# Multimodal Named Entity Recognition on Twitter-15 (Low-resource & Full-supervision)

Source: [Multimodal Named Entity Recognition on Twitter-15 (Low-resource & Full-supervision)](<https://www.sota2.com/research/sota/multimodal-named-entity-recognition-on-twitter-15-low-resource-and-full-supervision>)

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

Data updated: 2026-06-18T07:58:22.390Z

Evaluation of Multimodal Named Entity Recognition performance on the Twitter-15 dataset, specifically configured for low-resource and full-supervision settings, reporting Precision, Recall, and F1 scores.

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 | Multimodal Named Entity Recognition |
| Dataset (including any stated split) | Twitter-15 Low-resource & Full-supervision |
| Metric | Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Precision](<https://www.sota2.com/research/sota/multimodal-named-entity-recognition-on-twitter-15-low-resource-and-full-supervision.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/multimodal-named-entity-recognition-on-twitter-15-low-resource-and-full-supervision.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/multimodal-named-entity-recognition-on-twitter-15-low-resource-and-full-supervision.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| PGIM -w/ SAMA | 78.2 | Not recorded | 6a337bc4206542251d7c520b |
| PGIM | 72.6 | Not recorded | 6a337bc4206542251d7c520b |
| MMT5 -w/ SAMA | 71.6 | Not recorded | 6a337bc4206542251d7c520b |
| MMT5 -w/ GMDA | 69.6 | Not recorded | 6a337bc4206542251d7c520b |
| MMT5 -w/ mixGen | 68.2 | Not recorded | 6a337bc4206542251d7c520b |
| MMT5 | 63.9 | Not recorded | 6a337bc4206542251d7c520b |

### PGIM -w/ SAMA

Precision: 78.2. Result ID: 6a33a514fbc373592c30b8db.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bc4206542251d7c520b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bc4206542251d7c520b.md>)

Recorded evaluation configuration: {"Training Data Ratio":"100%"}. This record does not assert independent reproduction.

### PGIM

Precision: 72.6. Result ID: 6a33a514fbc373592c30b8da.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bc4206542251d7c520b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e51e209131cea4dbd1.md>)

[Implementation](<https://github.com/JinYuanLi0012/PGIM>)

Recorded evaluation configuration: {"Training Data Ratio":"10%"}. This record does not assert independent reproduction.

### MMT5 -w/ SAMA

Precision: 71.6. Result ID: 6a33a514fbc373592c30b8d9.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bc4206542251d7c520b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a337bc4206542251d7c520b.md>)

Recorded evaluation configuration: {"Training Data Ratio":"10%"}. This record does not assert independent reproduction.

### MMT5 -w/ GMDA

Precision: 69.6. Result ID: 6a33a514fbc373592c30b8d8.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bc4206542251d7c520b.md>)

Recorded evaluation configuration: {"Training Data Ratio":"10%"}. This record does not assert independent reproduction.

### MMT5 -w/ mixGen

Precision: 68.2. Result ID: 6a33a514fbc373592c30b8d7.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bc4206542251d7c520b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e5f1e209131cea3f790.md>)

Recorded evaluation configuration: {"Training Data Ratio":"10%"}. This record does not assert independent reproduction.

### MMT5

Precision: 63.9. Result ID: 6a33a514fbc373592c30b8d6.

[Reporting paper](<https://www.sota2.com/research/paper/6a337bc4206542251d7c520b.md>)

Recorded evaluation configuration: {"Training Data Ratio":"10%"}. This record does not assert independent reproduction.

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