Abbreviations are very common and are widely used in both written and spoken language. However, they are not always explicitly defined and in many cases they are ambiguous. In this research, we present a process that attempts to solve the problem of abbreviation ambiguity. Various features have been explored, including context-related methods and statistical methods. The application domain is Jewish Law documents written in Hebrew, which are known to be rich in ambiguous abbreviations. Various variants of the one sense per discourse hypothesis (by varying the scope of discourse) have been implemented. Several common machine learning methods have been tested to find a successful integration of these variants. The best results have been achieved by SVM, with 96.09% accuracy.
展开▼
