Discovering Entity Knowledge Bases on the Web

Abstract

Recognition and disambiguation of named entities in text is a knowledge-intensive task. Systems are typically bound by the resources and coverage of a single target knowledge base (KB). In place of a fixed knowledge base, we attempt to infer a set of endpoints which reliably disambiguate entity mentions on the web. We propose a method for discovering web KBs and our preliminary results suggest that web KBs allow linking to entities that can be found on the web, but may not merit a major KB entry.

What if we had no Wikipedia? Domain-independent Term Extraction from a Large News Corpus

“…However, closer to this work is domainspecific ATE, which, given a corpus of documents related to a well defined knowledge domain, aims to extract the salient terms fundamental to this domain. Work on ATE have been instrumental for facilitating downstream tasks such as indexing, mention detection (Usbeck et al, 2015), extracting textual themes (Bawakid, 2015), lexicon construction (Velardi et al, 2008), ontology learning (Brewster et al, 2007), and knowledge organization (Chisholm et al, 2016) -all within the context of a well defined domain.…”