Supple equality of terms: definition and evaluation

摘要

To recognize a complex term is a difficult task because of the possible variations: singular or plural, verbal or nominal form, etc. We present the supple equality of terms which determines whether two terms can be considered as variations one from the each other. This operator is based on the minimum editing distance between two strings. It does not need big amounts of linguistic resources except a list of functional words. We evaluate the performances of the algorithm by comparison with the results of FASTR, a system dedicated to the recognition of complex terms, on an English corpus. This system is based on linguistic treatments and uses linguistic resources. We found a rate of recall of 76,6% and a rate of precision of 96,3%. We outline that the supple-equality operator is based on quantitative treatment and can be easily adapted to different non agglutinative language. Developed for French, it is evaluated in this paper on English.