Automatic word segmentation is a basic requirement for unsupervised learning in morphological analysis. In this paper, we formulate a novel recursive method for minimum description length (MDL) word segmentation, whose basic operation is resegmenting the corpus on a prefix (equivalently, a suffix). We derive a local expression for the change in description length under resegmentation, i.e., one...

A major task in computational biology is the discovery of short recurring string patterns known as motifs. Most of the schemes to discover motifs are either stochastic or combinatorial in nature. Stochastic approaches do not guarantee finding the correct motifs, while the combinatorial schemes tend to have an exponential time complexity with respect to motif length. To alleviate the cost, the c...

In this work we investigate and extend the current state-of-the-art system for text spotting in natural images [Jaderberg et al. 2014a]. First, we extend text recognition to be case-sensitive and include special characters and punctuation marks. Next, we improve text recognition at various word-length scales using separate deep convolutional neural networks for different length intervals. Final...

The present study aims at the quantitative classification of texts and text types. By way of a case study, 398 Slovenian texts from different genres and authors are analyzed as to their word length. It is shown that word length is an important factor in the synergetic self-regulation of texts and text types, and that word length may significantly contribute to a new typology of discourse types.

A plaintext is separated into two parts, a fixed length part and a variable length part. The second part of the plaintext is encrypted to a cipher text using a key. In this paper, an encryption algorithm which encrypts the first part of the plaintext and the key of the second part to a cipher text is proposed. Basic computing operations, such as inserting dummy symbols, rotating, transposition,...

For the last few years, text mining has been gaining significant importance. Since Knowledge is now available to users through variety of sources i.e. electronic media, digital media, print media, and many more. Due to huge availability of text in numerous forms, a lot of unstructured data has been recorded by research experts and have found numerous ways in literature to convert this scattered...

MOTIVATION A palindrome is a string that reads the same forward and backward. Finding palindromic substructures is important in DNA, RNA or protein sequence analysis. We say that two strings of the same length are pal-equivalent if, for each possible centre, they have the same length of the maximal palindrome. Given a text T of length n and a pattern P of length m, we study the palindrome patte...

In this letter, we propose a vocal tract length (VTL) perturbation method for text-dependent speaker verification (TD-SV), in which set of TD-SV systems are trained, one each VTL factor, and score-level fusion is applied to make final decision. Next, explore the bottleneck (BN) feature extracted by training deep neural networks with self-supervised objective, autoregressive predictive coding (A...

We propose an end-to-end recurrent encoder-decoder based sequence learning approach for printed text Optical Character Recognition (OCR). In contrast to present day existing state-of-art OCR solution [Graves et al. (2006)] which uses CTC output layer, our approach makes minimalistic assumptions on the structure and length of the sequence. We use a two step encoder-decoder approach – (a) A recur...