SparqlMap-M
Executing SPARQL Queries over Mapped Document Stores with SparqlMap-MExecuting SPARQL Queries over Mapped Document Stores with SparqlMap-M
Executing SPARQL Queries over Mapped Document Stores with SparqlMap-MLinked Enterprise Date Services
 
Introduction to Named Entity Recognition
Introduction to Named Entity RecognitionIntroduction to Named Entity Recognition
Introduction to Named Entity RecognitionTomer Lieber
 
Logical Inference in a Hyper-Relational Database
Logical Inference in a Hyper-Relational DatabaseLogical Inference in a Hyper-Relational Database
Logical Inference in a Hyper-Relational DatabaseVaticle
 
Harnessing Linked Knowledge Sources for Topic Classification in Social Media
Harnessing Linked Knowledge Sources for Topic Classification in Social MediaHarnessing Linked Knowledge Sources for Topic Classification in Social Media
Harnessing Linked Knowledge Sources for Topic Classification in Social MediaAmparo Elizabeth Cano Basave
 
Knowledge Graph Embeddings for Recommender Systems
Knowledge Graph Embeddings for Recommender SystemsKnowledge Graph Embeddings for Recommender Systems
Knowledge Graph Embeddings for Recommender SystemsEnrico Palumbo
 

What's hot (12)

An Empirical Comparison of Knowledge Graph Embeddings for Item Recommendation
An Empirical Comparison of Knowledge Graph Embeddings for Item RecommendationAn Empirical Comparison of Knowledge Graph Embeddings for Item Recommendation
An Empirical Comparison of Knowledge Graph Embeddings for Item Recommendation
 
NEEL2015 challenge summary
NEEL2015 challenge summaryNEEL2015 challenge summary
NEEL2015 challenge summary
 
Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...Schema-agnositc queries over large-schema databases: a distributional semanti...
Schema-agnositc queries over large-schema databases: a distributional semanti...
 
Strategies for Processing and Explaining Distributed Queries on Linked Data
Strategies for Processing and Explaining Distributed Queries on Linked DataStrategies for Processing and Explaining Distributed Queries on Linked Data
Strategies for Processing and Explaining Distributed Queries on Linked Data
 
EARL: Joint Entity and Relation Linking for Question Answering over Knowledge...
EARL: Joint Entity and Relation Linking for Question Answering over Knowledge...EARL: Joint Entity and Relation Linking for Question Answering over Knowledge...
EARL: Joint Entity and Relation Linking for Question Answering over Knowledge...
 
Linkanalysis handout
Linkanalysis handoutLinkanalysis handout
Linkanalysis handout
 
Linkset quality (LWDM 2013)
Linkset quality (LWDM 2013)Linkset quality (LWDM 2013)
Linkset quality (LWDM 2013)
 
Executing SPARQL Queries over Mapped Document Stores with SparqlMap-M
Executing SPARQL Queries over Mapped Document Stores with SparqlMap-MExecuting SPARQL Queries over Mapped Document Stores with SparqlMap-M
Executing SPARQL Queries over Mapped Document Stores with SparqlMap-M
 
Introduction to Named Entity Recognition
Introduction to Named Entity RecognitionIntroduction to Named Entity Recognition
Introduction to Named Entity Recognition
 
Logical Inference in a Hyper-Relational Database
Logical Inference in a Hyper-Relational DatabaseLogical Inference in a Hyper-Relational Database
Logical Inference in a Hyper-Relational Database
 
Harnessing Linked Knowledge Sources for Topic Classification in Social Media
Harnessing Linked Knowledge Sources for Topic Classification in Social MediaHarnessing Linked Knowledge Sources for Topic Classification in Social Media
Harnessing Linked Knowledge Sources for Topic Classification in Social Media
 
Knowledge Graph Embeddings for Recommender Systems
Knowledge Graph Embeddings for Recommender SystemsKnowledge Graph Embeddings for Recommender Systems
Knowledge Graph Embeddings for Recommender Systems
 

Viewers also liked

Exploiting Entity Linking in Queries For Entity Retrieval
Exploiting Entity Linking in Queries For Entity RetrievalExploiting Entity Linking in Queries For Entity Retrieval
Exploiting Entity Linking in Queries For Entity RetrievalFaegheh Hasibi
 
