# Dependency Parsing on Valibel corpus (test)

Source: [Dependency Parsing on Valibel corpus (test)](<https://www.sota2.com/research/sota/dependency-parsing-on-valibel-corpus-test>)

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

Data updated: 2026-02-26T05:55:08.810Z

Evaluation of Dependency Parsing performance on the test split of the Valibel corpus, reporting POS, UAS, and LAS 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 | Dependency Parsing |
| Dataset (including any stated split) | Valibel corpus (test) |
| Metric | POS Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [POS Accuracy](<https://www.sota2.com/research/sota/dependency-parsing-on-valibel-corpus-test.md?metric=POS%20Accuracy>): Higher is better; unit: PERCENT.

- [UAS](<https://www.sota2.com/research/sota/dependency-parsing-on-valibel-corpus-test.md?metric=UAS>): Higher is better; unit: PERCENT.

- [LAS](<https://www.sota2.com/research/sota/dependency-parsing-on-valibel-corpus-test.md?metric=LAS>): Higher is better; unit: PERCENT.

## Recorded results

| Method | POS Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| TEXT HOPS | 98.2 | Not recorded | 68fa73ab1e209131cea5dceb |
| TEXT GRAPH | 96.8 | Not recorded | 68fa73ab1e209131cea5dceb |
| TEXT SEQ2LABEL | 94.5 | Not recorded | 68fa73ab1e209131cea5dceb |
| ORACLE GRAPH | 79.8 | Not recorded | 68fa73ab1e209131cea5dceb |
| ORACLE SEQ2LABEL | 78.3 | Not recorded | 68fa73ab1e209131cea5dceb |
| AUDIO SEQ2LABEL | 77.1 | Not recorded | 68fa73ab1e209131cea5dceb |
| AUDIO GRAPH | 77 | Not recorded | 68fa73ab1e209131cea5dceb |
| PIPELINE HOPS | 76.3 | Not recorded | 68fa73ab1e209131cea5dceb |
| PIPELINE SEQ2LABEL | 74.7 | Not recorded | 68fa73ab1e209131cea5dceb |
| PIPELINE GRAPH | 73.5 | Not recorded | 68fa73ab1e209131cea5dceb |

### TEXT HOPS

POS Accuracy: 98.2. Result ID: 699307663a6c314849132ccf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Implementation](<https://github.com/Pupiera/Growing_tree_on_sound>)

Recorded evaluation configuration: {"Input":"Text (Gold)","Parameters":"110M + 100M","Pre-training":"CamemBERT"}. This record does not assert independent reproduction.

### TEXT GRAPH

POS Accuracy: 96.8. Result ID: 699307663a6c314849132cce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Implementation](<https://github.com/Pupiera/Growing_tree_on_sound>)

Recorded evaluation configuration: {"Input":"Text (Gold)","Parameters":"110M + 41.4M","Pre-training":"CamemBERT"}. This record does not assert independent reproduction.

### TEXT SEQ2LABEL

POS Accuracy: 94.5. Result ID: 699307663a6c314849132ccd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

Recorded evaluation configuration: {"Input":"Text (Gold)","Parameters":"110M + 39.2M","Pre-training":"CamemBERT"}. This record does not assert independent reproduction.

### ORACLE GRAPH

POS Accuracy: 79.8. Result ID: 699307663a6c314849132cc9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Implementation](<https://github.com/Pupiera/Growing_tree_on_sound>)

Recorded evaluation configuration: {"Input":"Oracle","Parameters":"315M + 34.9M","Pre-training":"Wav2vec2"}. This record does not assert independent reproduction.

### ORACLE SEQ2LABEL

POS Accuracy: 78.3. Result ID: 699307663a6c314849132cc8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

Recorded evaluation configuration: {"Input":"Oracle","Parameters":"315M + 34.9M","Pre-training":"Wav2vec2"}. This record does not assert independent reproduction.

### AUDIO SEQ2LABEL

POS Accuracy: 77.1. Result ID: 699307663a6c314849132cc6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

Recorded evaluation configuration: {"Input":"Audio","Parameters":"315M + 34.9M","Pre-training":"Wav2vec2"}. This record does not assert independent reproduction.

### AUDIO GRAPH

POS Accuracy: 77. Result ID: 699307663a6c314849132cc7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Implementation](<https://github.com/Pupiera/Growing_tree_on_sound>)

Recorded evaluation configuration: {"Input":"Audio","Parameters":"315M + 34.9M","Pre-training":"Wav2vec2"}. This record does not assert independent reproduction.

### PIPELINE HOPS

POS Accuracy: 76.3. Result ID: 699307663a6c314849132ccc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Implementation](<https://github.com/Pupiera/Growing_tree_on_sound>)

Recorded evaluation configuration: {"Input":"Pipeline","Parameters":"314M + 110M + 100M","Pre-training":"Wav2vec2 + CamemBERT"}. This record does not assert independent reproduction.

### PIPELINE SEQ2LABEL

POS Accuracy: 74.7. Result ID: 699307663a6c314849132cca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

Recorded evaluation configuration: {"Input":"Pipeline","Parameters":"314M + 110M + 39.2M","Pre-training":"Wav2vec2 + CamemBERT"}. This record does not assert independent reproduction.

### PIPELINE GRAPH

POS Accuracy: 73.5. Result ID: 699307663a6c314849132ccb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73ab1e209131cea5dceb.md>)

[Implementation](<https://github.com/Pupiera/Growing_tree_on_sound>)

Recorded evaluation configuration: {"Input":"Pipeline","Parameters":"314M + 110M + 41.4M","Pre-training":"Wav2vec2 + CamemBERT"}. This record does not assert independent reproduction.

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