# Universal Dependency Parsing on SpokeBench Discourse+ v1 (test)

Source: [Universal Dependency Parsing on SpokeBench Discourse+ v1 (test)](<https://www.sota2.com/research/sota/universal-dependency-parsing-on-spokebench-discourse-plus-v1-test>)

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

Data updated: 2026-02-26T05:46:48.383Z

Evaluation of Universal Dependency Parsing performance on the test split of the SpokeBench Discourse+ v1 dataset, reporting metrics including ID, UPOS, HEAD, DEPREL, and Final scores.

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 | Universal Dependency Parsing |
| Dataset (including any stated split) | SpokeBench Discourse+ v1 (test) |
| Metric | ID Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [ID Accuracy](<https://www.sota2.com/research/sota/universal-dependency-parsing-on-spokebench-discourse-plus-v1-test.md?metric=ID%20Accuracy>): Higher is better; unit: PERCENT.

- [UPOS Accuracy](<https://www.sota2.com/research/sota/universal-dependency-parsing-on-spokebench-discourse-plus-v1-test.md?metric=UPOS%20Accuracy>): Higher is better; unit: PERCENT.

- [HEAD Accuracy](<https://www.sota2.com/research/sota/universal-dependency-parsing-on-spokebench-discourse-plus-v1-test.md?metric=HEAD%20Accuracy>): Higher is better; unit: PERCENT.

- [DEPREL Accuracy](<https://www.sota2.com/research/sota/universal-dependency-parsing-on-spokebench-discourse-plus-v1-test.md?metric=DEPREL%20Accuracy>): Higher is better; unit: PERCENT.

- [Final Score](<https://www.sota2.com/research/sota/universal-dependency-parsing-on-spokebench-discourse-plus-v1-test.md?metric=Final%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ID Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| BiLingua Parser | 71.6 | Not recorded | 69896a2fc97a0b3e3b5dc602 |
| DECAP | 60.4 | Not recorded | 69896a2fc97a0b3e3b5dc602 |
| Bilingual Traditional Parser | 29.4 | Not recorded | 69896a2fc97a0b3e3b5dc602 |

### BiLingua Parser

ID Accuracy: 71.6. Result ID: 699646185698665ec489f2a5.

[Reporting paper](<https://www.sota2.com/research/paper/69896a2fc97a0b3e3b5dc602.md>)

Recorded evaluation configuration: {"Type":"LLM-based pipeline"}. This record does not assert independent reproduction.

### DECAP

ID Accuracy: 60.4. Result ID: 699646185698665ec489f2a6.

[Reporting paper](<https://www.sota2.com/research/paper/69896a2fc97a0b3e3b5dc602.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69896a2fc97a0b3e3b5dc602.md>)

Recorded evaluation configuration: {"Backbone":"GPT-4.1"}. This record does not assert independent reproduction.

### Bilingual Traditional Parser

ID Accuracy: 29.4. Result ID: 699646185698665ec489f2a4.

[Reporting paper](<https://www.sota2.com/research/paper/69896a2fc97a0b3e3b5dc602.md>)

Recorded evaluation configuration: {"Backbone":"Stanza"}. This record does not assert independent reproduction.

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