Datasets › map2seq

map2seq

Introduced by Raphael Schumann et al. in Generating Landmark Navigation Instructions from Maps as a Graph-to-Text Problem30 Dec 2020 archive 2025-07-28

7,672 human written natural language navigation instructions for routes in OpenStreetMap with a focus on visual landmarks. Validated in Street View.

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

3 shown of 3 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 5. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
FLAME: Learning to Navigate with Multimodal LLM in Urban Environments 1 1 20 Aug 2024 ran 6 of 7 samples (1 unverified)
Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas 1 4 25 Mar 2022 ran 0 of 4 samples (4 unverified)
Generating Landmark Navigation Instructions from Maps as a Graph-to-Text Problem 0 1 30 Dec 2020 not harvested

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

No licence recorded in the archive. Absence here is not a statement about the dataset's terms.

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • map2seq

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections