Enriching a Multilingual Terminology Exploiting Parallel Texts: An Experiment on the Italian Translation of the Babylonian Talmud

Parallel texts can represent an extremely useful source of information in a number of text and linguistic processing tasks. In this work we show an experiment conducted on the Italian translation of the Babylonian Talmud, a text we have analyzed and processed to support in the construction of a multilingual Hebrew/Aramaic/Italian terminological resource. The approach we adopted comprised: i) the TEI encoding of the text, ii) the automatic extraction of the Italian terms, iii) the addition of Hebrew/Aramaic terms via word-by-word alignment, iv) the revision of the obtained results.