Representing image captions as concept graphs using semantic information

Conceptual interpretation of languages has gathered peak interest in the world of artificial intelligence. The challenge in modeling various complications involved in a language is the main motivation behind our work. Our main focus in this work is to develop conceptual graphical representation for image captions. We have used discourse representation structure to gain semantic information which is further modeled into a graphical structure. The effectiveness of the model is evaluated by a caption based image retrieval system. The image retrieval is performed by computing subgraph based similarity measures. Best retrievals were given an average rating of . ± . out of 4 by a group of 25 human judges. The experiments were performed on a subset of the SBU Captioned Photo Dataset. This purpose of this work is to establish the cognitive sensibility of the approach to caption representations

Representing image captions as concept graphs using semantic information

Conceptual interpretation of languages has gathered peak interest in the world of artificial intelligence. The challenge in modeling various complications involved in a language is the main motivation behind our work. Our main focus in this work is to develop conceptual graphical representation for image captions. We have used discourse representation structure to gain semantic information which is further modeled into a graphical structure. The effectiveness of the model is evaluated by a caption based image retrieval system. The image retrieval is performed by computing subgraph based similarity measures. Best retrievals were given an average rating of . ± . out of 4 by a group of 25 human judges. The experiments were performed on a subset of the SBU Captioned Photo Dataset. This purpose of this work is to establish the cognitive sensibility of the approach to caption representations.

Zeitgeist or chameleon? A quantitative analysis of CSR definitions.

Despite its increasing relevance, corporate social responsibility (CSR) remains hobbled by problems, variously charged as being chameleon, vacuous or an utterly meaningless concept. One reason is the absence of an agreed upon normative basis underpinning CSR. This is in large part due to the concept lacking a universally accepted definition. This paper explores how the concept of CSR has evolved over time drawing from 110 definitions of the construct. Using co-word analysis of definitions from 1953 to 2014, the study maps how the structure of the definitions has evolved during the field's historical development. The research uncovers the key terms underpinning the phenomenon, the centrality of these terms as well as mapping their interrelationships and evolution. The findings suggest that, despite the profusion and definitional heterogeneity over the six decades of the development of the field, there are six recurrent, enduring dimensions that underpin the CSR concept. These dimensions are economic, social, ethical, stakeholders, sustainability and voluntary. This paper makes several contributions to the academic literature. The systematic, quantitative analysis of definitions brings an objectivity that previous qualitative bibliometric analyses of CSR have lacked. The time period selected is substantially longer than previous analyses and captures the complete historical evolution of the concept. Moreover, the analysis provides the basis for the development of a new, comprehensive, yet concise, definition of CSR that captures all six of the recurring dimensions underpinning the concept.