Abstract | ||
---|---|---|
This article describes our participation at the VideoCLEF track of the CLEF campaign 2008. We designed and implemented a prototype for the classication of the Video ASR data. Our approach was to regard the task as text classication problem. We used terms from Wikipedia categories as training data for our text classiers. For the text classication the Naive-Bayes and kNN classier from the WEKA toolkit were used. We submitted experiments for classication task 1 and 2. For the translation of the feeds to English (translation task) Google's AJAX language API was used. The evaluation of the classication task showed bad results for our experiments with a precision between 10 and 15 percent. These values did not meet our expectations. Interestingly, we could not improve the quality of the classication by using the provided metadata. But at least the created translation of the RSS Feeds was well. |
Year | Venue | Keywords |
---|---|---|
2008 | CLEF (Working Notes) | video classication,automatic speech transcripts |
Field | DocType | Citations |
Training set,Metadata,Computer science,Ajax,Natural language processing,Artificial intelligence,Classifier (linguistics),RSS,Clef | Conference | 4 |
PageRank | References | Authors |
0.51 | 3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jens Kursten | 1 | 18 | 2.62 |
Daniel Richter | 2 | 60 | 9.52 |
Maximilian Eibl | 3 | 119 | 37.66 |