Using a semantic tagger as dictionary search tool

Abstract

The USAS semantic tagger is a powerful language technology tool that has proven to be very effective in various applications such as content analysis, discourse analysis and information extraction. In the Benedict project, we intend to use the semantic taggers for the English and Finnish languages as search tools in electronic dictionaries, thereby enabling users to carry out context-sensitive dictionary searches. The aim of this paper is to envisage ways in which a semantic tagger can help users find the ”right ” answer from a dictionary (i.e. the answer that the user needs). We begin with a brief introduction of the semantic taggers for the English and Finnish languages. Thereafter, we focus on the presentation of the context-sensitive dictionary look-up, and show how the dictionary software will be able (i) to determine the correct sense in the context at hand, and (ii) to highlight that sense for the user. The new search tool will be commercially available in the Benedict software. 1