SlideShare a Scribd company logo
1 of 25
UAIC Participation at RTE5 Adrian Iftene Mihai Alex Moruz {adiftene,mmoruz}@info.uaic.ro TAC 2009, NIST „ Al. I. Cuza“ University, Iasi, Romania Faculty of Computer Science
Overview ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
RTE Competition ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
System presentation Iftene, Moruz –  TAC , 200 9 600 pairs (T, H) DIRT Minipar module Dependency trees for  (T, H) pairs LingPipe module Named entities for  (T, H) pairs Final result Acronyms Background knowledge Wordnet ,[object Object],Wikipedia VerbOcean TreeTagger Numbers &Dates NE rule Fitness rule Contradiction rule Negation rule Numb GATE ,[object Object],Preparation Jobs & Languages Google API ,[object Object]
Preparation and New Modules ,[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Example Iftene, Moruz –  TAC , 200 9 NE (N) subj loc adv (A) subj mod … … NE (N) loc … … DIRT, VerbOcean WordNet Acronyms, BK DIRT: solve=resolve 0.31453 DIRT: convict=arrest 0.28895 DIRT:  convict=acquit  0.302455,OPPOSITE VerbOcean:  increase<>decrease,  VerbOcean:   leave<>stay WordNet: trouble=problem WordNet: talk=discussion   Acronym: EU=European Union BK: Buenos Aires [in] Argentine BK: 16 [is] sixteen   Hypothesis Text verb H  (V) noun (N) verb T  (V) noun (N) … … … …
Rules ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Entailment cases ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Entailment cases (cont.) ,[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Entailment cases for numbers ,[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Contradiction cases ,[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Contradiction cases (cont.) ,[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Unknown cases ,[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Unknown cases  (cont.) ,[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Unknown cases (cont…) ,[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Results in RTE5 Iftene, Moruz –  TAC , 200 9 Answer Type In Gold Correct offered by our system Total offered by our system Precision Recall F-measure Entailment 300 260 379 68.60% 86.67% 76.58% Contradiction 90 22 44 50.00% 24.44% 32.84% Unknown 210 128 177 72.32% 60.95% 66.15% Total 600 410 600 68.33% Answer Type In Gold Correct offered by our system Total offered by our system Precision Recall F-measure Yes 300 260 379 68.60% 86.67% 76.58% No 300 181 221 81.90% 60.33% 69.48% Total 600 441 600 73.50%
Ablation tests Iftene, Moruz –  TAC , 200 9 System description RTE-3 (69.13 %) RTE-4 (72.1 %) RTE-5 (73.5 %) P C WR P C WR P C WR Without DIRT 68.76 0.37 0.54 71.40 0.7 0.97 73.33 0.17 0.23 Without WordNet 68.00 1.13 1.63 69.10 3.0 4.16 72.5 1.00 1.36 Without Acronyms 68.38 0.75 1.08 71.80 0.3 0.42 73.33 0.17 0.23 Without BK 67.75 1.38 2.00 70.40 1.7 2.36 72.33 1.17 1.59 Without the NE rule 57.58 11.55 16.71 66.90 5.2 7.21 67.33 6.17 8.39 Without the Negation rule 67.63 1.50 2.17 68.70 3.4 4.72 73.5 0.00 0.00 Without the Contradiction rule - - - 68.10 4.0 5.55 71.5 2.00 2.72 No additional processing steps - - - - - - 69.33 4.17 5.67 Total 16.68 24.13 18.3 25.39 14.85 20.20
Pilot task ,[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Pilot task (cont.) ,[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Pilot task (cont.) ,[object Object],Iftene, Moruz –  TAC , 200 9 Result Precision Recall F-measure Micro-average 51.12% 22.88% 31.61% Macro-average Topic 53.03% 24.08% 33.12% Macro-average Hypothesis 46.55% 26.42% 33.71%
Conclusions Iftene, Moruz –  TAC , 200 9 ,[object Object],[object Object],[object Object],[object Object]
Further work ,[object Object],[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Further work (cont.) ,[object Object],[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
Acknowledgments ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Iftene, Moruz –  TAC , 200 9
[object Object],Iftene, Moruz –  TAC , 200 9

