Natural Language Interface on a Video Data Model.
Guzen Erozel, Nihan Kesim Çiçekli, Ilyas Cicekli · 2005
Depending on a content-based spatio-temporal video data model, a natural language interface is implemented to query the video data. The queries, which are given as English sentences, are parsed using Link Parser, and the semantic representations of given queries are extracted from their syntactic structures using information extraction techniques. At the last step, the extracted semantic representations are used to call the related parts of the underlying spatio-temporal video data model to get the results of the queries.