ATC-Anno is an annotation tool for the transcription and semantic annotation of air traffic control utterances. Its most unusual feature is its prediction of semantic annotations based on a finite-state grammar. As long as a transcribed sentence is moderately close to a sentence in the grammar, the annotation found in the grammar can be applied to the transcription.
To demonstrate the workflow and features of the tool, we have created a brief video tutorial. The video has optional subtitles.
- Repository location:
media/tutorial.mp4
- Download the tutorial (you may have to right click and use "Save link as...")
- Watch on Youtube
ATC-Anno is written in Python 2.7 and requires the following additional packages:
Note: The installation on Ubuntu 20.04 or higher is non trivial due to older dependencies. We therefore have a build on a VM, which can be accessed here: https://unisaarlandde-my.sharepoint.com/:f:/g/personal/s9algawl_uni-saarland_de/EomjdHvZ0gtBtrr8-s36C3QBlbV_v42HmGk9exmiRiOWIQ?e=Z7btQP
To access the Get XML feature, you need to provide a finite-state grammar that uses the OpenFST format.
The default location for the grammar is data/grammars/default.fst
The conversion of airline names to callsign representations (e.g. "Lufthansa" to "DLH") is based on the airline dictionary found at data/airlines/callsigns.txt
. You can expand the file to include all airlines that occur in your grammar.
This software is published under an MIT License.
If you use it in your research or work, please cite the following publication:
Schulder, Marc and O'Mahony, Johannah and Bakanouski, Yury and Klakow, Dietrich (2020). "ATC-Anno: Semantic Annotation for Air Traffic Control with Assistive Auto-Annotation". Proceedings of the 12th Conference on Language Resources and Evaluation (LREC), pages 6375–6380, Marseille, France, 13 May 2020.
@InProceedings{schulder2020atcAnno,
author = {Schulder, Marc and O'Mahony, Johannah and Bakanouski, Yury and Klakow, Dietrich},
title = {{ATC-Anno}: Semantic Annotation for Air Traffic Control with Assistive Auto-Annotation},
booktitle = {Proceedings of the Twelfth International Conference on Language Resources and Evaluation (LREC 2020)},
year = {2020},
month = {May},
address = {Marseille, France},
publisher = {European Language Resources Association (ELRA)},
}