# Aspect Sentiment Classification on Restaurant SemEval 2016 (test)

Source: [Aspect Sentiment Classification on Restaurant SemEval 2016 (test)](<https://www.sota2.com/research/sota/aspect-sentiment-classification-on-restaurant-semeval-2016-test>)

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

Data updated: 2026-02-27T09:17:14.021Z

Evaluation of Aspect Sentiment Classification performance on the test split of the SemEval 2016 Restaurant dataset.

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 | Aspect Sentiment Classification |
| Dataset (including any stated split) | Restaurant SemEval 2016 (test) |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 27 of 27 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/aspect-sentiment-classification-on-restaurant-semeval-2016-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/aspect-sentiment-classification-on-restaurant-semeval-2016-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| InstructABSA2 | 93.01 | Not recorded | 68fa738b1e209131cea5d201 |
| PFInstruct-RE | 92.51 | Not recorded | 68fa738b1e209131cea5d201 |
| PFInstruct-Noise | 91.54 | Not recorded | 68fa738b1e209131cea5d201 |
| PFInstruct-NER | 86.6 | Not recorded | 68fa738b1e209131cea5d201 |
| LSAE-X-DeBERTa | 84.87 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAP-X-DeBERTa | 84.68 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAT-X-DeBERTa | 84.34 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAS-X-DeBERTa | 83.5 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAT-RoBERTa | 83.41 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAE-DeBERTa | 82.39 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAE-RoBERTa | 82.18 | Not recorded | 68fa72b01e209131cea57eb2 |
| SARL-RoBERTa | 81.92 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAS-RoBERTa | 81.82 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAS-DeBERTa | 81.61 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAT-DeBERTa | 81.53 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAP-DeBERTa | 81.44 | Not recorded | 68fa72b01e209131cea57eb2 |
| RoBERTa | 80.88 | Not recorded | 68fa72b01e209131cea57eb2 |
| SARL-DeBERTa | 80.13 | Not recorded | 68fa72b01e209131cea57eb2 |
| DGEDT-BERT | 79 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAE-BERT | 78.49 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAP-BERT | 78.25 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAS-BERT | 77.54 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAT-BERT | 77.5 | Not recorded | 68fa72b01e209131cea57eb2 |
| LSAP-RoBERTa | 76.17 | Not recorded | 68fa72b01e209131cea57eb2 |
| DeBERTa | 73.59 | Not recorded | 68fa72b01e209131cea57eb2 |
| TGCN-BERT | 72.81 | Not recorded | 68fa72b01e209131cea57eb2 |
| SK-GCN-BERT | 72.02 | Not recorded | 68fa72b01e209131cea57eb2 |

### InstructABSA2

F1 Score: 93.01. Result ID: 69a1611135dfcabb00e6aa3e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738b1e209131cea5d201.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa712c1e209131cea4fb8d.md>)

[Implementation](<https://anonymous.4open.science/r/InstructABSA-EB71>)

Recorded evaluation configuration: {"Model":"InstructABSA2","Status":"Reproduced"}. This record does not assert independent reproduction.

### PFInstruct-RE

F1 Score: 92.51. Result ID: 69a1611135dfcabb00e6aa3f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738b1e209131cea5d201.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738b1e209131cea5d201.md>)

[Implementation](<https://github.com/lautel-sony/PFInstruct>)

Recorded evaluation configuration: {"Model":"PFInstruct-RE","Prefix":"Relation Extraction"}. This record does not assert independent reproduction.

### PFInstruct-Noise

F1 Score: 91.54. Result ID: 69a1611135dfcabb00e6aa41.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738b1e209131cea5d201.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738b1e209131cea5d201.md>)

[Implementation](<https://github.com/lautel-sony/PFInstruct>)

Recorded evaluation configuration: {"Model":"PFInstruct-Noise","Prefix":"Noise"}. This record does not assert independent reproduction.

### PFInstruct-NER

F1 Score: 86.6. Result ID: 69a1611135dfcabb00e6aa40.

[Reporting paper](<https://www.sota2.com/research/paper/68fa738b1e209131cea5d201.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738b1e209131cea5d201.md>)

[Implementation](<https://github.com/lautel-sony/PFInstruct>)

Recorded evaluation configuration: {"Model":"PFInstruct-NER","Prefix":"Named Entity Recognition"}. This record does not assert independent reproduction.

### LSAE-X-DeBERTa

F1 Score: 84.87. Result ID: 6992504a3a6c3148490e1ab1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAP-X-DeBERTa

F1 Score: 84.68. Result ID: 6992504a3a6c3148490e1aae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAT-X-DeBERTa

F1 Score: 84.34. Result ID: 6992504a3a6c3148490e1aaf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAS-X-DeBERTa

F1 Score: 83.5. Result ID: 6992504a3a6c3148490e1ab0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAT-RoBERTa

F1 Score: 83.41. Result ID: 6992504a3a6c3148490e1aa7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAE-DeBERTa

F1 Score: 82.39. Result ID: 6992504a3a6c3148490e1aad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAE-RoBERTa

F1 Score: 82.18. Result ID: 6992504a3a6c3148490e1aa9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### SARL-RoBERTa

F1 Score: 81.92. Result ID: 6992504a3a6c3148490e1a9e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ab51e209131cea29ee2.md>)

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

### LSAS-RoBERTa

F1 Score: 81.82. Result ID: 6992504a3a6c3148490e1aa8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAS-DeBERTa

F1 Score: 81.61. Result ID: 6992504a3a6c3148490e1aac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAT-DeBERTa

F1 Score: 81.53. Result ID: 6992504a3a6c3148490e1aab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAP-DeBERTa

F1 Score: 81.44. Result ID: 6992504a3a6c3148490e1aaa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### RoBERTa

F1 Score: 80.88. Result ID: 6992504a3a6c3148490e1a9f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66131e209131cea0e18b.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

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

### SARL-DeBERTa

F1 Score: 80.13. Result ID: 6992504a3a6c3148490e1aa1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ab51e209131cea29ee2.md>)

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

### DGEDT-BERT

F1 Score: 79. Result ID: 6992504a3a6c3148490e1a9c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

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

### LSAE-BERT

F1 Score: 78.49. Result ID: 6992504a3a6c3148490e1aa5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAP-BERT

F1 Score: 78.25. Result ID: 6992504a3a6c3148490e1aa2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAS-BERT

F1 Score: 77.54. Result ID: 6992504a3a6c3148490e1aa4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAT-BERT

F1 Score: 77.5. Result ID: 6992504a3a6c3148490e1aa3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### LSAP-RoBERTa

F1 Score: 76.17. Result ID: 6992504a3a6c3148490e1aa6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Implementation](<https://github.com/yangheng95/PyABSA>)

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

### DeBERTa

F1 Score: 73.59. Result ID: 6992504a3a6c3148490e1aa0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee11e209131cea4297b.md>)

[Implementation](<https://github.com/microsoft/DeBERTa>)

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

### TGCN-BERT

F1 Score: 72.81. Result ID: 6992504a3a6c3148490e1a9d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

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

### SK-GCN-BERT

F1 Score: 72.02. Result ID: 6992504a3a6c3148490e1a9b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57eb2.md>)

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

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