# Flat Named Entity Recognition on OntoNotes 5.0 (test)

Source: [Flat Named Entity Recognition on OntoNotes 5.0 (test)](<https://www.sota2.com/research/sota/flat-named-entity-recognition-on-ontonotes-5-0-test>)

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

Data updated: 2026-02-26T05:52:42.240Z

Evaluation of Flat Named Entity Recognition performance on the test split of the OntoNotes 5.0 dataset, reporting Micro F1 score.

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 | Flat Named Entity Recognition |
| Dataset (including any stated split) | OntoNotes 5.0 (test) |
| Metric | Micro F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [Micro F1](<https://www.sota2.com/research/sota/flat-named-entity-recognition-on-ontonotes-5-0-test.md?metric=Micro%20F1>): Higher is better; unit: PERCENT.

- [Micro Precision](<https://www.sota2.com/research/sota/flat-named-entity-recognition-on-ontonotes-5-0-test.md?metric=Micro%20Precision>): Higher is better; unit: PERCENT.

- [Micro Recall](<https://www.sota2.com/research/sota/flat-named-entity-recognition-on-ontonotes-5-0-test.md?metric=Micro%20Recall>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Micro F1 | Result date | Report paper |
| --- | --- | --- | --- |
| PL-Marker | 91.9 | Not recorded | 68fa6c541e209131cea3352b |
| Random Packing | 91.8 | Not recorded | 68fa6c541e209131cea3352b |
| DSpERT | 91.76 | Not recorded | 68fa6f411e209131cea448c6 |
| Zhu and Li | 91.74 | Not recorded | 68fa6f411e209131cea448c6 |
| T-Concat | 91.7 | Not recorded | 68fa6c541e209131cea3352b |
| Yu et al. (2020) | 91.3 | Not recorded | 68fa6c541e209131cea3352b |
| Yu et al. | 91.3 | Not recorded | 68fa6f411e209131cea448c6 |
| SeqTagger | 91.2 | Not recorded | 68fa6c541e209131cea3352b |
| Li et al. | 91.11 | Not recorded | 68fa6f411e209131cea448c6 |
| Li et al. (2020) | 91.1 | Not recorded | 68fa6c541e209131cea3352b |
| DSpERT | 91.06 | Not recorded | 68fa6f411e209131cea448c6 |
| Shen et al. | 90.96 | Not recorded | 68fa6f411e209131cea448c6 |
| Li et al. | 90.5 | Not recorded | 68fa6f411e209131cea448c6 |
| Yan et al. (2021) | 90.4 | Not recorded | 68fa6c541e209131cea3352b |
| Yan et al. | 90.38 | Not recorded | 68fa6f411e209131cea448c6 |
| Devlin et al. (2019) | 89.2 | Not recorded | 68fa6c541e209131cea3352b |
| Ma and Hovy (2016) | 86.3 | Not recorded | 68fa6c541e209131cea3352b |

### PL-Marker

Micro F1: 91.9. Result ID: 698f02e33a6c314849f4ae56.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c541e209131cea3352b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c541e209131cea3352b.md>)

[Implementation](<https://github.com/thunlp/PL-Marker>)

Recorded evaluation configuration: {"Implementation":"Our model"}. This record does not assert independent reproduction.

### Random Packing

Micro F1: 91.8. Result ID: 698f02e33a6c314849f4ae55.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c541e209131cea3352b.md>)

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

### DSpERT

Micro F1: 91.76. Result ID: 69909d9f3a6c31484901e340.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f411e209131cea448c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f411e209131cea448c6.md>)

[Implementation](<https://github.com/syuoni/eznlp>)

Recorded evaluation configuration: {"best score":true}. This record does not assert independent reproduction.

### Zhu and Li

Micro F1: 91.74. Result ID: 69909d9f3a6c31484901e33e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f411e209131cea448c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c671e209131cea33df6.md>)

[Implementation](<https://github.com/syuoni/eznlp>)

Recorded evaluation configuration: {"year":"2022"}. This record does not assert independent reproduction.

