Corpus ID: 52085371

Distil : A Mixed-Initiative Model Discovery System for Subject Matter Experts ( Demo )

@inproceedings{Langevin2018DistilA,
  title={Distil : A Mixed-Initiative Model Discovery System for Subject Matter Experts ( Demo )},
  author={Scott Langevin},
  year={2018}
}
  • Scott Langevin
  • Published 2018
  • We present in-progress work on Distil, a mixed-initiative system to enable non-experts with subject matter expertise to generate data-driven models using an interactive analytic question first workflow. Our approach incorporates data discovery, enrichment, analytic model recommendation, and automated visualization to understand data and models. 
    3 Citations

    Figures from this paper.

    Towards Evaluating Exploratory Model Building Process with AutoML Systems
    Survey on Automated Machine Learning
    • 30
    Semantic Classification of Tabular Datasets via Character-Level Convolutional Neural Networks
    • 3
    • PDF

    References

    SHOWING 1-10 OF 23 REFERENCES
    Mixed-Initiative for Big Data: The Intersection of Human + Visual Analytics + Prediction
    • 15
    • PDF
    Predictive Interaction for Data Transformation
    • 71
    • PDF
    Mixed-initiative visual analytics using task-driven recommendations
    • 24
    • PDF
    Predictive Analytics Using a Blackboard-Based Reasoning Agent
    • Jia Yue, A. Raja, W. Ribarsky
    • Computer Science
    • 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology
    • 2010
    • 4
    • PDF
    Proactive wrangling: mixed-initiative end-user programming of data transformation scripts
    • 56
    • PDF
    Articulate: A Semi-automated Model for Translating Natural Language Queries into Meaningful Visualizations
    • 54
    • PDF
    DataTone: Managing Ambiguity in Natural Language Interfaces for Data Visualization
    • 90
    • PDF
    Abstractive Tabular Dataset Summarization via Knowledge Base Semantic Embeddings
    • 2
    • PDF
    A Survey of Visual Analytic Pipelines
    • 33
    The human is the loop: new directions for visual analytics
    • 105
    • PDF