Transc&Anno: A Graphical Tool for the Transcription and On-the-Fly Annotation of Handwritten Documents

Submitted by Linda Stokman on 5 November 2019

Blog post written by Nadezda Okinina (Eurac Research, Italy)

On a sunny and warm September afternoon in Warsaw in a comfortable and quiet room the CLARIN Workshop: Transc&Anno: A Graphical Tool for the Transcription and On-the-Fly Annotation of Handwritten Documents took place. 

Ten linguists, all working with learner corpora, participated in the three-hour workshop in which the learner corpora transcription and annotation tool Transc&Anno was presented. 

Transc&Anno is a browser-based transcription and annotation tool. It works with the Mozilla Firefox browser. The tool is very useful, if one has text documents in image format (scanned or photographed documents) and wants to transcribe and annotate them. The transcription and annotation result will be saved to a database in XML format. It will be downloadable in -XML and XHTML format.

After the general overview of the tool was given, the participants had to set up a transcription project containing one learner text, create annotation categories and finally transcribe and annotate the text. They could also experiment with their own texts and download the result of their work in XML or HTML format. Time flew so fast, that some participants decided to continue testing the tool from home. One participant expressed a wish to use the tool for her future projects. 

A thank you goes out to all participants who made the workshop a success! 

This pre-conference workshop of the 5th Learner CorpusResearch conference was organised by Agnieszka Leńko-Szymańska (University of Warsaw), the organiser of the 5th LCR conference and was led by the developer of the tool, Nadezda Okinina (Eurac Research, Italy). The workshop took place on 10 September 2019 in Warsaw. 


Picture: Learner text cropped