# Navigation Instruction Generation on Partially seen routes 700 instances (test)

Source: [Navigation Instruction Generation on Partially seen routes 700 instances (test)](<https://www.sota2.com/research/sota/navigation-instruction-generation-on-partially-seen-routes-700-instances-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:48:35.222Z

Evaluation of Navigation Instruction Generation performance on the test split of the Partially Seen Routes 700 instances dataset, measured using metrics including BLEU, Length (Len.), Landmark accuracy (Landm.), SDTW, Success Rate (SR), and SNT.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Navigation Instruction Generation |
| Dataset (including any stated split) | Partially seen routes 700 instances (test) |
| Metric | Length (Len.) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Length (Len.)](<https://www.sota2.com/research/sota/navigation-instruction-generation-on-partially-seen-routes-700-instances-test.md?metric=Length%20(Len.)>): Higher is better; unit: SCALAR.

- [BLEU](<https://www.sota2.com/research/sota/navigation-instruction-generation-on-partially-seen-routes-700-instances-test.md?metric=BLEU>): Higher is better; unit: SCALAR.

- [Landmark Accuracy (Landm.)](<https://www.sota2.com/research/sota/navigation-instruction-generation-on-partially-seen-routes-700-instances-test.md?metric=Landmark%20Accuracy%20(Landm.)>): Higher is better; unit: SCALAR.

- [SDTW](<https://www.sota2.com/research/sota/navigation-instruction-generation-on-partially-seen-routes-700-instances-test.md?metric=SDTW>): Lower is better; unit: SCALAR.

- [Success Rate (SR)](<https://www.sota2.com/research/sota/navigation-instruction-generation-on-partially-seen-routes-700-instances-test.md?metric=Success%20Rate%20(SR)>): Higher is better; unit: PERCENT.

- [SNT](<https://www.sota2.com/research/sota/navigation-instruction-generation-on-partially-seen-routes-700-instances-test.md?metric=SNT>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Length (Len.) | Result date | Report paper |
| --- | --- | --- | --- |
| reference | 53.5 | Not recorded | 68fa6a011e209131cea2552c |
| g2t+pretrain | 53 | Not recorded | 68fa6a011e209131cea2552c |

### reference

Length (Len.): 53.5. Result ID: 698dfcddffc3901de099f628.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a011e209131cea2552c.md>)

Recorded evaluation configuration: {"Type":"Human Reference"}. This record does not assert independent reproduction.

### g2t+pretrain

Length (Len.): 53. Result ID: 698dfcddffc3901de099f629.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a011e209131cea2552c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a011e209131cea2552c.md>)

[Implementation](<https://www.sota2.com/www.cl.uni-heidelberg.de/statnlpgroup/map2seq/>)

Recorded evaluation configuration: {"Pre-training":true}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.