QUEST: Query Expansion Using Synonyms over Time
A particular problem of searching news archives with named entities is that they are very dynamic in appearance compared to other vocabulary terms, and synonym relationships between terms change with time. In previous work, we proposed an approach to extracting time-based synonyms of named entities from the whole history of Wikipedia. In this paper, we present QUEST (Query Expansion using Synonyms over Time), a system that exploits time-based synonyms in searching news archives. The system takes as input a named entity query, and automatically determines time-based synonyms for a given query wrt. time criteria. Query expansion using the determined synonyms can be employed in order to improve the retrieval effectiveness.
KeywordsQuery Expansion Query Keyword Retrieval Effectiveness Anchor Text Vocabulary Term
- 1.Berberich, K., Bedathur, S.J., Neumann, T., Weikum, G.: A time machine for text search. In: Proceedings of SIGIR 2007 (2007)Google Scholar
- 2.Bøhn, C., Nørvåg, K.: Extracting named entities and synonyms from wikipedia. In: Proceedings of AINA 2010 (2010)Google Scholar
- 3.Bunescu, R.C., Paşca, M.: Using encyclopedic knowledge for named entity disambiguation. In: Proceedings of EACL 2006 (2006)Google Scholar
- 4.Kanhabua, N., Nørvåg, K.: Exploiting time-based synonyms in searching document archives. In: Proceedings of JCDL 2010 (2010)Google Scholar
- 5.Kanhabua, N., Nørvåg, K.: Determining Time of Queries for Re-ranking Search Results. In: Proceedings of ECDL 2010 (2010)Google Scholar