More Related Content

Similar to Tac2009 rte5

A Distributed Architecture System for Recognizing Textual Entailment
A Distributed Architecture System for Recognizing Textual EntailmentA Distributed Architecture System for Recognizing Textual Entailment
A Distributed Architecture System for Recognizing Textual Entailment
Faculty of Computer Science
 
AlfordChapter4.ppt
AlfordChapter4.pptAlfordChapter4.ppt
AlfordChapter4.ppt
EidTahir
 
A NEW STEMMER TO IMPROVE INFORMATION RETRIEVAL
A NEW STEMMER TO IMPROVE INFORMATION RETRIEVALA NEW STEMMER TO IMPROVE INFORMATION RETRIEVAL
A NEW STEMMER TO IMPROVE INFORMATION RETRIEVAL
IJNSA Journal
 
Jarrar.lecture notes.aai.2011s.ch8.fol.introduction
Jarrar.lecture notes.aai.2011s.ch8.fol.introductionJarrar.lecture notes.aai.2011s.ch8.fol.introduction
Jarrar.lecture notes.aai.2011s.ch8.fol.introduction
PalGov
 
MACHINE LEARNING-LEARNING RULE
MACHINE LEARNING-LEARNING RULEMACHINE LEARNING-LEARNING RULE
MACHINE LEARNING-LEARNING RULE
DrBindhuM
 
santosh kumar fuzzy logic presentation
santosh kumar   fuzzy logic presentationsantosh kumar   fuzzy logic presentation
santosh kumar fuzzy logic presentation
Akash Maurya
 
VonNeumannAlgebraPresentation
VonNeumannAlgebraPresentationVonNeumannAlgebraPresentation
VonNeumannAlgebraPresentation
Matthew Geleta
 

Similar to Tac2009 rte5 (20)

UAIC Participation at RTE4
UAIC Participation at RTE4UAIC Participation at RTE4
UAIC Participation at RTE4
 
A Distributed Architecture System for Recognizing Textual Entailment
A Distributed Architecture System for Recognizing Textual EntailmentA Distributed Architecture System for Recognizing Textual Entailment
A Distributed Architecture System for Recognizing Textual Entailment
 
Seminar@KRDB 2011 - Montali - Runtime Reasoning with the Event Calculus: from...
Seminar@KRDB 2011 - Montali - Runtime Reasoning with the Event Calculus: from...Seminar@KRDB 2011 - Montali - Runtime Reasoning with the Event Calculus: from...
Seminar@KRDB 2011 - Montali - Runtime Reasoning with the Event Calculus: from...
 
Optimization of probabilistic argumentation with Markov processes
Optimization of probabilistic argumentation with Markov processesOptimization of probabilistic argumentation with Markov processes
Optimization of probabilistic argumentation with Markov processes
 
Hardness of approximation
Hardness of approximationHardness of approximation
Hardness of approximation
 
22 ijcse-01208
22 ijcse-0120822 ijcse-01208
22 ijcse-01208
 
Genetic Algorithms.ppt
Genetic Algorithms.pptGenetic Algorithms.ppt
Genetic Algorithms.ppt
 
Introduction to Machine Learning and Deep Learning
Introduction to Machine Learning and Deep LearningIntroduction to Machine Learning and Deep Learning
Introduction to Machine Learning and Deep Learning
 
Presentation
PresentationPresentation
Presentation
 
Nlp
NlpNlp
Nlp
 
Natural Language Processing
Natural Language ProcessingNatural Language Processing
Natural Language Processing
 
AlfordChapter4.ppt
AlfordChapter4.pptAlfordChapter4.ppt
AlfordChapter4.ppt
 
A NEW STEMMER TO IMPROVE INFORMATION RETRIEVAL
A NEW STEMMER TO IMPROVE INFORMATION RETRIEVALA NEW STEMMER TO IMPROVE INFORMATION RETRIEVAL
A NEW STEMMER TO IMPROVE INFORMATION RETRIEVAL
 
A NEW STEMMER TO IMPROVE INFORMATION RETRIEVAL
A NEW STEMMER TO IMPROVE INFORMATION RETRIEVALA NEW STEMMER TO IMPROVE INFORMATION RETRIEVAL
A NEW STEMMER TO IMPROVE INFORMATION RETRIEVAL
 
