Abstract
This paper presents a latent variable structured prediction model for discriminative supervised clustering of items called the Latent Left-linking Model ( M). We present an online clustering algorithm for M based on a feature-based item similarity function. We provide a learning framework for estimating the similarity function and present a fast stochastic gradient-based learning technique. In our experiments on coreference resolution and document clustering, M outperforms several existing online as well as batch supervised clustering techniques.