Difference between revisions of "The Xtrieval Framework at Clef 2008: Imageclef Wikipedia Mm Task"
(+ wikilinks) |
(infobox) |
||
| Line 1: | Line 1: | ||
| + | {{Infobox work | ||
| + | | title = The Xtrieval Framework at Clef 2008: Imageclef Wikipedia Mm Task | ||
| + | | date = 2008 | ||
| + | | authors = [[Thomas Wilhelm]]<br />[[Jens Kürsten]]<br />[[Maximilian Eibl]] | ||
| + | | link = http://ceur-ws.org/Vol-1174/CLEF2008wn-ImageCLEF-WilhelmEt2008b.pdf | ||
| + | }} | ||
'''The Xtrieval Framework at Clef 2008: Imageclef Wikipedia Mm Task''' - scientific work related to [[Wikipedia quality]] published in 2008, written by [[Thomas Wilhelm]], [[Jens Kürsten]] and [[Maximilian Eibl]]. | '''The Xtrieval Framework at Clef 2008: Imageclef Wikipedia Mm Task''' - scientific work related to [[Wikipedia quality]] published in 2008, written by [[Thomas Wilhelm]], [[Jens Kürsten]] and [[Maximilian Eibl]]. | ||
== Overview == | == Overview == | ||
This paper describes participation at the ImageCLEF [[Wikipedia]] MM task. Authors used Xtrieval framework for the preparation and execution of the experiments. Authors submitted 4 experiments in total. The results of these experiments were mixed. The text-only experiment scored second best with a mean average precision (MAP) of 0.2166. In combination with image based [[features]] the MAP dropped to 0.2138. With the addition of thesaurus based query expansion it scored best with a MAP of 0.2195. Without query expansion and with the inclusion of the provided concepts the lowest MAP of 0.2048 was achieved, but there were 23 more relevant documents retrieved than in all 3 other experiments. Furthermore, the retrieval speed and comparison operations for vectors could be speeded up by implementing an interface to the PostgreSQL database. | This paper describes participation at the ImageCLEF [[Wikipedia]] MM task. Authors used Xtrieval framework for the preparation and execution of the experiments. Authors submitted 4 experiments in total. The results of these experiments were mixed. The text-only experiment scored second best with a mean average precision (MAP) of 0.2166. In combination with image based [[features]] the MAP dropped to 0.2138. With the addition of thesaurus based query expansion it scored best with a MAP of 0.2195. Without query expansion and with the inclusion of the provided concepts the lowest MAP of 0.2048 was achieved, but there were 23 more relevant documents retrieved than in all 3 other experiments. Furthermore, the retrieval speed and comparison operations for vectors could be speeded up by implementing an interface to the PostgreSQL database. | ||
Revision as of 22:06, 5 October 2019
Authors | Thomas Wilhelm Jens Kürsten Maximilian Eibl |
|---|---|
Publication date | 2008 |
Links | Original |
The Xtrieval Framework at Clef 2008: Imageclef Wikipedia Mm Task - scientific work related to Wikipedia quality published in 2008, written by Thomas Wilhelm, Jens Kürsten and Maximilian Eibl.
Overview
This paper describes participation at the ImageCLEF Wikipedia MM task. Authors used Xtrieval framework for the preparation and execution of the experiments. Authors submitted 4 experiments in total. The results of these experiments were mixed. The text-only experiment scored second best with a mean average precision (MAP) of 0.2166. In combination with image based features the MAP dropped to 0.2138. With the addition of thesaurus based query expansion it scored best with a MAP of 0.2195. Without query expansion and with the inclusion of the provided concepts the lowest MAP of 0.2048 was achieved, but there were 23 more relevant documents retrieved than in all 3 other experiments. Furthermore, the retrieval speed and comparison operations for vectors could be speeded up by implementing an interface to the PostgreSQL database.
