# Sarcasm Explanation Generation on MORE OCR samples (test)

Source: [Sarcasm Explanation Generation on MORE OCR samples (test)](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test>)

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

Data updated: 2026-02-26T06:00:39.185Z

Evaluation of model performance on generating explanations for sarcasm instances using the test split of the MORE OCR samples dataset, measured using ROUGE, BLEU, METEOR, BERTScore, and Sent-BERT metrics.

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 | Sarcasm Explanation Generation |
| Dataset (including any stated split) | MORE OCR samples (test) |
| Metric | ROUGE-1 Precision |
| Unit | SCALAR |
| 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

- [ROUGE-1 Precision](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=ROUGE-1%20Precision>): Higher is better; unit: SCALAR.

- [ROUGE-2 Precision](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=ROUGE-2%20Precision>): Higher is better; unit: SCALAR.

- [ROUGE-3 Precision](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=ROUGE-3%20Precision>): Higher is better; unit: SCALAR.

- [ROUGE-4 Precision](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=ROUGE-4%20Precision>): Higher is better; unit: SCALAR.

- [ROUGE-L F1](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=ROUGE-L%20F1>): Higher is better; unit: SCALAR.

- [ROUGE-1 Recall](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=ROUGE-1%20Recall>): Higher is better; unit: SCALAR.

- [ROUGE-2 Recall](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=ROUGE-2%20Recall>): Higher is better; unit: SCALAR.

- [METEOR Score](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=METEOR%20Score>): Higher is better; unit: SCALAR.

- [BERTScore Precision](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=BERTScore%20Precision>): Higher is better; unit: SCALAR.

- [BERTScore Recall](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=BERTScore%20Recall>): Higher is better; unit: SCALAR.

- [BERTScore F1](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=BERTScore%20F1>): Higher is better; unit: SCALAR.

- [Sent-BERT Similarity](<https://www.sota2.com/research/sota/sarcasm-explanation-generation-on-more-ocr-samples-test.md?metric=Sent-BERT%20Similarity>): Higher is better; unit: SCALAR.

## Recorded results

| Method | ROUGE-1 Precision | Result date | Report paper |
| --- | --- | --- | --- |
| TEAM | 52.88 | Not recorded | 68fa6fea1e209131cea48245 |
| TEAM-w/o-Know | 51.91 | Not recorded | 68fa6fea1e209131cea48245 |
| ExMore | 19.4 | Not recorded | 68fa6fea1e209131cea48245 |
| PGN | 17.19 | Not recorded | 68fa6fea1e209131cea48245 |
| M-Transf | 14.06 | Not recorded | 68fa6fea1e209131cea48245 |
| MFFG-Transf | 12.87 | Not recorded | 68fa6fea1e209131cea48245 |
| MFFG-RNN | 12.18 | Not recorded | 68fa6fea1e209131cea48245 |
| Transformer | 10.68 | Not recorded | 68fa6fea1e209131cea48245 |

### TEAM

ROUGE-1 Precision: 52.88. Result ID: 6990f23f3a6c314849048235.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fea1e209131cea48245.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fea1e209131cea48245.md>)

[Implementation](<https://github.com/LiqiangJing/TEAM>)

Recorded evaluation configuration: {"Backbone":"bart-base-chinese","Knowledge":"Full"}. This record does not assert independent reproduction.

### TEAM-w/o-Know

ROUGE-1 Precision: 51.91. Result ID: 6990f23f3a6c314849048234.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fea1e209131cea48245.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fea1e209131cea48245.md>)

[Implementation](<https://github.com/LiqiangJing/TEAM>)

Recorded evaluation configuration: {"Backbone":"bart-base-chinese","Knowledge":"None"}. This record does not assert independent reproduction.

### ExMore

ROUGE-1 Precision: 19.4. Result ID: 6990f23f3a6c314849048233.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fea1e209131cea48245.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b611e209131cea2ddcf.md>)

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

### PGN

ROUGE-1 Precision: 17.19. Result ID: 6990f23f3a6c31484904822e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fea1e209131cea48245.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634a1e209131ce9fdbfb.md>)

[Implementation](<https://www.sota2.com/www.github.com/abisee/pointer-generator>)

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

### M-Transf

ROUGE-1 Precision: 14.06. Result ID: 6990f23f3a6c314849048232.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fea1e209131cea48245.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b611e209131cea2ddcf.md>)

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

### MFFG-Transf

ROUGE-1 Precision: 12.87. Result ID: 6990f23f3a6c314849048231.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fea1e209131cea48245.md>)

Recorded evaluation configuration: {"Architecture":"Transformer-based"}. This record does not assert independent reproduction.

### MFFG-RNN

ROUGE-1 Precision: 12.18. Result ID: 6990f23f3a6c314849048230.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fea1e209131cea48245.md>)

Recorded evaluation configuration: {"Architecture":"RNN-based"}. This record does not assert independent reproduction.

### Transformer

ROUGE-1 Precision: 10.68. Result ID: 6990f23f3a6c31484904822f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fea1e209131cea48245.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

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

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