HIEDS: A Generic and Efficient Approach to Hierarchical Dataset Summarization
Download as PPTX, PDF0 likes453 views
This document summarizes the HIEDS approach to hierarchical dataset summarization. HIEDS aims to provide multigranular summaries that preserve dataset structure and are comprehensible. It models summarization as a multidimensional knapsack problem to maximize subgroup cohesion and moderateness while disallowing large overlap. HIEDS uses a greedy strategy for efficient solving but requires non-trivial implementation. Experiments show HIEDS outperforms the baseline by generating hierarchical rather than flat groups with better trade-offs and less redundancy.
HIEDS: A Generic and Efficient Approach to Hierarchical Dataset Summarization
- 1. HIEDS: A Generic and Efficient Approach to Hierarchical Dataset Summarization Gong Cheng, Cheng Jin, Yuzhong Qu National Key Laboratory for Novel Software Technology Nanjing University, China Websoft
- 2. Linking Open Data cloud diagram 2014, by Max Schmachtenberg, Christian Bizer, Anja Jentzsch and Richard Cyganiak. http://lod-cloud.net/
- 3. Scenario: browsing a dataset in an open data portal https://data.europa.eu/euodp/en/data/dataset/dgt-translation-memory I need some insight into the contents, not just metadata.
- 4. Meeting the challenge with a dataset summary i.e., automatically generated small-sized, high-level abstraction of data, to summarize the contents of a dataset for quick inspection.
- 5. Expected features of a dataset summary • To provide multigranular abstraction of data to be incrementally explored • To preserve the structural nature of a dataset • To be comprehensible
- 6. Constitution of a dataset summary • An example A hierarchical grouping of entities Relations connecting sibling groups A property-value pair differentiates a group of entities from sibling groups.
- 7. Quality of a dataset summary • Coverage of data • Height of hierarchy • Cohesion within groups • Overlap between groups • Homogeneity of groups
- 8. Quality of a dataset summary • Coverage of data • large subgroups, frequent relations • Height of hierarchy • Cohesion within groups • Overlap between groups • Homogeneity of groups
- 9. Quality of a dataset summary • Coverage of data • Height of hierarchy • moderate-sized subgroups • Cohesion within groups • Overlap between groups • Homogeneity of groups
- 10. Quality of a dataset summary • Coverage of data • Height of hierarchy • Cohesion within groups • informative (i.e., less frequent) property-value pairs • Overlap between groups • Homogeneity of groups
- 11. Quality of a dataset summary • Coverage of data • Height of hierarchy • Cohesion within groups • Overlap between groups • controllable overlap • Homogeneity of groups
- 12. Quality of a dataset summary • Coverage of data • Height of hierarchy • Cohesion within groups • Overlap between groups • Homogeneity of groups • different values of the same property
- 13. Problem formulation: multidimensional knapsack problem (MKP) maximizing moderateness of each subgroup maximizing cohesion within each subgroup disallowing large overlap between subgroups selecting ≤k subgroups (optionally) disallowing different properties
- 14. Problem solution • A greedy strategy is used (sorting candidates by ) but its efficient implementation is non-trivial.
- 15. Experiments • Baseline: LODeX (ISWC’14) • flat grouping • biased towards coverage (e.g., Type:Person) • redundant information (e.g., Type:Person and Type:Chair) • Advantages of HIEDS • hierarchical grouping • trade-off between coverage and cohesion (e.g., Type:Actor) • controllable overlap
- 16. Details can be found in our poster!