Visual question answering is a recently proposed arti€cial intelligence task that requires a deep understanding of both images and texts. In deep learning, images are typically modeled through convolutional neural networks, and texts are typically modeled through recurrent neural networks. While the requirement for modeling images is similar to traditional computer vision tasks, such as object ...

This paper defines a representation of universal quantification within distributional semantic space. We propose a discourse-internal approach to the meaning of limited instances of every, highlighting the possibilities and limitations of doing textual logic in a purely distributional framework.

This paper proposes a general probabilistic setting that formalizes the notion of textual entailment. In addition we describe a concrete model for lexical entailment based on web co-occurrence statistics in a bag of words representation.

J.M. Coetzee is directly or indirectly always concerned with the multi-layered narrative texts problematising concept of authorship and narration. This study treats two novels as “textual narratives” “narrative dramas” at a time. From postclassical narratological perspective, investigates narrators levels in J. M. Coetzee’s Elizabeth Costello (2003) authors without authority. The characters nov...

In this paper, we present the first version of a simulator that allows executing models defined using Discrete Event System Specification and models defined using Specification and Description Language. Specification and Description Language (SDL) is a graphical language, standardized under the ITU Z.100 recommendation, widely used to represent telecommunication systems, process control and rea...

Building intelligent tools for searching, indexing and retrieval applications is needed to congregate the rapidly increasing amount of visual data. This raised the need for building and maintaining ontologies and knowledgebases to support textual semantic representation of visual contents, which is an important block in these applications. This paper proposes a commonsense knowledgebase that fo...

We investigate a semi-automated identification of technical problems occurred by armed forces weapon systems during mission of war. The proposed methodology is based on a semantic analysis of textual information in reports from soldiers (war logs). Latent semantic indexing (LSI) with non-negative matrix factorization (NMF) as technique from multivariate analysis and linear algebra is used to ex...

Since we can hardly get semantics from the low-level features of the image, it is much more difficult to analyze the image than textual information on the Web. Traditionally, textual information around the image is used to represent the high-level features of the image. We argue that such “flat” representation can not describe images well. In this paper, Hierarchical Representation (HR) and HR-...

The large number, and the importance, of applications that support multi-lingual document processing have shown that the current methods and concepts for representing textual data in document processing systems are deficient in various respects. One major advance in this area is the development of the Unicode standard ([UC95]) for text character encoding. While this, or an similar updated stand...

A novel two-dimensional representation of documents may be used both to visualize and classify textual documents and to build classification schemes that may be used to browse, explore, and retrieve resources from Digital Library Management System (DLMS)s. We propose a mathematical formalization of the two-dimensional approach where documents’ coordinates are defined as probabilities. An extens...