Constructing an Annotated Resource for Part-Of-Speech Tagging of Mishnaic Hebrew

Abstract

This paper introduces the research in Part-Of-Speech tagging of mishnaic Hebrew carried out within the Babylonian Talmud Translation Project. Since no tagged resource was available to train a stochastic POS tagger, a portion of the Mishna of the Babylonian Talmud has been morphologically annotated using an ad hoc developed tool connected with the DB containing the talmudic text being translated. The final aim of this research is to add a linguistic support to the Translation Memory System of Traduco, the Computer-Assisted Translation tool developed and used within the Project.