# Dialogue act prediction on DSTC2

Source: [Dialogue act prediction on DSTC2](<https://www.sota2.com/research/sota/dialogue-act-prediction-on-dstc2>)

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

Data updated: 2026-02-27T08:21:54.298Z

Evaluation of Dialogue act prediction performance on the DSTC2 dataset using micro-F1 and macro-F1 metrics.

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 | Dialogue act prediction |
| Dataset (including any stated split) | DSTC2 |
| Metric | Micro-F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Micro-F1 Score](<https://www.sota2.com/research/sota/dialogue-act-prediction-on-dstc2.md?metric=Micro-F1%20Score>): Higher is better; unit: PERCENT.

- [Macro-F1 Score](<https://www.sota2.com/research/sota/dialogue-act-prediction-on-dstc2.md?metric=Macro-F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Micro-F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| FutureTOD | 94.6 | Not recorded | 68fa6fcd1e209131cea47827 |
| DialoGPT | 93.8 | Not recorded | 68fa6fcd1e209131cea47827 |
| TOD-BERT | 93.8 | Not recorded | 68fa6fcd1e209131cea47827 |
| DSE | 92.6 | Not recorded | 68fa6fcd1e209131cea47827 |
| BERT | 92.3 | Not recorded | 68fa6fcd1e209131cea47827 |
| SimCSE | 91.5 | Not recorded | 68fa6fcd1e209131cea47827 |
| BERT-mlm | 90.9 | Not recorded | 68fa6fcd1e209131cea47827 |

### FutureTOD

Micro-F1 Score: 94.6. Result ID: 69a1540d35dfcabb00e64d49.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea47827.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea47827.md>)

[Implementation](<https://github.com/Zeng-WH/FutureTOD>)

Recorded evaluation configuration: {"Data Scale":"Full"}. This record does not assert independent reproduction.

### DialoGPT

Micro-F1 Score: 93.8. Result ID: 69a1540d35dfcabb00e64d44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea47827.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67771e209131cea16854.md>)

Recorded evaluation configuration: {"Data Scale":"Full"}. This record does not assert independent reproduction.

### TOD-BERT

Micro-F1 Score: 93.8. Result ID: 69a1540d35dfcabb00e64d47.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea47827.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa686d1e209131cea1c191.md>)

Recorded evaluation configuration: {"Data Scale":"Full"}. This record does not assert independent reproduction.

### DSE

Micro-F1 Score: 92.6. Result ID: 69a1540d35dfcabb00e64d48.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea47827.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d121e209131cea376d3.md>)

Recorded evaluation configuration: {"Data Scale":"Full"}. This record does not assert independent reproduction.

### BERT

Micro-F1 Score: 92.3. Result ID: 69a1540d35dfcabb00e64d43.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea47827.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Data Scale":"Full"}. This record does not assert independent reproduction.

### SimCSE

Micro-F1 Score: 91.5. Result ID: 69a1540d35dfcabb00e64d46.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea47827.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c9c1e209131cea34e2c.md>)

[Implementation](<https://github.com/princeton-nlp/SimCSE>)

Recorded evaluation configuration: {"Data Scale":"Full"}. This record does not assert independent reproduction.

### BERT-mlm

Micro-F1 Score: 90.9. Result ID: 69a1540d35dfcabb00e64d45.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fcd1e209131cea47827.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Data Scale":"Full"}. This record does not assert independent reproduction.

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