A Semantic Model for Integrated Content Management, Localisation and Language Technology Processing

Abstract

Providers of products and services are faced with the dual challenge of supporting the languages and individual needs of the global customer while also accommodating the increasing relevance of user-generated content. As a result, the content and localisation industries must now evolve rapidly from manually processing predicable content which arrives in large jobs to the highly automated processing of streams of fast moving, heterogeneous and unpredictable content. This requires a new generation of digital content management technologies that combine the agile flow of content from developers to localisers and consumers with the data-driven language technologies needed to handle the volume of content required to feed the demands of global markets. Data-driven technologies such as statistical machine translation, cross-lingual information retrieval, sentiment analysis and automatic speech recognition, all rely on high quality training content, which in turn must be continually harvested based on the human quality judgments made across the end-to-end content processing flow. This paper presents the motivation, approach and initial semantic models of a collection of research demonstrators where they represent a part of, or a step towards, documenting in a semantic model the multi-lingual semantic web.