Using Graphs of Classifiers to Impose Constraints on Semi-supervised Relation Extraction

We propose a general approach to modeling semi-supervised learning constraints on unlabeled data. Both traditional supervised classification tasks and many natural semi-supervised learning heuristics can be approximated by specifying the desired outcome of walks through a graph of classifiers. We demonstrate the modeling capability of this approach in the task of relation extraction, and experimental results show that the modeled constraints achieve better performance as expected.

Paper

Full text

PDF

Using Graphs of Classifiers to Impose Constraints on Semi-supervised Relation Extraction

Semantic Scholar · Computer Science · 2016

Abstract

We propose a general approach to modeling semi-supervised learning constraints on unlabeled data. Both traditional supervised classification tasks and many natural semi-supervised learning heuristics can be approximated by specifying the desired outcome of walks through a graph of classifiers. We demonstrate the modeling capability of this approach in the task of relation extraction, and experimental results show that the modeled constraints achieve better performance as expected.

References (12)

12Semisupervised learning using Gaussian fields and harmonic functions2003 · Proceedings of ICML-03, the 20th International Conference on Machine Learning

Similar papers

© 2026 NYSGPT2525 LLC