# Data-to-text generation on WebNLG 2017 (seen)

Source: [Data-to-text generation on WebNLG 2017 (seen)](<https://www.sota2.com/research/sota/data-to-text-generation-on-webnlg-2017-seen>)

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

Data updated: 2026-02-26T05:36:49.461Z

Evaluation of data-to-text generation performance on the seen split of the WebNLG 2017 dataset, assessed using standard sequence generation metrics like BLEU, METEOR, and TER.

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 | Data-to-text generation |
| Dataset (including any stated split) | WebNLG 2017 (seen) |
| Metric | BLEU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [BLEU](<https://www.sota2.com/research/sota/data-to-text-generation-on-webnlg-2017-seen.md?metric=BLEU>): Higher is better; unit: PERCENT.

- [TER](<https://www.sota2.com/research/sota/data-to-text-generation-on-webnlg-2017-seen.md?metric=TER>): Lower is better; unit: SCALAR.

- [METEOR](<https://www.sota2.com/research/sota/data-to-text-generation-on-webnlg-2017-seen.md?metric=METEOR>): Higher is better; unit: SCALAR.

## Recorded results

| Method | BLEU | Result date | Report paper |
| --- | --- | --- | --- |
| T5 | 64.7 | Not recorded | 68fa6a271e209131cea2665d |
| PlanEnc | 64.42 | Not recorded | 68fa6a271e209131cea2665d |
| ADAPT | 60.59 | Not recorded | 68fa6a271e209131cea2665d |
| AGGGEN | 58.74 | Not recorded | 68fa6a271e209131cea2665d |
| Transformer | 58.47 | Not recorded | 68fa6a271e209131cea2665d |
| AGGGEN-CD | 55.3 | Not recorded | 68fa6a271e209131cea2665d |
| AGGGEN-AG | 52.17 | Not recorded | 68fa6a271e209131cea2665d |
| TILB-PIPE | 44.34 | Not recorded | 68fa6a271e209131cea2665d |

### T5

BLEU: 64.7. Result ID: 698e18bbffc3901de09ac535.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5b1e209131cea27b18.md>)

Recorded evaluation configuration: {"source":"previous work"}. This record does not assert independent reproduction.

### PlanEnc

BLEU: 64.42. Result ID: 698e18bbffc3901de09ac536.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

Recorded evaluation configuration: {"source":"previous work"}. This record does not assert independent reproduction.

### ADAPT

BLEU: 60.59. Result ID: 698e18bbffc3901de09ac537.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

Recorded evaluation configuration: {"source":"previous work"}. This record does not assert independent reproduction.

### AGGGEN

BLEU: 58.74. Result ID: 698e18bbffc3901de09ac53a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Implementation](<https://github.com/XinnuoXu/AggGen>)

Recorded evaluation configuration: {"implementation":"ours"}. This record does not assert independent reproduction.

### Transformer

BLEU: 58.47. Result ID: 698e18bbffc3901de09ac539.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"implementation":"ours (baseline)"}. This record does not assert independent reproduction.

### AGGGEN-CD

BLEU: 55.3. Result ID: 698e18bbffc3901de09ac53b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Implementation](<https://github.com/XinnuoXu/AggGen>)

Recorded evaluation configuration: {"implementation":"ours","variant":"CD"}. This record does not assert independent reproduction.

### AGGGEN-AG

BLEU: 52.17. Result ID: 698e18bbffc3901de09ac53c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

[Implementation](<https://github.com/XinnuoXu/AggGen>)

Recorded evaluation configuration: {"implementation":"ours","variant":"AG"}. This record does not assert independent reproduction.

### TILB-PIPE

BLEU: 44.34. Result ID: 698e18bbffc3901de09ac538.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a271e209131cea2665d.md>)

Recorded evaluation configuration: {"source":"previous work"}. This record does not assert independent reproduction.

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