Download
VLN splits for the map2seq dataset used in the ORAR and VELMA paper:
Link [71 MB]
Citation
@inproceedings {schumann-riezler-2021-map2seq,
title = "Generating Landmark Navigation Instructions from Maps as a Graph-to-Text Problem",
author = "Raphael Schumann and Stefan Riezler",
year = "2021",
publisher = "Association for Computational Linguistics"
}
and
@inproceedings {schumann-riezler-2022-map2seq-vln,
title = "Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas",
author = "Raphael Schumann and Stefan Riezler",
year = "2022",
publisher = "Association for Computational Linguistics"
}