Automated interlinking of speech radio archives
Automated interlinking of speech radio archives
复制标题
语音广播档案自动互连
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Christopher Lowis
中科院分区：
文献类型：
--
作者：
Yves Raimond;Christopher Lowis
BBC目前正在手动为节目加标签，使用DBpedia作为标签标识的来源，并从节目提要中提取建议标签的列表。这些标签然后被用来帮助导航和基于主题的BBC节目搜索。然而，鉴于档案中可获得的节目数量非常多，其中大多数节目的元数据很少，我们需要一种自动为节目分配标签的方法。我们描述了一个框架来做到这一点，使用语音识别、文本处理和概念标记技术。我们针对手动应用的标签对该框架进行了评估，并将其与相关工作进行了比较。我们发现，这个框架足够好地引导归档内容的链接过程。
The BBC is currently tagging programmes manually, using DBpedia as a source of tag identiers, and a list of suggested tags extracted from their synopsis. These tags are then used to help navigation and topic-based search of BBC programmes. However, given the very large number of programmes available in the archive, most of them having very little metadata attached to them, we need a way of automatically assigning tags to programmes. We describe a framework to do so, using speech recognition, text processing and concept tagging techniques. We evaluate this framework against manually applied tags, and compare it with related work. We nd that this framework is good enough to bootstrap the interlinking process of archived content.