Open Domain INformer (ODIN) 
Rule-base information extraction (IE) has long enjoyed wide adoption throughout industry, though it has remained largely ignored in academia, in favor of machine learning (ML) methods (Chiticariu et al., 2013). However, rule-based systems have several advantages over pure ML systems, including: (a) the rules are interpretable and thus suitable for rapid development and/or domain transfer; and (b) humans and machines can contribute to the same model. Why then have such systems failed to hold the attention of the academic community? One argument raised by Chiticariu et al. is that, despite notable previous efforts (Appelt and Onyshkevych, 1998; Levy and Andrew, 2006; Hunter et al., 2008; Cunningham et al., 2011; Chang and Manning, 2014), there is not a standard language for this task, or a ‘standard way to express rules’, which raises the entry cost for new rule-based systems. ODIN aims to address these issues with a new language and framework. We follow the simplicity principles promoted by other natural language processing toolkits, such as Stanford’s CoreNLP, which aim to ‘avoid over-design’, ‘do one thing well’, and have a user ‘up and running in ten minutes or less’ (Manning et al., 2014). …
Learning by Association
In many real-world scenarios, labeled data for a specific machine learning task is costly to obtain. Semi-supervised training methods make use of abundantly available unlabeled data and a smaller number of labeled examples. We propose a new framework for semi-supervised training of deep neural networks inspired by learning in humans. ‘Associations’ are made from embeddings of labeled samples to those of unlabeled ones and back. The optimization schedule encourages correct association cycles that end up at the same class from which the association was started and penalizes wrong associations ending at a different class. The implementation is easy to use and can be added to any existing end-to-end training setup. We demonstrate the capabilities of learning by association on several data sets and show that it can improve performance on classification tasks tremendously by making use of additionally available unlabeled data. In particular, for cases with few labeled data, our training scheme outperforms the current state of the art on SVHN. …
Curvature
We study Stochastic Gradient Descent (SGD) with diminishing step sizes for convex objective functions. We introduce a definitional framework and theory that defines and characterizes a core property, called curvature, of convex objective functions. In terms of curvature we can derive a new inequality that can be used to compute an optimal sequence of diminishing step sizes by solving a differential equation. Our exact solutions confirm known results in literature and allows us to fully characterize a new regularizer with its corresponding expected convergence rates. …
Like this:
Like Loading…
Related