Facilitating Human Intervention in Coreference Resolution with Comparative Entity Summaries
•Télécharger en tant que PPTX, PDF•
0 j'aime•1,105 vues
The document presents a method for facilitating human intervention in coreference resolution by providing comparative entity summaries. It describes using properties and values of candidate coreferent entities to generate summaries that reflect their commonality and differences. The optimal summary maximizes commonality, difference, identity information and diversity, subject to a length limit. An evaluation involved human subjects verifying coreferent relationships for different summarization approaches. The comparative summary approach was found to improve verification efficiency without affecting accuracy as much as only showing common properties or entire descriptions.
Recommandé
Recommandé
Contenu connexe
Tendances
Tendances (20)
Similaire à Facilitating Human Intervention in Coreference Resolution with Comparative Entity Summaries
Similaire à Facilitating Human Intervention in Coreference Resolution with Comparative Entity Summaries (20)
Plus de Gong Cheng
Plus de Gong Cheng (20)
Dernier
Dernier (14)
Facilitating Human Intervention in Coreference Resolution with Comparative Entity Summaries
- 1. Facilitating Human Intervention in Coreference Resolution with Comparative Entity Summaries Danyun Xu, Gong Cheng, Yuzhong Qu Nanjing University, China Presented at ESWC 2014, Crete, Greece
- 2. Coreference resolution TimBL givenName: “Tim” surname: “Berners-Lee” altName: “Tim BL” type: Scientist gender: “male” isDirectorOf: W3C TBL name: “Tim Berners-Lee” type: ComputerScientist type: RoyalSocietyFellow sex: “Male” invented: WWW founded: WSRI Wendy fullName: “Wendy Hall” type: ComputerScientist type: RoyalSocietyFellow sex: “Female” birthplace: London founded: WSRI
- 3. Methods with humans in the loop (or, coordinating “ings”) • Active learning • Crowdsourcing • Pay-as-you-go
- 4. Methods with humans in the loop (or, coordinating “ings”) • Active learning • Crowdsourcing • Pay-as-you-go Candidate coreferent entities … TimBL ------ Wendy TimBL ------ TBL ChrisB ------ Bizer … Select & Present Verify
- 5. Methods with humans in the loop (or, coordinating “ings”) • Active learning • Crowdsourcing • Pay-as-you-go Candidate coreferent entities … TimBL ------ Wendy TimBL ------ TBL ChrisB ------ Bizer … Select & Present Verify Existing focus
- 6. Methods with humans in the loop (or, coordinating “ings”) • Active learning • Crowdsourcing • Pay-as-you-go Candidate coreferent entities … TimBL ------ Wendy TimBL ------ TBL ChrisB ------ Bizer … Select & Present Verify Our focus
- 7. Present entire entity descriptions?
- 8. Present a compact comparative summary! givenName: “Tim” surname: “Berners-Lee” isDirectorOf: W3C name: “Tim Berners-Lee” invented: WWW
- 9. Present a compact comparative summary! Which property-value (PV) pairs are more helpful?
- 10. Four aspects of a good comparative summary 1. Reflecting commonality 2. Reflecting difference 3. Providing information on identity 4. Providing diverse information
- 11. 1. Commonality • Common PV pairs = comparable properties + similar values TimBL givenName: “Tim” surname: “Berners-Lee” altName: “Tim BL” type: Scientist gender: “male” isDirectorOf: W3C TBL name: “Tim Berners-Lee” type: ComputerScientist type: RoyalSocietyFellow sex: “Male” invented: WWW founded: WSRI
- 12. 1. Commonality • Common PV pairs = comparable properties + similar values • More helpful properties = more like an Inverse Functional Property (IFP) TimBL givenName: “Tim” surname: “Berners-Lee” altName: “Tim BL” type: Scientist gender: “male” isDirectorOf: W3C TBL name: “Tim Berners-Lee” type: ComputerScientist type: RoyalSocietyFellow sex: “Male” invented: WWW founded: WSRI
- 13. 1. Commonality (details) • Comparability between properties • Learned from known coreferent entities • String similarity Comparable properties = Properties having similar values
- 14. 1. Commonality (details) • Comparability between properties • Learned from known coreferent entities • String similarity • Similarity between values • String similarity Comparable properties = Properties having similar values
- 15. 1. Commonality (details) • Comparability between properties • Learned from known coreferent entities • String similarity • Similarity between values • String similarity • Likeness to an IFP • Estimated based on the data set 𝐿𝑖𝑘𝑒𝑛𝑒𝑠𝑠 = 𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑑𝑖𝑠𝑡𝑖𝑛𝑐𝑡 𝑣𝑎𝑙𝑢𝑒𝑠 𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑎𝑙𝑙 𝑣𝑎𝑙𝑢𝑒𝑠 Comparable properties = Properties having similar values
- 16. 1. Commonality (weakness) • Only reflecting commonality can be misleading. TBL name: “Tim Berners-Lee” type: ComputerScientist type: RoyalSocietyFellow sex: “Male” invented: WWW founded: WSRI Wendy fullName: “Wendy Hall” type: ComputerScientist type: RoyalSocietyFellow sex: “Female” birthplace: London founded: WSRI
