Difference between revisions of "Combining Mention Context and Hyperlinks from Wikipedia for Named Entity Disambiguation"
(New study: Combining Mention Context and Hyperlinks from Wikipedia for Named Entity Disambiguation) |
(+ wikilinks) |
||
| Line 1: | Line 1: | ||
| − | '''Combining Mention Context and Hyperlinks from Wikipedia for Named Entity Disambiguation''' - scientific work related to Wikipedia quality published in 2015, written by Ander Barrena, Aitor Soroa and Eneko Agirre. | + | '''Combining Mention Context and Hyperlinks from Wikipedia for Named Entity Disambiguation''' - scientific work related to [[Wikipedia quality]] published in 2015, written by [[Ander Barrena]], [[Aitor Soroa]] and [[Eneko Agirre]]. |
== Overview == | == Overview == | ||
| − | Named entity disambiguation is the task of linking entity mentions to their intended referent, as represented in a Knowledge Base, usually derived from Wikipedia. In this paper, authors combine local mention context and global hyperlink structure from Wikipedia in a probabilistic framework. Authors test method in eight datasets, improving the state-of-the-art results in five. Authors results show that the two models of context, namely, words in the context and hyperlink pathways to other entities in the context, are complementary. Authors results are not tuned to any of the datasets, showing that it is robust to out-of-domain scenarios, and that further improvements are possible. | + | Named entity disambiguation is the task of linking entity mentions to their intended referent, as represented in a Knowledge Base, usually derived from [[Wikipedia]]. In this paper, authors combine local mention context and global hyperlink structure from Wikipedia in a probabilistic framework. Authors test method in eight datasets, improving the state-of-the-art results in five. Authors results show that the two models of context, namely, words in the context and hyperlink pathways to other entities in the context, are complementary. Authors results are not tuned to any of the datasets, showing that it is robust to out-of-domain scenarios, and that further improvements are possible. |
Revision as of 11:28, 8 September 2019
Combining Mention Context and Hyperlinks from Wikipedia for Named Entity Disambiguation - scientific work related to Wikipedia quality published in 2015, written by Ander Barrena, Aitor Soroa and Eneko Agirre.
Overview
Named entity disambiguation is the task of linking entity mentions to their intended referent, as represented in a Knowledge Base, usually derived from Wikipedia. In this paper, authors combine local mention context and global hyperlink structure from Wikipedia in a probabilistic framework. Authors test method in eight datasets, improving the state-of-the-art results in five. Authors results show that the two models of context, namely, words in the context and hyperlink pathways to other entities in the context, are complementary. Authors results are not tuned to any of the datasets, showing that it is robust to out-of-domain scenarios, and that further improvements are possible.