Julien Gonçalves: Named entity recognition and disambiguation using an iterat...
Julien Gonçalves: Named entity recognition and disambiguation using an iterat...Julien Gonçalves: Named entity recognition and disambiguation using an iterat...
Julien Gonçalves: Named entity recognition and disambiguation using an iterat...Semantic Web Company
 
Dynamically Optimizing Queries over Large Scale Data Platforms
Dynamically Optimizing Queries over Large Scale Data PlatformsDynamically Optimizing Queries over Large Scale Data Platforms
Dynamically Optimizing Queries over Large Scale Data PlatformsINRIA-OAK
 
Natural language procssing
Natural language procssing Natural language procssing
Natural language procssing Rajnish Raj
 
Being a PhD student: Experiences and Challenges
Being a PhD student: Experiences and ChallengesBeing a PhD student: Experiences and Challenges
Being a PhD student: Experiences and ChallengesFaegheh Hasibi
 
On building more human query answering systems
On building more human query answering systemsOn building more human query answering systems
On building more human query answering systemsINRIA-OAK
 
Entity linking with a knowledge base issues techniques and solutions
Entity linking with a knowledge base issues techniques and solutionsEntity linking with a knowledge base issues techniques and solutions
Entity linking with a knowledge base issues techniques and solutionsCloudTechnologies
 
Knowledge-based Systems
Knowledge-based SystemsKnowledge-based Systems
Knowledge-based Systemssaimohang
 
Surface Analysis
Surface AnalysisSurface Analysis
Surface Analysisluyenkimnet
 
Sparkly Notebook: Interactive Analysis and Visualization with Spark
Sparkly Notebook: Interactive Analysis and Visualization with SparkSparkly Notebook: Interactive Analysis and Visualization with Spark
Sparkly Notebook: Interactive Analysis and Visualization with Sparkfelixcss
 
Surface and Materials Analysis Techniques
Surface and Materials Analysis TechniquesSurface and Materials Analysis Techniques
Surface and Materials Analysis TechniquesRobert Cormia
 
Structural ambiguity
Structural ambiguityStructural ambiguity
Structural ambiguityAsif Ali Raza
 
Unit 11 Sense Relations (2)
Unit 11   Sense Relations (2)Unit 11   Sense Relations (2)
Unit 11 Sense Relations (2)Ashwag Al Hamid
 
Introspection method presentation
Introspection method presentationIntrospection method presentation
Introspection method presentationSaher Akhtar
 
Deep structure and surface structure
Deep structure and surface structureDeep structure and surface structure
Deep structure and surface structureAsif Ali Raza
 
Knowledge based systems
Knowledge based systemsKnowledge based systems
Knowledge based systemsYowan Rdotexe
 

Viewers also liked (20)

Exploiting Entity Linking in Queries For Entity Retrieval
Exploiting Entity Linking in Queries For Entity RetrievalExploiting Entity Linking in Queries For Entity Retrieval
Exploiting Entity Linking in Queries For Entity Retrieval
 
LR Parsing
LR ParsingLR Parsing
LR Parsing
 
Julien Gonçalves: Named entity recognition and disambiguation using an iterat...
Julien Gonçalves: Named entity recognition and disambiguation using an iterat...Julien Gonçalves: Named entity recognition and disambiguation using an iterat...
Julien Gonçalves: Named entity recognition and disambiguation using an iterat...
 
Discoverers of Surface Analysis
Discoverers of Surface AnalysisDiscoverers of Surface Analysis
Discoverers of Surface Analysis
 
Dynamically Optimizing Queries over Large Scale Data Platforms
Dynamically Optimizing Queries over Large Scale Data PlatformsDynamically Optimizing Queries over Large Scale Data Platforms
Dynamically Optimizing Queries over Large Scale Data Platforms
 
Natural language procssing
Natural language procssing Natural language procssing
Natural language procssing
 
Being a PhD student: Experiences and Challenges
Being a PhD student: Experiences and ChallengesBeing a PhD student: Experiences and Challenges
Being a PhD student: Experiences and Challenges
 