Jarrar.lecture notes.aai.2011s.ch8.fol.introduction
Jarrar.lecture notes.aai.2011s.ch8.fol.introductionJarrar.lecture notes.aai.2011s.ch8.fol.introduction
Jarrar.lecture notes.aai.2011s.ch8.fol.introduction
 
MACHINE LEARNING-LEARNING RULE
MACHINE LEARNING-LEARNING RULEMACHINE LEARNING-LEARNING RULE
MACHINE LEARNING-LEARNING RULE
 
santosh kumar fuzzy logic presentation
santosh kumar   fuzzy logic presentationsantosh kumar   fuzzy logic presentation
santosh kumar fuzzy logic presentation
 
defense
defensedefense
defense
 
VonNeumannAlgebraPresentation
VonNeumannAlgebraPresentationVonNeumannAlgebraPresentation
VonNeumannAlgebraPresentation
 
Higher Order Fused Regularization for Supervised Learning with Grouped Parame...
Higher Order Fused Regularization for Supervised Learning with Grouped Parame...Higher Order Fused Regularization for Supervised Learning with Grouped Parame...
Higher Order Fused Regularization for Supervised Learning with Grouped Parame...
 

Tac2009 rte5

  • 1. UAIC Participation at RTE5 Adrian Iftene Mihai Alex Moruz {adiftene,mmoruz}@info.uaic.ro TAC 2009, NIST „ Al. I. Cuza“ University, Iasi, Romania Faculty of Computer Science
  • 2.
  • 3.
  • 4.
  • 5.
  • 6. Example Iftene, Moruz – TAC , 200 9 NE (N) subj loc adv (A) subj mod … … NE (N) loc … … DIRT, VerbOcean WordNet Acronyms, BK DIRT: solve=resolve 0.31453 DIRT: convict=arrest 0.28895 DIRT: convict=acquit 0.302455,OPPOSITE VerbOcean: increase<>decrease, VerbOcean: leave<>stay WordNet: trouble=problem WordNet: talk=discussion Acronym: EU=European Union BK: Buenos Aires [in] Argentine BK: 16 [is] sixteen Hypothesis Text verb H (V) noun (N) verb T (V) noun (N) … … … …
  • 7.
  • 8.
  • 9.
  • 10.
  • 11.
  • 12.
  • 13.
  • 14.
  • 15.
  • 16. Results in RTE5 Iftene, Moruz – TAC , 200 9 Answer Type In Gold Correct offered by our system Total offered by our system Precision Recall F-measure Entailment 300 260 379 68.60% 86.67% 76.58% Contradiction 90 22 44 50.00% 24.44% 32.84% Unknown 210 128 177 72.32% 60.95% 66.15% Total 600 410 600 68.33% Answer Type In Gold Correct offered by our system Total offered by our system Precision Recall F-measure Yes 300 260 379 68.60% 86.67% 76.58% No 300 181 221 81.90% 60.33% 69.48% Total 600 441 600 73.50%
  • 17. Ablation tests Iftene, Moruz – TAC , 200 9 System description RTE-3 (69.13 %) RTE-4 (72.1 %) RTE-5 (73.5 %) P C WR P C WR P C WR Without DIRT 68.76 0.37 0.54 71.40 0.7 0.97 73.33 0.17 0.23 Without WordNet 68.00 1.13 1.63 69.10 3.0 4.16 72.5 1.00 1.36 Without Acronyms 68.38 0.75 1.08 71.80 0.3 0.42 73.33 0.17 0.23 Without BK 67.75 1.38 2.00 70.40 1.7 2.36 72.33 1.17 1.59 Without the NE rule 57.58 11.55 16.71 66.90 5.2 7.21 67.33 6.17 8.39 Without the Negation rule 67.63 1.50 2.17 68.70 3.4 4.72 73.5 0.00 0.00 Without the Contradiction rule - - - 68.10 4.0 5.55 71.5 2.00 2.72 No additional processing steps - - - - - - 69.33 4.17 5.67 Total 16.68 24.13 18.3 25.39 14.85 20.20
  • 18.
  • 19.
  • 20.
  • 21.
  • 22.
  • 23.
  • 24.
  • 25.