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.

Automatic tagging and geotagging in video collections and communities

Abstract: Automatically generated tags and geotags hold great promise to improve access to video collections and online communities. We overview three tasks offered in the MediaEval 2010 benchmarking initiative, for each, describing its use scenario, definition and the data set released. For each task, a reference algorithm is presented that was used within MediaEval 2010 and comments are included on lessons learned. The Tagging Task, Professional involves automatically matching episodes in a collection of Dutch television with subject labels drawn from the keyword thesaurus used by the archive staff. The Tagging Task, Wild Wild Web involves automatically predicting the tags that are assigned by users to their online videos. Finally, the Placing Task requires automatically assigning geo-coordinates to videos. The specification of each task admits the use of the full range of available information including user-generated metadata, speech recognition transcripts, audio, and visual features.

Exploiting Cross-Sentence Context for Neural Machine Translation

Abstract: In translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a cross-sentence context-aware approach and investigate the influence of historical contextual information on the performance of neural machine translation (NMT). First, this history is summarized in a hierarchical way. We then integrate the historical representation into NMT in two strategies: 1) a warm-start of encoder and decoder states, and 2) an auxiliary context source for updating decoder states. Experimental results on a large Chinese-English translation task show that our approach significantly improves upon a strong attention-based NMT system by up to +2.1 BLEU points.

The Power of Prime Ministers: Results of an Expert Survey

Abstract: Prime ministers are self-evidently important actors in the politics of parliamentary democracies. While there has been an ongoing debate about prime ministerial power in the political science literature, progress has been slow in a debate dating from the 1960s. This lack of progress is because of two connected factors. One is the lack of a theoretical framework to study prime ministerial power. A framework is less likely to be developed because of the lack of data on which hypotheses could be tested. This article reports in detail the methodology and results of an expert survey that was conducted to measure prime ministerial power. These data will provide a significant resource for the future study of prime ministers, cabinets, and the core executive.

Context-based arithmetic encoding of 2D shape sequences

Abstract: A new method for shape coding in object-based video sequences is presented. Context-based arithmetic encoding, as used in JBIG, is utilised within a block-based framework and further extended in order to make efficient use of temporal prediction. It is shown to be a simple, efficient and elegant solution.