On building more human query answering systems
On building more human query answering systemsOn building more human query answering systems
On building more human query answering systems
 
Entity linking with a knowledge base issues techniques and solutions
Entity linking with a knowledge base issues techniques and solutionsEntity linking with a knowledge base issues techniques and solutions
Entity linking with a knowledge base issues techniques and solutions
 
Knowledge-based Systems
Knowledge-based SystemsKnowledge-based Systems
Knowledge-based Systems
 
Surface Analysis
Surface AnalysisSurface Analysis
Surface Analysis
 
AMBIGUITY IN A LANGUAGE
AMBIGUITY IN A LANGUAGEAMBIGUITY IN A LANGUAGE
AMBIGUITY IN A LANGUAGE
 
Sparkly Notebook: Interactive Analysis and Visualization with Spark
Sparkly Notebook: Interactive Analysis and Visualization with SparkSparkly Notebook: Interactive Analysis and Visualization with Spark
Sparkly Notebook: Interactive Analysis and Visualization with Spark
 
Surface and Materials Analysis Techniques
Surface and Materials Analysis TechniquesSurface and Materials Analysis Techniques
Surface and Materials Analysis Techniques
 
Structural ambiguity
Structural ambiguityStructural ambiguity
Structural ambiguity
 
Unit 11 Sense Relations (2)
Unit 11   Sense Relations (2)Unit 11   Sense Relations (2)
Unit 11 Sense Relations (2)
 
Semantics
SemanticsSemantics
Semantics
 
Introspection method presentation
Introspection method presentationIntrospection method presentation
Introspection method presentation
 
Deep structure and surface structure
Deep structure and surface structureDeep structure and surface structure
Deep structure and surface structure
 
Knowledge based systems
Knowledge based systemsKnowledge based systems
Knowledge based systems
 

Similar to On the Reproducibility of the TAGME entity linking system

Context Semantic Analysis: a knowledge-based technique for computing inter-do...
Context Semantic Analysis: a knowledge-based technique for computing inter-do...Context Semantic Analysis: a knowledge-based technique for computing inter-do...
Context Semantic Analysis: a knowledge-based technique for computing inter-do...Fabio Benedetti
 
An evaluation of SimRank and Personalized PageRank to build a recommender sys...
An evaluation of SimRank and Personalized PageRank to build a recommender sys...An evaluation of SimRank and Personalized PageRank to build a recommender sys...
An evaluation of SimRank and Personalized PageRank to build a recommender sys...Paolo Tomeo
 
Link Discovery Tutorial Part III: Benchmarking for Instance Matching Systems
Link Discovery Tutorial Part III: Benchmarking for Instance Matching SystemsLink Discovery Tutorial Part III: Benchmarking for Instance Matching Systems
Link Discovery Tutorial Part III: Benchmarking for Instance Matching SystemsHolistic Benchmarking of Big Linked Data
 
Master defence 2020 - Kateryna Liubonko - Matching Red Links to Wikidata Items
 Master defence 2020 - Kateryna Liubonko - Matching Red Links to Wikidata Items Master defence 2020 - Kateryna Liubonko - Matching Red Links to Wikidata Items
Master defence 2020 - Kateryna Liubonko - Matching Red Links to Wikidata ItemsLviv Data Science Summer School
 
Automatic Detection of Web Trackers by Vasia Kalavri
Automatic Detection of Web Trackers by Vasia KalavriAutomatic Detection of Web Trackers by Vasia Kalavri
Automatic Detection of Web Trackers by Vasia KalavriFlink Forward
 
Evaluation Initiatives for Entity-oriented Search
Evaluation Initiatives for Entity-oriented SearchEvaluation Initiatives for Entity-oriented Search
Evaluation Initiatives for Entity-oriented Searchkrisztianbalog
 
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 Webhala Skaf
 
Link Reuse and Evolution for Data Integration (LSWT 2020)
Link Reuse and Evolution for Data Integration (LSWT 2020)Link Reuse and Evolution for Data Integration (LSWT 2020)
Link Reuse and Evolution for Data Integration (LSWT 2020)Anika Groß
 
