Skip to content

Latest commit

 

History

History
executable file
·
10 lines (10 loc) · 477 Bytes

README.md

File metadata and controls

executable file
·
10 lines (10 loc) · 477 Bytes

pytorch implementation for the STAR model in CIKM 2019 "STAR: Spatio-Temporal Taxonomy-Aware Tag Recommendation for Citizen Complaints"

Packages

  • python 3.6
  • torch 1.0.1
  • numpy 1.15.4
  • scikit-learn 0.20.2

Run

  • Step1: Create the data directory which contains texts, timestamps, and locations of complaints, as well as the tag taxonomy
  • Step2: Set hyper-parameters in main.py
  • Step3: python main.py, which trains the model and reports performance on the test set