Template-based Question Answering using Recursive Neural Networks

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Authors

  • Ram G. Athreya
  • Srividya K. Bansal
  • Axel Cyrille Ngonga Ngomo
  • Ricardo Usbeck

Most question answering (QA) systems over Linked Data, i.e. Knowledge Graphs, approach the question answering task as a conversion from a natural language question to its corresponding SPARQL query. A common approach is to use query templates to generate SPARQL queries with slots that need to be filled. Using templates instead of running an extensive NLP pipeline or end-to-end model shifts the QA problem into a classification task, where the system needs to match the input question to the appropriate template. This paper presents an approach to automatically learn and classify natural language questions into corresponding templates using recursive neural networks. Our model was trained on 5000 questions and their respective SPARQL queries from the preexisting LC-QuAD dataset grounded in DBpedia, spanning 5042 entities and 615 predicates. The resulting model was evaluated using the FAIR GERBIL QA framework resulting in 0.419 macro f-measure on LC-QuAD and 0.417 macro f-measure on QALD-7.

OriginalspracheEnglisch
TitelProceedings - 2021 IEEE 15th International Conference on Semantic Computing, ICSC 2021
Anzahl der Seiten4
VerlagInstitute of Electrical and Electronics Engineers Inc.
Erscheinungsdatum01.2021
Seiten195-198
Aufsatznummer9364639
ISBN (Print)978-1-7281-8900-0
ISBN (elektronisch)978-1-7281-8899-7
DOIs
PublikationsstatusErschienen - 01.2021
Extern publiziertJa
Veranstaltung15th IEEE International Conference on Semantic Computing - ICSC 2021 - Virtual, Laguna Hills, Virtual, Laguna Hills, USA / Vereinigte Staaten
Dauer: 27.01.202129.01.2021
Konferenznummer: 15

DOI

Zuletzt angesehen

Publikationen

  1. A sensor fault detection scheme as a functional safety feature for DC-DC converters
  2. Evaluating structural and compositional canopy characteristics to predict the light-demand signature of the forest understorey in mixed, semi-natural temperate forests
  3. lp-Norm Multiple Kernel Learning
  4. Design optimization of spiral coils for textile applications by genetic algorithm
  5. Exact and approximate inference for annotating graphs with structural SVMs
  6. Fast, Fully Automated Analysis of Voriconazole from Serum by LC-LC-ESI-MS-MS with Parallel Column-Switching Technique
  7. Recurrence Quantification Analysis of Processes and Products of Discourse
  8. Lessons learned for spatial modelling of ecosystem services in support of ecosystem accounting
  9. Construct Objectification and De-Objectification in Organization Theory
  10. Computational modeling of amorphous polymers
  11. Modeling and numerical simulation of multiscale behavior in polycrystals via extended crystal plasticity
  12. Influence of Process Parameters and Die Design on the Microstructure and Texture Development of Direct Extruded Magnesium Flat Products
  13. Simple saturated PID control for fast transient of motion systems
  14. Dynamic Lot Size Optimization with Reinforcement Learning
  15. The delay vector variance method and the recurrence quantification analysis of energy markets
  16. Introducing parametric uncertainty into a nonlinear friction model
  17. Faulty Process Detection Using Machine Learning Techniques
  18. TextGraphs 2024 Shared Task on Text-Graph Representations for Knowledge Graph Question Answering
  19. Clause identification using entropy guided transformation learning
  20. Mathematical Modeling for Robot 3D Laser Scanning in Complete Darkness Environments to Advance Pipeline Inspection
  21. Dispatching rule selection with Gaussian processes
  22. Constraints are the solution, not the problem
  23. Dynamic priority based dispatching of AGVs in flexible job shops
  24. Mining positional data streams
  25. Understanding the properties of isospectral points and pairs in graphs
  26. Improving students’ science text comprehension through metacognitive self-regulation when applying learning strategies
  27. Comments on "Tracking Control of Robotic Manipulators With Uncertain Kinematics and Dynamics"
  28. Computing regression statistics from grouped data
  29. From Knowledge to Application
  30. Gaussian processes for dispatching rule selection in production scheduling