- 17. 2. Difference • Different PV pairs = comparable properties + dissimilar values TBL name: “Tim Berners-Lee” type: ComputerScientist type: RoyalSocietyFellow sex: “Male” invented: WWW founded: WSRI Wendy fullName: “Wendy Hall” type: ComputerScientist type: RoyalSocietyFellow sex: “Female” birthplace: London founded: WSRI
- 18. 2. Difference • Different PV pairs = comparable properties + dissimilar values • More helpful properties = more like a Functional Property (FP) TBL name: “Tim Berners-Lee” type: ComputerScientist type: RoyalSocietyFellow sex: “Male” invented: WWW founded: WSRI Wendy fullName: “Wendy Hall” type: ComputerScientist type: RoyalSocietyFellow sex: “Female” birthplace: London founded: WSRI
- 19. 2. Difference (details) • Comparability between properties • Learned from known coreferent entities • String similarity • Dissimilarity between values • String similarity • Likeness to a FP • Estimated based on the data set 𝐿𝑖𝑘𝑒𝑛𝑒𝑠𝑠 = 𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑑𝑖𝑠𝑡𝑖𝑛𝑐𝑡 𝑠𝑢𝑏𝑗𝑒𝑐𝑡𝑠 𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑎𝑙𝑙 𝑠𝑢𝑏𝑗𝑒𝑐𝑡𝑠
- 20. 3. Information on identity TimBL givenName: “Tim” surname: “Berners-Lee” altName: “Tim BL” type: Scientist gender: “male” isDirectorOf: W3C TBL name: “Tim Berners-Lee” type: ComputerScientist type: RoyalSocietyFellow sex: “Male” invented: WWW founded: WSRI
- 21. 3. Information on identity (details) • Information on identity • Estimated based on the data set 𝑖𝑛𝑓𝑜𝑟𝑚𝑎𝑡𝑖𝑜𝑛 = 1 − log 𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑒𝑛𝑡𝑖𝑡𝑖𝑒𝑠 ℎ𝑎𝑣𝑖𝑛𝑔 𝑡ℎ𝑖𝑠 𝑃𝑉 𝑝𝑎𝑖𝑟 log 𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑎𝑙𝑙 𝑒𝑛𝑡𝑖𝑡𝑖𝑒𝑠
- 22. 4. Diversity of information • Overlapping PV pairs = similar properties or similar values TimBL givenName: “Tim” surname: “Berners-Lee” altName: “Tim BL” type: Scientist gender: “male” isDirectorOf: W3C Overlapping
- 23. To find an optimal summary (or, to find the most helpful PV pairs) • Maximize • Commonality • Difference • Information on identity • Diversity of information • Subject to • A length limit
- 24. To find an optimal summary (or, to find the most helpful PV pairs) • Maximize • Commonality • Difference • Information on identity • Diversity of information • Subject to • A length limit • Formulated as a binary quadratic knapsack problem • Solved by GRASP-based local search
- 25. Evaluation method • 4 approaches to be blindly tested • 20 subjects (university students) • 24 random tasks for each subject • 4 approaches * (3 positive cases + 3 negative cases) • Sorted in random order givenName: “Tim” surname: “Berners-Lee” isDirectorOf: W3C name: “Tim Berners-Lee” invented: WWW Entity summary Subject Coreferent Non-coreferent Not sure Present Verify
- 26. Data sets and tasks • Data sets Places Films
- 27. Data sets and tasks • Data sets • Tasks http://dbpedia.org/resource/Paris,_Texas http://dbpedia.org/resource/Paris http://sws.geonames.org/4717560/ http://sws.geonames.org/2988507/ sameAs (positive case) sameAs (positive case) Places Films
- 28. Data sets and tasks • Data sets • Tasks Paris http://dbpedia.org/resource/Paris,_Texas http://dbpedia.org/resource/Paris http://sws.geonames.org/4717560/ http://sws.geonames.org/2988507/ disambiguates sameAs (positive case) sameAs (positive case) (negative cases) Places Films
- 29. Approaches Approach Description NOSUMM Present entire entity descriptions GENERIC • Information on identity [3] • Diversity of information COMPSUMM • Commonality • Difference • Information on identity • Diversity of information COMPSUMM-C • Commonality • Difference • Information on identity • Diversity of information [3] Gong Cheng et al. RELIN: Relatedness and Informativeness-based Centrality for Entity Summarization (ISWC 2011)
- 30. Results (1) • Accuracy of verification • COMPSUMM ≈ NOSUMM > COMPSUMM-C > GENERIC
- 31. Results (2) • Efficiency of verification • COMPSUMM > NOSUMM (2.7—2.9 times faster)
- 32. Take-home messages • Provide entity summaries for verifying coreference. • improves efficiency (2.7—2.9 times faster) • without notably affecting accuracy • Provide comparative (but not just generic) summaries. • Show both commonality and difference.
- 33. Future work • Present = Summarize + Visualize Candidate coreferent entities … TimBL ------ Wendy TimBL ------ TBL ChrisB ------ Bizer … Select & Present Verify Our focus
- 34. Thanks for your attention
- 35. Results (3) • Erroneous decisions • COMPSUMM-C > COMPSUMM (mostly in negative cases)
- 36. Performance testing • Offline computation • Comparability between properties (the learning part) • Likeness to an IFP/FP • Information on identity
- 37. Performance testing • Offline computation • Comparability between properties (the learning part) • Likeness to an IFP/FP • Information on identity • Online computation • Similarity between properties/values • Optimization • Results • Places (DBpedia and GeoNames): 24ms per case • Films (DBpedia and LinkedMDB): 35ms per case