Abstract | ||
---|---|---|
Named Entity Linking (NEL) in microblogs is a challenging task due to the use of cryptic abbreviations, insufficient contextual information, and the time-varying importance of entities. We propose three techniques to target these challenges: Mention Normalization, Contextual Enrichment, and Temporal Entity Importance. By combining these novel techniques, we achieve 13% improvement in precision over a state-of-the-art NEL tool. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1145/2663712.2666185 | ESAIR |
Keywords | Field | DocType |
semantic annotation,social media,general,information extraction,named entity linking | Entity linking,Contextual information,Social media,Normalization (statistics),Information retrieval,Computer science,Microblogging,Social stream,Weak entity,Information extraction | Conference |
Citations | PageRank | References |
6 | 0.48 | 17 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yusra Ibrahim | 1 | 22 | 3.10 |
Mohamed Amir Yosef | 2 | 499 | 18.42 |
Gerhard Weikum | 3 | 12710 | 2146.01 |