Learning and Inference in Structured Prediction Models
نویسندگان
چکیده
This tutorial targets AI researchers who are interested in designing and applying structured prediction models to problems with interdependent output variables. The tutorial will introduce the problem of structured prediction exemplifying it in multiple AI problems, and then cover recent developments in efficient inference and learning methods in discriminative structured models and outline further research directions in this topic.
منابع مشابه
Learning Speed-Accuracy Tradeoffs in Nondeterministic Inference Algorithms
Statistical learning has led to great advances in building models that achieve high accuracy. However, testtime inference in these models can be slow, for example in structured prediction problems. This is frequently addressed by using test-time heuristics to guide and prune the search for a good structured output. In this high-level paper, we ask: Could we explicitly train such heuristics to t...
متن کاملDeep Learning and Structured Prediction for the Segmentation of Mass in Mammograms
In this paper, we explore the use of deep convolution and deep belief networks as potential functions in structured prediction models for the segmentation of breast masses from mammograms. In particular, the structured prediction models are estimated with loss minimization parameter learning algorithms, representing: a) conditional random field (CRF), and b) structured support vector machine (S...
متن کاملBlending Learning and Inference in Structured Prediction
In this paper we derive an efficient algorithm to learn the parameters of structured predictors in general graphical models. This algorithm blends the learning and inference tasks, which results in a significant speedup over traditional approaches, such as conditional random fields and structured support vector machines. For this purpose we utilize the structures of the predictors to describe a...
متن کاملThe Geometry of Constrained Structured Prediction: Applications to Inference and Learning of Natural Language Syntax
This thesis proposes new models and algorithms for structured output prediction, with an emphasis on natural language processing applications. We advance in two fronts: in the inference problem, whose aim is to make a prediction given a model, and in the learning problem, where the model is trained from data. For inference, we make a paradigm shift, by considering rich models with global featur...
متن کاملA Study of Imitation Learning Methods for Semantic Role Labeling
Global features have proven effective in a wide range of structured prediction problems but come with high inference costs. Imitation learning is a common method for training models when exact inference isn’t feasible. We study imitation learning for Semantic Role Labeling (SRL) and analyze the effectiveness of the Violation Fixing Perceptron (VFP) (Huang et al., 2012) and Locally Optimal Learn...
متن کامل