Analysing Entity Context in Multilingual Wikipedia to Support Entity-Centric Retrieval Applications
Representation of influential entities, such as famous people and multinational corporations, on the Web can vary across languages, reflecting language-specific entity aspects as well as divergent views on these entities in different communities. A system
- PDF / 234,741 Bytes
- 12 Pages / 439.37 x 666.142 pts Page_size
- 118 Downloads / 181 Views
2
Department of Computer Science, University of Warwick, Coventry, UK {Yiwei.Zhou,A.I.Cristea}@warwick.ac.uk L3S Research Center and Leibniz Universit¨ at Hannover, Hannover, Germany [email protected]
Abstract. Representation of influential entities, such as famous people and multinational corporations, on the Web can vary across languages, reflecting language-specific entity aspects as well as divergent views on these entities in different communities. A systematic analysis of languagespecific entity contexts can provide a better overview of the existing aspects and support entity-centric retrieval applications over multilingual Web data. An important source of cross-lingual information about influential entities is Wikipedia — an online community-created encyclopaedia — containing more than 280 language editions. In this paper we focus on the extraction and analysis of the language-specific entity contexts from different Wikipedia language editions over multilingual data. We discuss alternative ways such contexts can be built, including graph-based and article-based contexts. Furthermore, we analyse the similarities and the differences in these contexts in a case study including 80 entities and five Wikipedia language editions.
1
Introduction
Entities with world-wide influence, such as famous people and multinational corporations, can be represented differently in the news, in Web pages and in other documents originating from various cultures and written in different languages. These various representations can reflect language-specific entity aspects as well as views on the entity in different communities. In order to enable a better representation of the language-specific entity aspects in the information retrieval systems, methods to systematically identify language-specific entity contexts — i.e. the aspects in the entity descriptions typical to a specific language — need to be developed. For example, in the English news, the entity “Angela Merkel”, the Chancellor of Germany, is often associated with US and UK politicians such as Barack Obama, or David Cameron. Also, recent discussions of the European importance, such as Greek financial situation are included. On the contrary, although the German pages also include European topics, they frequently focus on the c Springer International Publishing Switzerland 2015 J. Cardoso et al. (Eds.): KEYWORD 2015, LNCS 9398, pp. 197–208, 2015. DOI: 10.1007/978-3-319-27932-9 17
198
Y. Zhou et al.
domestic political topics, featuring discussions of political parties in Germany, scandals arising around German politicians, local elections, finances and other country-specific topics. For another example, in case of the multinational companies like GlaxoSmithKline (a British healthcare company), the aspects related to the local activities are prevalent in the reporting in specific languages. These aspects range from the effectiveness of the various vaccines developed by the company to the sports events sponsored by this company in a specific country. The knowledge of such language-specific aspe
Data Loading...
