Reconstructing the Diachronic Morphology of Romanian from Dictionary Citations

摘要

This work represents a first step in the direction of reconstructing a diachronic morphology for Romanian. The main resource used in this task is the digital version of the Romanian Language Thesaurus Dictionary (eDTLR). This resource offers various usage examples for its entries, citations extracted from old and modem Romanian texts. The concept of "word deformation" is introduced and classified into more categories. The research conducted aims at detecting one type of such deformations occurring in the citations -changes only in the root of the old form words, without the migration to another paradigm. An algorithm is presented which automatically infers old root forms, and which is based on a paradigmatic data model of the current Romanian morphology. Having the inferred roots and the paradigms that they are part of, old flexion forms of the words can be deduced. Even more, by exploiting the chronology of the citations, the inferred old word forms can be framed in certain periods of time, finally configuring an important linguistic resource for researchers interested in the evolution of the Romanian language.