Weakly-Supervised Acquisition of Labeled Class Instances using Graph Random Walks

We present a graph-based semi-supervised label propagation algorithm for acquiring opendomain labeled classes and their instances from a combination of unstructured and structured text sources. This acquisition method significantly improves coverage compared to a previous set of labeled classes and instances derived from free text, while achieving comparable precision.

• Type: Conference
• Year: 2008
• Where: EMNLP
• Authors: Partha Pratim Talukdar, Joseph Reisinger, Marius Pasca, Deepak Ravichandran, Rahul Bhagat, Fernando Pereira
• Keywords: EMNLP 2008, Graph-based Semi-supervised Label, Natural Language Processing, Opendomain Labeled Classes, Structured Text Sources