Simile Quality Evaluation on Simile Quality Dataset 1.0 (test)
0.32Pearson PCCHAUSER
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| HAUSERMetric Category=HAUSER, Sub-metric=Full Quality2023.06 | 0.32 | 0.292 | |
| HAUSER (-consistency_i)Metric Category=HAUSER, Ablation=Removal of image consistency sub-metric2023.06 | 0.307 | 0.265 | |
| HAUSER (-consistency_s)Metric Category=HAUSER, Ablation=Removal of sentiment consistency sub-metric2023.06 | 0.259 | 0.217 | |
| BLEU2Metric Category=N-gram-level2023.06 | 0.255 | 0.208 | |
| METEORMetric Category=N-gram-level2023.06 | 0.234 | 0.233 | |
| BLEU1Metric Category=N-gram-level2023.06 | 0.229 | 0.218 | |
| Rouge2Metric Category=N-gram-level2023.06 | 0.21 | 0.19 | |
| HAUSER (-relevance)Metric Category=HAUSER, Ablation=Removal of relevance sub-metric2023.06 | 0.206 | 0.194 | |
| BLEU3Metric Category=N-gram-level2023.06 | 0.193 | 0.172 | |
| Rouge1Metric Category=N-gram-level2023.06 | 0.185 | 0.176 | |
| RougeLMetric Category=N-gram-level2023.06 | 0.173 | 0.152 | |
| BLEU4Metric Category=N-gram-level2023.06 | 0.159 | 0.14 | |
| PerplexityMetric Category=Sentence-level2023.06 | 0.157 | 0.12 | |
| BERTSlargeMetric Category=Sentence-level2023.06 | 0.143 | 0.12 | |
| BERTSbaseMetric Category=Sentence-level2023.06 | 0.107 | 0.075 |