Appendix 1: LT-TTT2 TutorialΒΆ

The geotagging part of the pipeline is built using the Text Tokenisation Tool (LT-TTT2) developed by the Language Technology Group at Edinburgh. This in turn makes use of the LT-XML2 toolkit. Both LT-TTT2 and LT-XML2 are downloadable from the LTG software page.

There is a tutorial on the LTG website explaining how to use the LT-TTT2 suite, and in particular how to write and modify the grammars used by the lxtransduce program which is at the heart of LT-TTT2:

LT-TTT2 tutorial

This tutorial is also included in the documentation provided with the download of LT-TTT2.