Reversible stochastic attribute-value grammars (de Kok et al., 2011) use one model for parse disambiguation and fluency ranking. Such a model encodes preferences with respect to syntax, fluency, and appropriateness of logical forms, as weighted features. Reversible models are built on the premise that syntactic preferences are shared between parse disambiguation and fluency ranking. Given that ...

Reversible stochastic attribute-value grammars (de Kok et al., 2011) use one model for parse disambiguation and fluency ranking. Such a model encodes preferences with respect to syntax, fluency, and appropriateness of logical forms, as weighted features. Reversible models are built on the premise that syntactic preferences are shared between parse disambiguation and fluency ranking. Given that ...

In this paper, we propose a novel model, named Stroke Sequence-dependent Deep Convolutional Neural Network (SSDCNN), using the stroke sequence information and eight-directional features for Online Handwritten Chinese Character Recognition (OLHCCR). On one hand, SSDCNN can learn the representation of Online Handwritten Chinese Character (OLHCC) by incorporating the natural sequence information o...

the dogleg severity is one of the most important parameters in directional drilling. improvement of these indicators actually means choosing the best conditions for the directional drilling in order to reach the target point. selection of high levels of the dogleg severity actually means minimizing well trajectory, but on the other hand, increases fatigue in drill string, increases torque and d...

Recently, neural network approaches for parsing have largely automated the combination of individual features, but still rely on (often a larger number of) atomic features created from human linguistic intuition, and potentially omitting important global context. To further reduce feature engineering to the bare minimum, we use bi-directional LSTM sentence representations to model a parser stat...

This paper describes a method of retrieving handwritten text using directional features. Text search from handwritten digital ink employing character recognition technology has been developed. However, the character recognition based approach does not support languages which are not assumed. To address this problem, the proposed method was devised to hypothetically segment text into character s...

let $g=(v, e)$ be a graph. by emph{directional labeling (ord-labeling)} of an edge $x=uv$ of $g$ by an ordered $n$-tuple$(a_1,a_2,...,a_n)$, we mean a labeling of the edge $x$ such thatwe consider the label on $uv$ as $(a_1,a_2,...,a_n)$ in thedirection from $u$ to $v$, and the label on $x$ as$(a_{n},a_{n-1},...,a_1)$ in the direction from $v$ to $u$. inthis paper, we study graphs, called emph{...

A new feature called multi-directional local feature (MDLF) is proposed and applied in automatic speaker recognition. In order to extract the MDLF, a windowed speech signal is processed by fast Fourier transform and passed through 24 mel-scaled Filter Bank, followed by log compression. A three-point linear regression is then applied in four different directions, which are horizontal (time axis)...

The retrieval effectiveness of Automatic Fingerprint Recognition Systems can be improved greatly by restricting the search of a fingerprint to a limited scope. Fingerprint classification refers to the process of assigning a fingerprint to a predefined class predominantly based on global features. In this paper, an efficient compact fixed size feature vector based on directional variance for rep...

We compare the performance of Directional Derivatives features for automatic speech recognition when extracted from different time-frequency representations. Specifically, we use the short-time Fourier transform, Mel-frequency, and Gammatone spectrograms as a base from which we extract spectrotemporal modulations. We then assess the noise robustness of each representation with varied number of ...