DynaLearn: Problem-based learning supported by semantic techniques

1,111 views

Published on

Presentation of the

Published in: Education
0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
1,111
On SlideShare
0
From Embeds
0
Number of Embeds
8
Actions
Shares
0
Downloads
11
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide

DynaLearn: Problem-based learning supported by semantic techniques

  1. 1. Problem-based learning supported by semantic techniques Esther Lozano, Jorge Gracia, Oscar Corcho Ontology Engineering Group, Universidad Politécnica de Madrid. Spain {elozano,jgracia,ocorcho}@fi.upm.es
  2. 2. Outline1. Introduction2. System overview3. Semantic grounding4. Semantic-based feedback5. Conclusions and Future Work 2
  3. 3. Introduction“Engaging and informed tools for learning conceptual system knowledge” 3
  4. 4. IntroductionQualitative Reasoning • Tries to capture human interpretation of reality • Physical systems represented in models • System behaviour studied by simulation • Focused on qualitative variables rather than on numerical ones (eg., certain tree has a “big” size, certain species population “grows”, etc.) 4
  5. 5. IntroductionApplication: Learning of Environmental Sciences• Core idea: “Learning by modelling”• Learning tools: • Definition of a suitable terminology • Interaction with the model • Prediction of its behaviour• Application examples: • “Study the evolution of a species population when another species is introduced in the same ecosystem” • “Study the effect of contaminant agents in a river” • .... 5
  6. 6. IntroductionDynaLearn• “System for knowledge acquisition of conceptual knowledge in the context of environmental science”. It combines: • Model construction representing a system • Semantic techniques to put such models in relationship • Use of virtual characters to interact with the system 6
  7. 7. IntroductionDynaLearn 7
  8. 8. QR ModellingEntities 8
  9. 9. QR ModellingModel fragmentsEntity: model fragment:Imported Reuse structure of the The within a model system Influence: Natality determines δSizeQuantity: The dynamic aspects of the systemProportionality: δSize determines δNatality 9
  10. 10. QR ModellingRunning simulations 10
  11. 11. QR ModellingSimulations Results• Based on a scenario, model fragments and model ingredient definitions State Graph Dependencies View of State 1 Value History 11
  12. 12. Semantic TechniquesSemantic Techniques • To bridge the gap between the loosely and imprecise terminology used by a learner and the well-defined semantics of an ontology • To put in relation to the QR models created by other learners or experts in order to automate the acquisition of feedback and recommendations from others 12
  13. 13. Outline1. Introduction2. System overview3. Semantic grounding4. Semantic-based feedback5. Conclusions and Future Work 13
  14. 14. System overview Online semantic Semantic repository resourcesLearner Grounding of Grounded Recommendation Reference Model learner model Learner Model of relevant models Model ? Generation of List of suggestions semantic feedbackLearner 14
  15. 15. Outline1. Introduction2. System overview3. Semantic grounding4. Semantic-based feedback5. Conclusions and Future Work 15
  16. 16. Semantic GroundingExpert/teacher Learner Anchor ontology http://www.anchorTerm.owl#NumberOf http://dbpedia.org/resource/Population http://dbpedia.org/resource/Mortality_rate grounding Semantic repository 16
  17. 17. Semantic GroundingBenefits of grounding • Support the process of learning a domain vocabulary • Ensure lexical and semantic correctness of terms • Ensure the interoperability among models • Extraction of a common domain knowledge • Detection of inconsistencies and contradictions between models • Inference of new, non declared, knowledge • Assist the model construction with feedback and recommendations 17
  18. 18. Semantic Grounding18
  19. 19. Outline1. Introduction2. System overview3. Semantic grounding4. Semantic-based feedback5. Conclusions and Future Work 19
  20. 20. Semantic-based feedbackLearner Model Grounding-based Preliminary Ontology alignment mappings matchingReference Model List of QR structures equivalences Discrepancies List of Taxonomy Generation of suggestions Inconsistencies semantic feedback Terminology Discrepancies
