Keepin' It Real: Semi-Supervised Learning With Realistic Tuning

Free registration required

Executive Summary

The authors address two critical issues involved in applying Semi-Supervised Learning (SSL) to a real-world task: parameter tuning and choosing which (If any) SSL algorithm is best suited for the task at hand. To gain a better understanding of these issues, they carry out a medium-scale empirical study comparing Supervised Learning (SL) to two popular SSL algorithms on eight natural language processing tasks under three performance metrics. They simulate how a practitioner would go about tackling a new problem, including parameter tuning using Cross Validation (CV). They show that, under such realistic conditions, each of the SSL algorithms can be worse than SL on some datasets

  • Format: PDF
  • Size: 100.33 KB