Authors:Mena B. Morgan andMaurice van Keulen
Affiliation:University of Twente, Netherlands
Keyword(s):Named Entity Disambiguation, Social Media, Twitter.
RelatedOntology Subjects/Areas/Topics:Artificial Intelligence ;Information Extraction ;Knowledge Discovery and Information Retrieval ;Knowledge-Based Systems ;Mining Text and Semi-Structured Data ;Symbolic Systems
Abstract:Social media is a rich source of information. To make use of this information, it is sometimes required to extract and disambiguate named entities. In this paper, we focus on named entity disambiguation (NED) in twitter messages. NED in tweets is challenging in two ways. First, the limited length of Tweet makes it hard to have enough context while many disambiguation techniques depend on it. The second is that many named entities in tweets do not exist in a knowledge base (KB). We share ideas from information retrieval (IR) and NED to propose solutions for both challenges. For the first problem we make use of the gregarious nature of tweets to get enough context needed for disambiguation. For the second problem we look for an alternative home page if there is no Wikipedia page represents the entity. Given a mention, we obtain a list of Wikipedia candidates from YAGO KB in addition to top ranked pages from Google search engine. We use Support Vector Machine (SVM) to rank the candidate pages to find the best representative entities. Experiments conducted on two data sets show better disambiguation results compared with the baselines and a competitor.(More)
Social media is a rich source of information. To make use of this information, it is sometimes required to extract and disambiguate named entities. In this paper, we focus on named entity disambiguation (NED) in twitter messages. NED in tweets is challenging in two ways. First, the limited length of Tweet makes it hard to have enough context while many disambiguation techniques depend on it. The second is that many named entities in tweets do not exist in a knowledge base (KB). We share ideas from information retrieval (IR) and NED to propose solutions for both challenges. For the first problem we make use of the gregarious nature of tweets to get enough context needed for disambiguation. For the second problem we look for an alternative home page if there is no Wikipedia page represents the entity. Given a mention, we obtain a list of Wikipedia candidates from YAGO KB in addition to top ranked pages from Google search engine. We use Support Vector Machine (SVM) to rank the candidate pages to find the best representative entities. Experiments conducted on two data sets show better disambiguation results compared with the baselines and a competitor.