### T-Concat

Micro F1: 91.7. Result ID: 698f02e33a6c314849f4ae54.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c541e209131cea3352b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67771e209131cea1685a.md>)

[Implementation](<https://github.com/neulab/cmu-multinlp>)

Recorded evaluation configuration: {"Implementation":"Our implementation"}. This record does not assert independent reproduction.

### Yu et al. (2020)

Micro F1: 91.3. Result ID: 698f02e33a6c314849f4ae51.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c541e209131cea3352b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67bb1e209131cea182b4.md>)

[Implementation](<https://github.com/juntaoy/biaffine-ner>)

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

### Yu et al.

Micro F1: 91.3. Result ID: 69909d9f3a6c31484901e33b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f411e209131cea448c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67bb1e209131cea182b4.md>)

[Implementation](<https://github.com/juntaoy/biaffine-ner>)

Recorded evaluation configuration: {"year":"2020"}. This record does not assert independent reproduction.

### SeqTagger

Micro F1: 91.2. Result ID: 698f02e33a6c314849f4ae53.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c541e209131cea3352b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

Recorded evaluation configuration: {"Implementation":"Our implementation"}. This record does not assert independent reproduction.

### Li et al.

Micro F1: 91.11. Result ID: 69909d9f3a6c31484901e33a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f411e209131cea448c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ab1e209131cea17a6d.md>)

[Implementation](<https://github.com/LeeSureman/Flat-Lattice-Transformer>)

Recorded evaluation configuration: {"year":"2020b"}. This record does not assert independent reproduction.

### Li et al. (2020)

Micro F1: 91.1. Result ID: 698f02e33a6c314849f4ae50.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c541e209131cea3352b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfa1e209131cea3d1ea.md>)

[Implementation](<https://github.com/ShannonAI/mrc-for-flat-nested-ner>)

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

### DSpERT

Micro F1: 91.06. Result ID: 69909d9f3a6c31484901e341.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f411e209131cea448c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f411e209131cea448c6.md>)

[Implementation](<https://github.com/syuoni/eznlp>)

Recorded evaluation configuration: {"average of multiple independent runs":true}. This record does not assert independent reproduction.

### Shen et al.

Micro F1: 90.96. Result ID: 69909d9f3a6c31484901e33f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f411e209131cea448c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a551e209131cea27793.md>)

[Implementation](<https://github.com/tricktreat/locate-and-label.>)

Recorded evaluation configuration: {"year":"2022"}. This record does not assert independent reproduction.

### Li et al.

Micro F1: 90.5. Result ID: 69909d9f3a6c31484901e33d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f411e209131cea448c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ab1e209131cea17a6d.md>)

[Implementation](<https://github.com/LeeSureman/Flat-Lattice-Transformer>)

Recorded evaluation configuration: {"average of multiple independent runs":true,"year":"2022"}. This record does not assert independent reproduction.

### Yan et al. (2021)

Micro F1: 90.4. Result ID: 698f02e33a6c314849f4ae52.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c541e209131cea3352b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0a1e209131cea25ac7.md>)

[Implementation](<https://github.com/yhcc/BARTNER>)

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

### Yan et al.

Micro F1: 90.38. Result ID: 69909d9f3a6c31484901e33c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f411e209131cea448c6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0a1e209131cea25ac7.md>)

[Implementation](<https://github.com/yhcc/BARTNER>)

Recorded evaluation configuration: {"year":"2021"}. This record does not assert independent reproduction.

### Devlin et al. (2019)

Micro F1: 89.2. Result ID: 698f02e33a6c314849f4ae4f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c541e209131cea3352b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65c31e209131cea0c4ed.md>)

[Implementation](<https://github.com/google-research/bert>)

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

### Ma and Hovy (2016)

Micro F1: 86.3. Result ID: 698f02e33a6c314849f4ae4e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c541e209131cea3352b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62861e209131ce9f9e7e.md>)

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.