8th TUC Meeting – George Fletcher (TU Eindhoven), gMark: Schema-driven data a...
8th TUC Meeting – George Fletcher (TU Eindhoven), gMark: Schema-driven data a...8th TUC Meeting – George Fletcher (TU Eindhoven), gMark: Schema-driven data a...
8th TUC Meeting – George Fletcher (TU Eindhoven), gMark: Schema-driven data a...LDBC council
 
Exploiting large-scale graph analytics for unsupervised Entity Linking
Exploiting large-scale graph analytics for unsupervised Entity LinkingExploiting large-scale graph analytics for unsupervised Entity Linking
Exploiting large-scale graph analytics for unsupervised Entity LinkingNECST Lab @ Politecnico di Milano
 
Detecting Incongruity Between News Headline and Body Text via a Deep Hierarch...
Detecting Incongruity Between News Headline and Body Text via a Deep Hierarch...Detecting Incongruity Between News Headline and Body Text via a Deep Hierarch...
Detecting Incongruity Between News Headline and Body Text via a Deep Hierarch...Seoul National University
 
Graph processing at scale using spark & graph frames
Graph processing at scale using spark & graph framesGraph processing at scale using spark & graph frames
Graph processing at scale using spark & graph framesRon Barabash
 
Incentives for infrastructure modernization
Incentives for infrastructure modernizationIncentives for infrastructure modernization
Incentives for infrastructure modernizationBjörn Brembs
 
Automated Content Analysis of Discussion Transcripts
Automated Content Analysis of Discussion TranscriptsAutomated Content Analysis of Discussion Transcripts
Automated Content Analysis of Discussion TranscriptsVitomir Kovanovic
 
Stream Reasoning: Where we got so far. Oxford 2010.1.18
Stream Reasoning: Where we got so far. Oxford 2010.1.18Stream Reasoning: Where we got so far. Oxford 2010.1.18
Stream Reasoning: Where we got so far. Oxford 2010.1.18Emanuele Della Valle
 

Similar to On the Reproducibility of the TAGME entity linking system (20)

Context Semantic Analysis: a knowledge-based technique for computing inter-do...
Context Semantic Analysis: a knowledge-based technique for computing inter-do...Context Semantic Analysis: a knowledge-based technique for computing inter-do...
Context Semantic Analysis: a knowledge-based technique for computing inter-do...
 
An evaluation of SimRank and Personalized PageRank to build a recommender sys...
An evaluation of SimRank and Personalized PageRank to build a recommender sys...An evaluation of SimRank and Personalized PageRank to build a recommender sys...
An evaluation of SimRank and Personalized PageRank to build a recommender sys...
 
Link Discovery Tutorial Part III: Benchmarking for Instance Matching Systems
Link Discovery Tutorial Part III: Benchmarking for Instance Matching SystemsLink Discovery Tutorial Part III: Benchmarking for Instance Matching Systems
Link Discovery Tutorial Part III: Benchmarking for Instance Matching Systems
 
Master defence 2020 - Kateryna Liubonko - Matching Red Links to Wikidata Items
 Master defence 2020 - Kateryna Liubonko - Matching Red Links to Wikidata Items Master defence 2020 - Kateryna Liubonko - Matching Red Links to Wikidata Items
Master defence 2020 - Kateryna Liubonko - Matching Red Links to Wikidata Items
 
Web mining
Web miningWeb mining
Web mining
 
Automatic Detection of Web Trackers by Vasia Kalavri
Automatic Detection of Web Trackers by Vasia KalavriAutomatic Detection of Web Trackers by Vasia Kalavri
Automatic Detection of Web Trackers by Vasia Kalavri
 
Sybrandt Thesis Proposal Presentation
Sybrandt Thesis Proposal PresentationSybrandt Thesis Proposal Presentation
Sybrandt Thesis Proposal Presentation
 
Evaluation Initiatives for Entity-oriented Search
Evaluation Initiatives for Entity-oriented SearchEvaluation Initiatives for Entity-oriented Search
Evaluation Initiatives for Entity-oriented Search
 
