Multimodal Named Entity Recognition on Twitter 17 (test)
90.67F1 ScoreMoRe_MoE
Evaluation results
| Method | Links | |
|---|---|---|
| MoRe_MoERetrieval Modality=Mixture-of-Experts (Text + Image)2022.12 | 90.67 | |
| MoRe_ImageRetrieval Modality=Image-based2022.12 | 89.82 | |
| ITARetrieval Modality=None2022.12 | 89.75 | |
| MoRe_TextRetrieval Modality=Textual2022.12 | 89.5 | |
| Ours: BaselineRetrieval Modality=None2022.12 | 88.68 | |
| ITA-All+CVASource=Our Reproductions2021.12 | 86.45 | |
| UMGFSource=Reported2021.12 | 85.51 | |
| Zhang et al.Retrieval Modality=None2022.12 | 85.51 | |
| UMT+Source=Reported2021.12 | 85.31 | |
| Yu et al.Retrieval Modality=None2022.12 | 85.31 | |
| UMGFSource=Reproduced2021.12 | 85.27 | |
| BERT-CRFSource=Reproduced2021.12 | 85.18 | |
| UMTSource=Reproduced2021.12 | 84.88 | |
| BERT-CRF+Source=Reported2021.12 | 83.44 |