Using Multi-Label Classification for Improved Question Answering

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearch

Authors

  • Ricardo Usbeck
  • Michael Hoffmann
  • Michael Röder
  • Jens Lehmann
  • Axel-Cyrille Ngonga Ngomo
A plethora of diverse approaches for question answering over RDF data have been developed in recent years. While the accuracy of these systems has increased significantly over time, most systems still focus on particular types of questions or particular challenges in question answering. What is a curse for single systems is a blessing for the combination of these systems. We show in this paper how machine learning techniques can be applied to create a more accurate question answering metasystem by reusing existing systems. In particular, we develop a multi-label classification-based metasystem for question answering over 6 existing systems using an innovative set of 14 question features. The metasystem outperforms the best single system by 14% F-measure on the recent QALD-6 benchmark. Furthermore, we analyzed the influence and correlation of the underlying features on the metasystem quality.
Original languageEnglish
Title of host publicationConference XXX
Number of pages15
DOIs
Publication statusIn preparation - 24.10.2017
Externally publishedYes

Bibliographical note

15 pages, 4 Tables, 3 Figues

Recently viewed

Publications

  1. Predicting online user behavior based on Real-Time Advertising Data
  2. Question Answering Mediated by Visual Clues and Knowledge Graphs
  3. From Learning Machines to Learning Humans
  4. Reducing problematic alcohol use in employees: economic evaluation of guided and unguided web-based interventions alongside a three-arm randomized controlled trial
  5. Logical-Rollenspiele
  6. Aboveground overyielding in grassland mixtures is associated with reduced biomass partitioning to belowground organs
  7. Green your community click by click
  8. "Introduction," communication +1
  9. On-board pneumatic pressure generation methods for soft robotics applications
  10. Degrees of Integration
  11. Does online-delivered Cognitive Behavioural Therapy for Insomnia improve insomnia severity in nurses working shifts? Protocol for a randomised-controlled trial
  12. Europe and the media: Changing structures in a changing context
  13. How do distinct facets of tree diversity and community assembly respond to environmental variables in the subtropical Atlantic Forest?
  14. When Do Pictures Help Learning from Expository Text? Multimedia and Modality Effects in Primary Schools
  15. Subsistence and substitutability in consumer preferences
  16. Probing turbulent superstructures in Rayleigh-Bénard convection by Lagrangian trajectory clusters
  17. Digital Seriality as Structure and Process
  18. Development of a robust classifier of freshwater residence in barramundi (Lates calcarifer) life histories using elemental ratios in scales and boosted regression trees
  19. Narrative dialogic reading with wordless picture books
  20. Extrusion Benchmark 2009 – A Step Ahead in Virtual Process Optimization
  21. How to assess transformative performance towards sustainable development in higher education institutions
  22. Introduction: The representative turn in EU Studies
  23. Learning linear classifiers sensitive to example dependent and noisy costs
  24. Swarm Robotics, or: the smartness of 'a bunch of cheap dumb things'
  25. Repeated sampling detects gene flow in a flightless ground beetle in a fragmented landscape
  26. Digital language teaching after COVID-19: what can we learn from the crisis?
  27. Credit constraints and exports: A survey of empirical studies using firm level data