A Discriminative Latent Variable Model for Clustering of Streaming Data with Application to Coreference Resolution

We present a latent variable structured prediction model, called the Latent Left-linking Model (L3M), for discriminative supervised clustering of items that follow a streaming order. LM admits efficient inference and we present a learning framework for LM that smoothly interpolates between latent structural SVMs and hidden variable CRFs. We present a fast stochastic gradientbased learning technique for LM. We apply LM to coreference resolution, which is a well known clustering task in Natural Language Processing, and experimentally show that LM outperforms several existing structured predictionbased techniques for coreference as well as several state-of-the-art, albeit ad hoc, approaches.