论文信息 - Deriving semantic annotations of an audiovisual program from contextual texts

Deriving semantic annotations of an audiovisual program from contextual texts

The aim of this paper is to explore whether indexing terms for an audiovisual program can be derived from contextual texts automatically. For this we apply natural-language processing techniques to contextual texts of two Dutch TV-programs. We use a Dutch domain thesaurus to derive possible metadata. This possible metadata is ranked by an algorithm which uses the relations of the thesaurus. We evaluate the results by comparing them to human made descriptions.

[1] Diana Maynard,et al. NE Recognition Without Training Data on a Language You Don't Speak , 2003, NER@ACL.

[2] Wessel Kraaij,et al. Viewing stemming as recall enhancement , 1996, SIGIR '96.

[3] Sergey Brin,et al. The Anatomy of a Large-Scale Hypertextual Web Search Engine , 1998, Comput. Networks.

[4] Estelle Le Roux. Extraction d'information de documents textuels associ es ` ad es contenus audiovisuels , 2001 .

[5] Kalina Bontcheva,et al. Multimedia indexing through multi-source and multi-language information extraction: the MUMIS project , 2004, Data Knowl. Eng..

[6] Helmut Schmid,et al. Improvements in Part-of-Speech Tagging with an Application to German , 1999 .