TRACEsoftTools: Software Tools for Contrastive Analysis of Texts in Parallel Bilingual Corpus

The TRACEsoftTools project is one of the four subprojects that compose the TRACE project. TRACE stands for "Translation under Censorship", and involves the study of translation and censorship in Spain of different textual genres in different language combinations, from 1939 to 1985. TRACE performs intensive use of XML markup, TEI, translations memories (TMX), in order to build and exploit multilingual parallel aligned corpora.

TRACEsoftTools involves the development of computing techniques and tools for contrastive textual analysis and is twofold: First, it supports the other TRACE subprojects, by developing efficient algorithmic techniques and providing practical tools for parallel text alignment and automated markup. On the other hand, it feeds from TRACE parallel corpora and metadata databases to experiment in the application of data mining and text mining techniques.