# Semantic Role Classification on FrameNet 1.7 (test)

Source: [Semantic Role Classification on FrameNet 1.7 (test)](<https://www.sota2.com/research/sota/semantic-role-classification-on-framenet-1-7-test>)

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

Data updated: 2026-04-23T10:48:21.372Z

Evaluation of Semantic Role Classification performance on the test set of the FrameNet 1.7 dataset, typically measured using Accuracy.

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 | Semantic Role Classification |
| Dataset (including any stated split) | FrameNet 1.7 (test) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/semantic-role-classification-on-framenet-1-7-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [micro-F1](<https://www.sota2.com/research/sota/semantic-role-classification-on-framenet-1-7-test.md?metric=micro-F1>): Higher is better; unit: PERCENT.

- [macro-F1](<https://www.sota2.com/research/sota/semantic-role-classification-on-framenet-1-7-test.md?metric=macro-F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| An et al. (2023) | 89.9 | Not recorded | 69e9a78355a3c32af89f6fd8 |
| RoBERTa SEP | 86.1 | Not recorded | 69e9a78355a3c32af89f6fd8 |
| RoBERTa MASK | 80.6 | Not recorded | 69e9a78355a3c32af89f6fd8 |
| Claude Sonnet 4.0 | 73.6 | Not recorded | 69e9a78355a3c32af89f6fd8 |
| analogical transfer | 59.35 | Not recorded | 69c0c8e40636e5bf4afc3a08 |
| Swayamdipta et al. | 58.46 | Not recorded | 69c0c8e40636e5bf4afc3a08 |
| Gemini 2.5 | 50.8 | Not recorded | 69e9a78355a3c32af89f6fd8 |

### An et al. (2023)

Accuracy: 89.9. Result ID: 69e9f8da47f34ce924d1f0ca.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78355a3c32af89f6fd8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e91e209131cea4df04.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RoBERTa SEP

Accuracy: 86.1. Result ID: 69e9f8da47f34ce924d1f0c7.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78355a3c32af89f6fd8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e9a78355a3c32af89f6fd8.md>)

Recorded evaluation configuration: {"Input style":"SEP","Evaluation protocol":"fine-tuned"}. This record does not assert independent reproduction.

### RoBERTa MASK

Accuracy: 80.6. Result ID: 69e9f8da47f34ce924d1f0c6.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78355a3c32af89f6fd8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e9a78355a3c32af89f6fd8.md>)

Recorded evaluation configuration: {"Input style":"MASK","Evaluation protocol":"fine-tuned"}. This record does not assert independent reproduction.

### Claude Sonnet 4.0

Accuracy: 73.6. Result ID: 69e9f8da47f34ce924d1f0c9.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78355a3c32af89f6fd8.md>)

Recorded evaluation configuration: {"Evaluation protocol":"zero-shot"}. This record does not assert independent reproduction.

### analogical transfer

Accuracy: 59.35. Result ID: 69c1237847f34ce924a99bfe.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8e40636e5bf4afc3a08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c0c8e40636e5bf4afc3a08.md>)

Recorded evaluation configuration: {"Frame id.":"gold","Arg id.":"Swayamdipta et al.","SR cl.":"Ours"}. This record does not assert independent reproduction.

### Swayamdipta et al.

Accuracy: 58.46. Result ID: 69c1237847f34ce924a99bfd.

[Reporting paper](<https://www.sota2.com/research/paper/69c0c8e40636e5bf4afc3a08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63711e209131ce9fee0b.md>)

Recorded evaluation configuration: {"Frame id.":"gold","Arg id.":"Swayamdipta et al.","SR cl.":"Swayamdipta et al."}. This record does not assert independent reproduction.

### Gemini 2.5

Accuracy: 50.8. Result ID: 69e9f8da47f34ce924d1f0c8.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78355a3c32af89f6fd8.md>)

Recorded evaluation configuration: {"Evaluation protocol":"zero-shot"}. This record does not assert independent reproduction.

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