String Similarity Measures for Template Extraction

String similarity is a frequently used technique in various Language Technology applications. However, the use of a certain similarity measure is task specific.

In my talk, I will describe how similarity measures can be used for template extraction.

Results of a set of experiments are going to be described and discussed. The main goal of the experiments was to detect the most appropriate similarity measure which can be applied for retrieving candidate sentences for translation templates to be used in an EBMT system. A similarity matrix was built using the result of the best similarity measure.

The advantage of such an approach is that it is based entirely on surface forms, therefore being independent from linguistic resources.

SLIDES

-- GavrilaMonica -- 05 Jun 2007
 
This site is powered by FoswikiCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Foswiki? Send feedback