Dublin City University

About: Dublin City University is a education organization based out in Dublin, Ireland. It is known for research contribution in the topics: Machine translation & Laser. The organization has 5904 authors who have published 17178 publications receiving 389376 citations. The organization is also known as: National Institute for Higher Education, Dublin & DCU.

Is Green the New Black? Reflections on a Green Commodity Discourse:

Abstract: This article examines the global sustainability movement through the lens of a green commodity discourse as introduced by Prothero and Fitchett. The current wave of sustainability efforts and initi...

Knowledge Diffusion for Neural Dialogue Generation

Abstract: End-to-end neural dialogue generation has shown promising results recently, but it does not employ knowledge to guide the generation and hence tends to generate short, general, and meaningless responses. In this paper, we propose a neural knowledge diffusion (NKD) model to introduce knowledge into dialogue generation. This method can not only match the relevant facts for the input utterance but diffuse them to similar entities. With the help of facts matching and entity diffusion, the neural dialogue generation is augmented with the ability of convergent and divergent thinking over the knowledge base. Our empirical study on a real-world dataset prove that our model is capable of generating meaningful, diverse and natural responses for both factoid-questions and knowledge grounded chi-chats. The experiment results also show that our model outperforms competitive baseline models significantly.

Subject-oriented design: towards improved alignment of requirements, design, and code

Abstract: In practice, object-oriented design models have been less useful throughout the lifetime of software systems than they should be. Design models are often large and monolithic, and the structure of the designs is generally quite different from that of requirements. As a result, developers tend to discard the design, especially as the system evolves, since it is too difficult to keep its relationship to requirements and code accurate, especially when both are changing. This paper presents a different approach to designing systems, based on flexible decomposition and composition, that closely aligns designs with both requirements specifications and with code. We illustrate how this approach permits the benefits of designs to be maintained throughout a system’s lifetime.