Show simple item record

dc.contributor.authorWang, Han
dc.contributor.authorZheng, Jin
dc.contributor.authorMa, Xiaogang
dc.contributor.authorFox, Peter
dc.contributor.authorJi, Heng
dc.date.accessioned2022-02-18T02:34:27Z
dc.date.available2022-02-18T02:34:27Z
dc.date.issued2015-09-17
dc.identifier.other76
dc.identifier.urihttp://archive.tw.rpi.edu/media/2015/08/11/db82/hanwang_emnlp_2015.pdf
dc.identifier.urihttps://hdl.handle.net/20.500.13015/4478
dc.description.abstractLinking named mentions detected in a source document to an existing knowl- edge base provides disambiguated entity referents for the mentions. This allows better document analysis, knowledge ex- traction and knowledge base population. Most of the previous research extensively exploited the linguistic features of the source documents in a supervised or semi- supervised way. These systems there- fore cannot be easily applied to a new language or domain. In this paper, we present a novel unsupervised algorithm named Quantified Collective Validation that avoids excessive linguistic analysis on the source documents and fully lever- ages the knowledge base structure for the entity linking task. We show our ap- proach achieves state-of-the-art English entity linking performance and demon- strate successful deployment in a new lan- guage (Chinese) and two new domains (Biomedical and Earth Science).
dc.titleLanguage and Domain Independent Entity Linking with Quantified Collective Validation


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record