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
 
Link Reuse and Evolution for Data Integration (LSWT 2020)
Link Reuse and Evolution for Data Integration (LSWT 2020)Link Reuse and Evolution for Data Integration (LSWT 2020)
Link Reuse and Evolution for Data Integration (LSWT 2020)
 
Recommender Systems and Linked Open Data
Recommender Systems and Linked Open DataRecommender Systems and Linked Open Data
Recommender Systems and Linked Open Data
 
8th TUC Meeting – George Fletcher (TU Eindhoven), gMark: Schema-driven data a...
8th TUC Meeting – George Fletcher (TU Eindhoven), gMark: Schema-driven data a...8th TUC Meeting – George Fletcher (TU Eindhoven), gMark: Schema-driven data a...
8th TUC Meeting – George Fletcher (TU Eindhoven), gMark: Schema-driven data a...
 
Exploiting large-scale graph analytics for unsupervised Entity Linking
Exploiting large-scale graph analytics for unsupervised Entity LinkingExploiting large-scale graph analytics for unsupervised Entity Linking
Exploiting large-scale graph analytics for unsupervised Entity Linking
 
Detecting Incongruity Between News Headline and Body Text via a Deep Hierarch...
Detecting Incongruity Between News Headline and Body Text via a Deep Hierarch...Detecting Incongruity Between News Headline and Body Text via a Deep Hierarch...
Detecting Incongruity Between News Headline and Body Text via a Deep Hierarch...
 
Graph processing at scale using spark & graph frames
Graph processing at scale using spark & graph framesGraph processing at scale using spark & graph frames
Graph processing at scale using spark & graph frames
 
Incentives for infrastructure modernization
Incentives for infrastructure modernizationIncentives for infrastructure modernization
Incentives for infrastructure modernization
 
OpenML Tutorial ECMLPKDD 2015
OpenML Tutorial ECMLPKDD 2015OpenML Tutorial ECMLPKDD 2015
OpenML Tutorial ECMLPKDD 2015
 
Content-based link prediction
Content-based link predictionContent-based link prediction
Content-based link prediction
 
Automated Content Analysis of Discussion Transcripts
Automated Content Analysis of Discussion TranscriptsAutomated Content Analysis of Discussion Transcripts
Automated Content Analysis of Discussion Transcripts
 
Stream Reasoning: Where we got so far. Oxford 2010.1.18
Stream Reasoning: Where we got so far. Oxford 2010.1.18Stream Reasoning: Where we got so far. Oxford 2010.1.18
Stream Reasoning: Where we got so far. Oxford 2010.1.18
 

Recently uploaded

Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksSérgio Sacani
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxAleenaTreesaSaji
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...anilsa9823
 
Orientation, design and principles of polyhouse
Orientation, design and principles of polyhouseOrientation, design and principles of polyhouse
Orientation, design and principles of polyhousejana861314
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxUmerFayaz5
 
Analytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptxAnalytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptxSwapnil Therkar
 
Artificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C PArtificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C PPRINCE C P
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bSérgio Sacani
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRDelhi Call girls
 
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisDiwakar Mishra
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Lokesh Kothari
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Nistarini College, Purulia (W.B) India
 
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCEPRINCE C P
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡anilsa9823
 
Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​kaibalyasahoo82800
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...Sérgio Sacani
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
Boyles law module in the grade 10 science
Boyles law module in the grade 10 scienceBoyles law module in the grade 10 science
Boyles law module in the grade 10 sciencefloriejanemacaya1
 

Recently uploaded (20)

Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptx
 
Engler and Prantl system of classification in plant taxonomy
Engler and Prantl system of classification in plant taxonomyEngler and Prantl system of classification in plant taxonomy
Engler and Prantl system of classification in plant taxonomy
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
 
Orientation, design and principles of polyhouse
Orientation, design and principles of polyhouseOrientation, design and principles of polyhouse
Orientation, design and principles of polyhouse
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptx
 
Analytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptxAnalytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptx
 
Artificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C PArtificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C P
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
 
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...
 
