Description The ACCEPT Academic Portal is a user-centred online platform specifically designed to offer a complete machine translation workflow including pre-editing and post-editing steps for teaching purposes. The platform leverages technology developed in the ACCEPT European Project (2012-2014) devoted to improving the translatability of user-generated content. Originally available as a seri...

In this paper, we present the approaches used by our NLP systems to automatically extract templates for example-based machine translation and pun generation. Our translation system is able to extract an average of 73.25% correct translation templates, resulting in a translation quality that has a low word error rate of 18% when the test document contains sentence patterns matching the training ...

With the active participation of users in product review platforms, online consumer-generated content, and, more specifically, user-generated reviews, have become a clear reference purchasing decision-making processes, which sometimes exceed impact advertising campaigns. A common feature most tourism platforms is use machine translation (MT) systems to immediately make reviews available various...

Current machine translation systems require human revision to produce high-quality translations. This is achieved through a post-editing process or by means of an interactive human–computer collaboration. Most protocols belonging to the last scenario follow a left-to-right strategy, where the prefix of the translation is iteratively increased by successive validations and corrections made by th...

This paper describes one approach for calculating the cohomology of a particular complex which arises in knot theory and which is used to prove the existence of ‘associators’, a key ingredient in the construction of a universal knot invariant. The approach taken is to show that the relevant complex can be interpreted, essentially, as the cohomology of the functor Hom(K, C), where C is the coalg...

This paper presents the approach of the Glocal European funded project towards the co-production of news on World events, on an information marketplace involving both amateurs and professionals. It discuss the rise of user-generated content amongst worldwide media and how event modelling and technology usage may help to foster this pro-am collaboration. Glocal: Event-based Retrieval of Networke...

We propose a two-stage process to explain the relationship between the local news environment and citizen engagement. Our original content analysis of newspaper coverage in every US House district during the 2010 midterms reveals that districts with uncompetitive races and those served by large-circulation outlets see significantly less, and less substantive, coverage than hotly contested distr...