A Discriminative Latent Variable Model for Online Clustering
نویسندگان
چکیده
This paper presents a latent variable structured prediction model for discriminative supervised clustering of items called the Latent Left-linking Model (LM). We present an online clustering algorithm for LM 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, LM outperforms several existing online as well as batch supervised clustering techniques.
منابع مشابه
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 techn...
متن کاملCoactive Learning for Interactive Machine Translation
Coactive learning describes the interaction between an online structured learner and a human user who corrects the learner by responding with weak feedback, that is, with an improved, but not necessarily optimal, structure. We apply this framework to discriminative learning in interactive machine translation. We present a generalization to latent variable models and give regret and generalizati...
متن کاملGender-based Differences in Associations between Attitude and Self-esteem with Smoking Behavior among Adolescents: A Secondary Analysis Applying Bayesian Nonparametric Functional Latent Variable Model
Background: Different patterns of gender-based relationships between attitude toward smoking and self-esteem with smoking behavior have reported. However, such associations may be much more complex than a simply supposed linear relationship. We aimed to propose a method of providing hand details on the total and gender-based scenarios of the relationships between attitude toward smoking and sel...
متن کاملA Discriminative Latent Variable Model for Statistical Machine Translation
Large-scale discriminative machine translation promises to further the state-of-the-art, but has failed to deliver convincing gains over current heuristic frequency count systems. We argue that a principle reason for this failure is not dealing with multiple, equivalent translations. We present a translation model which models derivations as a latent variable, in both training and decoding, and...
متن کاملStochastic Discriminative EM
Stochastic discriminative EM (sdEM) is an online-EM-type algorithm for discriminative training of probabilistic generative models belonging to the natural exponential family. In this work, we introduce and justify this algorithm as a stochastic natural gradient descent method, i.e. a method which accounts for the information geometry in the parameter space of the statistical model. We show how ...
متن کامل