Abstract

In this paper we apply a spreading activation algorithm to the problem of mapping senses between machine readable dictionaries, which is required in order to combined information extracted from them. The algorithm is run over networks automatically constructed from dictionary definition texts. On a sample corpus of sense definitions, our strategy correctly identifies the corresponding homograph in a second dictionary in 97% of the cases, and the correct sense within that homograph in 90% of the cases. This result is a substantial improvement over previously proposed strategies, such as Lesk's method. It also demonstrates that spreading activation strategies, which have rarely been used in computational lexicography, are one means to exploit the full potential of relations implicitly encoded in machine-readable dictionaries. The authors would like to thank Lisa Lassek for her contribution to the work of this project. 2 1. Introduction It is widely recognized that machine re...

Citations