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
 
Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​
 
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
Boyles law module in the grade 10 science
Boyles law module in the grade 10 scienceBoyles law module in the grade 10 science
Boyles law module in the grade 10 science
 

On the Reproducibility of the TAGME entity linking system

  • 1. On the Reproducibility of the TAGME Entity Linking System Faegheh Hasibi, Krisztian Balog, Svein Erik Bratsberg ECIR conference, March 2016
  • 2. England national football team 1966 FIFA World Cup Argentina national football team Entity linking British expatriates brought football to Argentina in the 19th century. 
 The rivalry between the England and Argentina national football teams, however, is generally traced back to the 
 1966 FIFA World Cup.
  • 4. TAGME • Cited: ‣ >50 times based on ACM DL ‣ > 200 based on Google scholar • One of the must-have baselines • Delivers competitive results ‣ 1st and 2nd ranked systems of the ERD challenge used TAGME - P. Ferragina and U. Scaiella. TAGME: On-the-fly annotation of short text fragments (by Wikipedia entities). In Proc. of CIKM ’10, pages 1625–1628, 2010. - P. Ferragina and U. Scaiella. Fast and accurate annotation of short texts with Wikipedia pages. CoRR, abs/1006.3498, 2010.
  • 5. Offers invaluable sources for reproducibility: • Test collections • Source code • RESTful API • GUI demo TAGME
  • 6. In this talk … ✓ Repeatability ✓ Reproducibility ✓ Generalizability J. Arguello, F. Diaz, J. Lin, and A. Trotman. SIGIR 2015 Workshop on Reproducibility, Inexplicability, and Generalizability of Results (RIGOR). In Proc. of SIGIR '15, pages1147-1148.
  • 7. In this talk … ✓ Repeatability ✓ Reproducibility ✓ Generalizability “Repeating a previous result under the original conditions (e.g., same dataset and system configuration).” “Reproducing a previous result under different, but comparable conditions (e.g., different, but comparable dataset).” “Applying an existing, empirically validated technique to a different IR task/domain than the original.” J. Arguello, F. Diaz, J. Lin, and A. Trotman. SIGIR 2015 Workshop on Reproducibility, Inexplicability, and Generalizability of Results (RIGOR). In Proc. of SIGIR '15, pages1147-1148.
  • 8. Question • Does the code actually implement what is described in the paper? • We need to (re)implement the entity linking method • Integrating in a larger framework • Making a (fair) comparison between different entity linking approaches What is the point of reproducibility experiments when the source code is made available?
  • 9. Our goal is … • Learn about reproducibility • Verification • Criticism
  • 10. Agenda • Overview of TAGME • Repeatability • Reproducibility • Generalizability • Lessons to be learned
  • 11. Agenda • Overview of TAGME • Repeatability • Reproducibility • Generalizability • Lessons to be learned
  • 12. Approach British expatriates brought football to Argentina in the 19th century. The rivalry between the England and Argentina national … - England - England National Football Team - England Cricket Team … British: United Kingdom expatriates: Expatriate century: Century (song) England: England … British: United Kingdom expatriates: Expatriate century: Century (song) England: England … Parsing Disambiguation PruningText Annotated text
  • 13. Test collections • Wiki-Disamb30 ‣ For evaluating disambiguation phase ‣ Each snippet is linked to single entity • Wiki-Annot30 ‣ For evaluating end-to-end performance ‣ All entity mentions are annotated
 ☞ Number of snippets deviate from what is reported in the paper #Snippets Original Paper Wiki-Disamb30 2M 1.4M Wiki-Annot30 185K 180K
  • 14. Repeatability Repeating previous results under the original conditions
  • 15. Repeatability challenges • Unavailability of Wikipedia dump Nov. 2009 ‣ Could not be provided by the TAGME authors • Unavailability of training and test set splits • Discrepancies between the number of snippets
  • 16. Repeatability ‣ Weka could load 1.4M snippets of Wiki-Disamb30 ‣ Whole Wiki-Annot30 is used; difference is a matter of approximation TAGME results are not repeatable due to unavailability of data Post-acceptance responses:
  • 17. Reproducibility Reproducing results under different, but comparable conditions
