Summary for Structured Prediction Cascades
نویسنده
چکیده
Structured prediction is a supervised machine learning technique that involves predicting structured objects, rather than scalar discrete or real values(which correspond to classifications and regressions)[1]. Structured data is data that consists of several parts, and not only the parts themselves contain information, but also the way in which the parts belong together[2]. Under this definition, many tasks can be regarded as a structured prediction problem, like part-of-speech tagging, machine translation, parsing in NLP, and segmentation, pose estimation in computer vision. Thus, a fast and accurate structured prediction algorithm is appealing because it can help many tasks in different fields.
منابع مشابه
Stuctured Predictions Cascades
Structured prediction tasks pose a fundamental trade off between the need for model complexity to increase predictive power and the limited computational resources for inference in the exponentially-sized output spaces such models require. We formulate and develop structured prediction cascades: a sequence of increasingly complex models that progressively filter the space of possible outputs. W...
متن کاملStructured Prediction Cascades
Structured prediction tasks pose a fundamental trade-off between the need for model complexity to increase predictive power and the limited computational resources for inference in the exponentially-sized output spaces such models require. We formulate and develop the Structured Prediction Cascade architecture: a sequence of increasingly complex models that progressively filter the space of pos...
متن کاملVine Pruning for Efficient Multi-Pass Dependency Parsing
Coarse-to-fine inference has been shown to be a robust approximate method for improving the efficiency of structured prediction models while preserving their accuracy. We propose a multi-pass coarse-to-fine architecture for dependency parsing using linear-time vine pruning and structured prediction cascades. Our first-, second-, and third-order models achieve accuracies comparable to those of t...
متن کاملSidestepping Intractable Inference with Structured Ensemble Cascades
For many structured prediction problems, complex models often require adopting approximate inference techniques such as variational methods or sampling, which generally provide no satisfactory accuracy guarantees. In this work, we propose sidestepping intractable inference altogether by learning ensembles of tractable sub-models as part of a structured prediction cascade. We focus in particular...
متن کاملIDK Cascades: Fast Deep Learning by Learning not to Overthink
Advances in deep learning have led to substantial increases in prediction accuracy but have been accompanied by increases in the cost of rendering predictions. We conjecture that for a majority of real-world inputs, the recent advances in deep learning have created models that effectively “over-think” on simple inputs. In this paper we revisit the question of how to effectively build model casc...
متن کامل