Difference between revisions of "Link Detection with Wikipedia"
(New work - Link Detection with Wikipedia) |
(Links) |
||
| Line 1: | Line 1: | ||
| − | '''Link Detection with Wikipedia''' - scientific work related to Wikipedia quality published in 2009, written by Jiyin He. | + | '''Link Detection with Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2009, written by [[Jiyin He]]. |
== Overview == | == Overview == | ||
| − | This paper describes participation in the INEX 2008 Link the Wiki track. Authors focused on the file-to-file task and submitted three runs, which were designed to compare the impact of different features on link generation. For outgoing links, authors introduce the anchor likelihood ratio as an indicator for anchor detection, and explore two types of evidence for target identification, namely, the title field evidence and the topic article content evidence. Authors find that the anchor likelihood ratio is a useful indicator for anchor detection, and that in addition to the title field evidence, re-ranking with the topic article content evidence is effective for improving target identification. For incoming links, authors use exact match and retrieval method with language modeling approach, and find that the exact match approach works best. On top of that, experiment shows that the semantic relatedness between Wikipedia articles also has certain ability to indicate links. | + | This paper describes participation in the INEX 2008 Link the Wiki track. Authors focused on the file-to-file task and submitted three runs, which were designed to compare the impact of different [[features]] on link generation. For outgoing links, authors introduce the anchor likelihood ratio as an indicator for anchor detection, and explore two types of evidence for target identification, namely, the title field evidence and the topic article content evidence. Authors find that the anchor likelihood ratio is a useful indicator for anchor detection, and that in addition to the title field evidence, re-ranking with the topic article content evidence is effective for improving target identification. For incoming links, authors use exact match and retrieval method with language modeling approach, and find that the exact match approach works best. On top of that, experiment shows that the semantic [[relatedness]] between [[Wikipedia]] articles also has certain ability to indicate links. |
Revision as of 22:26, 6 August 2019
Link Detection with Wikipedia - scientific work related to Wikipedia quality published in 2009, written by Jiyin He.
Overview
This paper describes participation in the INEX 2008 Link the Wiki track. Authors focused on the file-to-file task and submitted three runs, which were designed to compare the impact of different features on link generation. For outgoing links, authors introduce the anchor likelihood ratio as an indicator for anchor detection, and explore two types of evidence for target identification, namely, the title field evidence and the topic article content evidence. Authors find that the anchor likelihood ratio is a useful indicator for anchor detection, and that in addition to the title field evidence, re-ranking with the topic article content evidence is effective for improving target identification. For incoming links, authors use exact match and retrieval method with language modeling approach, and find that the exact match approach works best. On top of that, experiment shows that the semantic relatedness between Wikipedia articles also has certain ability to indicate links.
