Purpose. Text documents are an important source of data for tech mining techniques. Usually text databases include document sufficiently long to apply conventional text mining techniques. However in some tech mining tasks, such as capabilities identification process, we have database with very short texts, which represent a challenge for conventional text mining techniques. The problem has to d...

Exploring an online conversation can be very difficult for a user, especially when it becomes a long complex thread. We follow a human-centered design approach to tightly integrate text mining methods with interactive visualization techniques to support the users in fulfilling their information needs. The resulting visual text analytic system provides multifaceted exploration of asynchronous co...

Establishing hidden communication and conveying information secretly has been of interest since long past ago. One of the methods introduced for establishing hidden communication is Steganography. Methods of Steganography have been mostly applied on images, audios, videos, and text files while the major characteristics of these methods are to change in the structure and features so as not be id...

The reading of text by computer without human intervention remains an elusive goal of Artificial Intelligence research. Reading is the transformation of an arbitrary page of text, that could contain a mixture of machine -printed, hand -printed, or handwritten text, from its representation as a two -dimensional image into a form understandable by a computer' such as ASCII code. The current lack ...

We examine deployment strategies for text translation and text summarization tasks. We formalize a deployment strategy along three dimensions: work structure, workforce organization, and work style. Work structure can be either simultaneous or sequential, workforce organization independent or collaborative, and work style either crowd-only or hybrid. We use Amazon Mechanical Turk to evaluate th...

The work of the textual critic has long centered in the task of collating manuscripts, counting variants, and computing the results for the purpose of placing manuscripts in their proper text -types. This process is essential for building a critical text. However, as important as this , work may be, dealing statistically with variant readings can result in a neglect of the contribution the vari...

Semantic Text segmentation and sub-topic extraction divides the input text into coherent paragraphs and extracts topics out of them. This enables applications to extract relevant meaningful data that could be useful in many text analysis tasks like information retrieval and summarization. In this project we have combined the techniques of text tiling and latent semantic analysis and have come u...

This paper describes a new compression algorithm of document images based on separating the text layer from the graphics one on the initial image and compression of each layer by the most suitable common algorithm. Then compressed layers are placed into PDF/A, a standardizated file format for long-term archiving of electronic documents. Using the individual separation algorithm for each type of...

0