  21. 21. Grounding-based alignment http://dbpedia.org/resource/Mortality_rateExpert model Student model grounding Semantic repository Preliminary mapping: Death_rate ≡ Death
  22. 22. Grounding-Based Alignment• In the learner model:• In the reference model:• Resulting preliminary mapping: 22
  23. 23. Ontology Matching• Ontology matching tool: CIDER• Input of the ontology matching tool • Learner model with preliminary mappings • Reference model• Output: set of mappings (Alignment API format)Gracia, J. Integration and Disambiguation Techniqies for Semantic Heterogeneity Reduction on the Web. 2009 23
  24. 24. Terminology discrepanciesDiscrepancies between labels Learner model: Reference model: equivalent terms with different label 24
  25. 25. Terminology discrepancies Missing and extra ontological elements Reference model:Learner model: subclass of missing term extra term equivalent terms 25
  26. 26. Taxonomic discrepanciesInconsistency between hierarchies Learner model: Reference model: Disjoint classes INCONSISTENT equivalent terms HIERARCHIES! 26
  27. 27. QR structural discrepancies Algorithm: 1. Extraction of basic units 2. Integration of basic units of the same type 3. Comparison of equivalent integrated basic units 4. Matching of basic units of the same type 5. Comparison of equivalent basic unitsOEG Oct 2010 27
  28. 28. QR structural discrepancies Extraction of basic units External relationships Internal relationshipsOEG Oct 2010 28
  29. 29. QR structural discrepancies Algorithm: 1. Extraction of basic units 2. Integration of basic units of the same type 3. Comparison of equivalent integrated basic units 4. Matching of basic units of the same type 5. Comparison of equivalent basic unitsOEG Oct 2010 29
  30. 30. QR structural discrepancies Integration of basic units by typeOEG Oct 2010 30
  31. 31. QR structural discrepancies Algorithm: 1. Extraction of basic units 2. Integration of basic units of the same type 3. Comparison of equivalent integrated basic units 1. Missing instances in the learner model 2. Discrepancies in the internal relationships 4. Matching of basic units of the same type 5. Comparison of equivalent basic unitsOEG Oct 2010 31
  32. 32. QR structural discrepancies Missing instances in the learner modelReference model Learner model Missing quantity OEG Oct 2010 32
  33. 33. QR structural discrepancies Discrepancies between internal relationshipsReference model Learner model Different causal dependency OEG Oct 2010 33
  34. 34. QR structural discrepancies Algorithm: 1. Extraction of basic units 2. Integration of basic units of the same type 3. Comparison of equivalent integrated basic units 4. Matching of basic units • Filter by MF (matching of MF first) • Matching based on the external relations 5. Comparison of equivalent basic unitsOEG Oct 2010 34
  35. 35. QR structural discrepancies Matching of basic unitsReference model Learner model OEG Oct 2010 35
  36. 36. QR structural discrepancies Algorithm: 1. Extraction of basic units 2. Integration of basic units of the same type 3. Comparison of equivalent integrated basic units 4. Matching of basic units of the same type 5. Comparison of equivalent basic units 1. Missing entity instances 2. Discrepancies in external relationshipsOEG Oct 2010 36
  37. 37. QR structural discrepancies Missing entity instances Learner model Missing entity instancesReference modelOEG Oct 2010 37
  38. 38. QR structural discrepancies Discrepancies in the internal relationships Learner model Different causal dependenciesReference model OEG Oct 2010 38
  39. 39. Feedback from the pool of models Algorithm: 1. Get semantic-based feedback from each model 2. For each generated suggestion, calculate agreement among models 3. Filter information with agreement < minimum agreement 4. Communicate information to the learnerOEG Oct 2010 39
  40. 40. Feedback from the pool of models Example:Learner model OEG Oct 2010 40
  41. 41. Feedback from the pool of models Example: 67% 25% 75% 67%OEG Oct 2010 41
  42. 42. InterfaceOEG Oct 2010 42
  43. 43. Problem-based learning supported by semantic techniques Esther Lozano, Jorge Gracia, Oscar Corcho Ontology Engineering Group, Universidad Politécnica de Madrid. Spain {elozano,jgracia,ocorcho}@fi.upm.es

×