# Dialogue Discourse Parsing on STAC in-domain (test)

Source: [Dialogue Discourse Parsing on STAC in-domain (test)](<https://www.sota2.com/research/sota/dialogue-discourse-parsing-on-stac-in-domain-test>)

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

Data updated: 2026-02-26T06:07:48.265Z

Evaluation of Dialogue Discourse Parsing performance on the in-domain test split of the STAC dataset, reporting Unlabeled Attachment Score (UAS) and Labeled Attachment Score (LAS).

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 Discourse Parsing |
| Dataset (including any stated split) | STAC in-domain (test) |
| Metric | UAS |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [UAS](<https://www.sota2.com/research/sota/dialogue-discourse-parsing-on-stac-in-domain-test.md?metric=UAS>): Higher is better; unit: PERCENT.

- [LAS](<https://www.sota2.com/research/sota/dialogue-discourse-parsing-on-stac-in-domain-test.md?metric=LAS>): Higher is better; unit: PERCENT.

## Recorded results

| Method | UAS | Result date | Report paper |
| --- | --- | --- | --- |
| Structured Dialogue Discourse Parsing | 74.4 | Not recorded | 68fa6fde1e209131cea47c6e |
| Struct-Aware | 73.4 | Not recorded | 68fa6fde1e209131cea47c6e |
| Deep-Seq. | 73.2 | Not recorded | 68fa6fde1e209131cea47c6e |
| Hierarchical | 73.1 | Not recorded | 68fa6fde1e209131cea47c6e |
| MST | 69.6 | Not recorded | 68fa6fde1e209131cea47c6e |
| ILP | 69 | Not recorded | 68fa6fde1e209131cea47c6e |

### Structured Dialogue Discourse Parsing

UAS: 74.4. Result ID: 6990efde3a6c314849046d6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c6e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c6e.md>)

[Implementation](<https://github.com/chijames/structured_dialogue_discourse_parsing>)

Recorded evaluation configuration: {"runs":"average of three","speaker\_information":"not modeled explicitly"}. This record does not assert independent reproduction.

### Struct-Aware

UAS: 73.4. Result ID: 6990efde3a6c314849046d6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c6e.md>)

Recorded evaluation configuration: {"runs":"average of three","speaker\_information":"used"}. This record does not assert independent reproduction.

### Deep-Seq.

UAS: 73.2. Result ID: 6990efde3a6c314849046d6c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c6e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa651a1e209131cea08555.md>)

Recorded evaluation configuration: {"runs":"average of three","speaker\_information":"used"}. This record does not assert independent reproduction.

### Hierarchical

UAS: 73.1. Result ID: 6990efde3a6c314849046d6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c6e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6afd1e209131cea2b93b.md>)

Recorded evaluation configuration: {"runs":"average of three","speaker\_information":"used"}. This record does not assert independent reproduction.

### MST

UAS: 69.6. Result ID: 6990efde3a6c314849046d6a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c6e.md>)

Recorded evaluation configuration: {"runs":"average of three","speaker\_information":"used"}. This record does not assert independent reproduction.

### ILP

UAS: 69. Result ID: 6990efde3a6c314849046d6b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fde1e209131cea47c6e.md>)

Recorded evaluation configuration: {"runs":"average of three","speaker\_information":"used"}. This record does not assert independent reproduction.

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