  • 18. Reproducibility TAGME paper results are compared with: • TAGME API (similar to running the source code) • implementation of TAGME • Our implementation D. Ceccarelli, C. Lucchese, S. Orlando, R. Perego, and S. Trani. Dexter: An open source framework for entity linking. In Proc. of the Sixth International Workshop on Exploiting Semantic Annotations in Information Retrieval, pages 17–20, 2013.
  • 19. Implementation • Implementation is based on the paper • Whenever in doubt: checking the source code • The closet available Wikipedia dump: April 2010
  • 20. Implementation Link probability: Number of times mention m appears as a link Number of times mention m occurs in Wikipedia (as a link or not)
  • 21. Implementation Link probability: ‣ Due to efficiency reasons TAGME makes estimations Number of articles containing the mention m ➝
  • 22. Implementation Link probability: ‣ Due to efficiency reasons TAGME makes estimations Number of articles containing the mention m ➝ Number of articles mention m is linked to an entity (Wikipedia creates link for the first occurrence of an entity) ≈
  • 23. Implementation Link probability: ‣ Due to efficiency reasons TAGME makes estimations ‣ In fact, TAGME implements Keyphraseness:
  • 26. Implementation Relatedness: • Defined as:• Implemented as: Pruning based on commonness: • TAGME performs and extra pruning in the parsing step • We followed TAGME, as it makes the system considerably faster
  • 27. Table 1 Results to be reproduced: Approach: • Submit Wiki-Disamb30 snippets to the TAGME API • Set the pruning threshold to 0
  • 28. Table 1-Evaluation metrics Several questions are left unanswered: • Are the metrics micro- or macro-averaged? • What are the matching criteria for the mentions? ‣ E.g. “New York City” = “New York” ?
  • 29. Table 1-Evaluation metrics We computed the upper bound: • If any of the entities matches the ground truth: ‣ Precision =1 Recall = 1 • Otherwise: ‣ Precision =0 Recall = 0 Other interpretation of precision or recall would result in a lower number.
  • 30. Table 1- Results Given the magnitude of the differences, even against their own API, we did not get the results for our implementation. Reproducing of the disambiguation phase:
  • 31. Table 1- Results Our initial guess: • Discrepancy between the number of snippets made differences Post-acceptance responses: ‣ TAGME performs extra (undocumented) filtering before pruning ‣ Computation of evaluation metrics are explained
  • 32. Table 2 Results to be reproduced:
  • 33. Table 2- Results TAGME results are reproducible through its own API.
  • 34. Table 2- Results Post-acceptance responses: ‣ TAGME uses wiki page-to-page link records, while our (and Dexter’s) implementation extracts links from the body of the pages. ‣ TAGME API and Source code corresponds to a newer version (v.2) ‣ Several optimizations has been performed in v.2 ‣ The evaluation metrics are micro-averaged
  • 35. Generalizability Applying an existing technique to a different IR task/domain
  • 36. Entity Linking in Queries (ELQ) Entity linking Entity linking in queries “new york pizza manhattan” {New York City, Manhattan} {New York City, Manhattan} {New York-style Pizza, Manhattan} “cambridge population” {Cambridge} {Cambridge} {Cambridge, Massachusetts} - F. Hasibi, K. Balog, and S. E. Bratsberg. Entity Linking in Queries: Tasks and Evaluation. In Proc. of the ICTIR ’15, pages 171–180, 2015. - D. Carmel, M.-W. Chang, E. Gabrilovich,B.-J.P. Hsu, and K. Wang. ERD’14: Entity recognition and disambiguation challenge. SIGIR Forum, 48(2):63–77, 2014.
  • 37. Why ELQ? TAGME has great potential to be used for ELQ ✓ Designed to operate with short texts ✓ On-fly-annotation
  • 38. Generalizability TAGME results are generalizable to the task of entity linking in queries. TAGME API > Dexter > TAGME-wp12 > TAGME-wp10
  • 40. Lessons learned 1/2 • All technical details that affect performance should be mentioned in the paper • Differences between the published approach and publicly API/code should be made explicit
  • 41. Lessons learned 2/2 • Evaluation metrics should be explained in detail • Keep all data sources used in a published paper Maintain an “online appendix” to a publication • Extra details can be explained there • Can be easily edited and extended
  • 42. Thanks! Questions? Check our online appendix http://bit.ly/tagme-rep