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"
}