# Part-of-Speech Tagging on CoNLL

Source: [Part-of-Speech Tagging on CoNLL](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll>)

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

Data updated: 2026-02-26T05:38:51.977Z

Evaluation of Part-of-Speech Tagging performance on the standard CoNLL dataset using custom metrics (EO, CT, RC, etc.).

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 | Part-of-Speech Tagging |
| Dataset (including any stated split) | CoNLL |
| Metric | CT (Coverage Threshold) |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 7 of 7 |
| 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

- [CT (Coverage Threshold)](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll.md?metric=CT%20(Coverage%20Threshold)>): Lower is better; unit: PERCENT.

- [EO (Error Overlap)](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll.md?metric=EO%20(Error%20Overlap)>): Lower is better; unit: PERCENT.

- [RC (Recall)](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll.md?metric=RC%20(Recall)>): Higher is better; unit: PERCENT.

- [EO Delta 1](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll.md?metric=EO%20Delta%201>): Lower is better; unit: PERCENT.

- [EO Delta 2](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll.md?metric=EO%20Delta%202>): Lower is better; unit: PERCENT.

- [RCA 1](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll.md?metric=RCA%201>): Higher is better; unit: PERCENT.

- [RCA 2](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll.md?metric=RCA%202>): Higher is better; unit: PERCENT.

## Recorded results

| Method | CT (Coverage Threshold) | Result date | Report paper |
| --- | --- | --- | --- |
| TAPIR-LT | 2.3 | Not recorded | 68fa6f6c1e209131cea45774 |
| TAPIR-Trf | 2.5 | Not recorded | 68fa6f6c1e209131cea45774 |
| TAPIR-LT | 2.6 | Not recorded | 68fa6f6c1e209131cea45774 |
| TAPIR-Trf | 2.7 | Not recorded | 68fa6f6c1e209131cea45774 |
| TAPIR-LT | 2.8 | Not recorded | 68fa6f6c1e209131cea45774 |
| TAPIR-Trf | 3.2 | Not recorded | 68fa6f6c1e209131cea45774 |
| Reference Model | 7.2 | Not recorded | 68fa6f6c1e209131cea45774 |

### TAPIR-LT

CT (Coverage Threshold): 2.3. Result ID: 6990bca93a6c31484902ddde.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Implementation](<https://github.com/pkhdipraja/tapir>)

Recorded evaluation configuration: {"Delay steps (Δt)":1}. This record does not assert independent reproduction.

### TAPIR-Trf

CT (Coverage Threshold): 2.5. Result ID: 6990bca93a6c31484902dddb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Implementation](<https://github.com/pkhdipraja/tapir>)

Recorded evaluation configuration: {"Delay steps (Δt)":1}. This record does not assert independent reproduction.

### TAPIR-LT

CT (Coverage Threshold): 2.6. Result ID: 6990bca93a6c31484902dddf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Implementation](<https://github.com/pkhdipraja/tapir>)

Recorded evaluation configuration: {"Delay steps (Δt)":2}. This record does not assert independent reproduction.

### TAPIR-Trf

CT (Coverage Threshold): 2.7. Result ID: 6990bca93a6c31484902dddc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Implementation](<https://github.com/pkhdipraja/tapir>)

Recorded evaluation configuration: {"Delay steps (Δt)":2}. This record does not assert independent reproduction.

### TAPIR-LT

CT (Coverage Threshold): 2.8. Result ID: 6990bca93a6c31484902dddd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Implementation](<https://github.com/pkhdipraja/tapir>)

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

### TAPIR-Trf

CT (Coverage Threshold): 3.2. Result ID: 6990bca93a6c31484902ddda.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Implementation](<https://github.com/pkhdipraja/tapir>)

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

### Reference Model

CT (Coverage Threshold): 7.2. Result ID: 6990bca93a6c31484902ddd9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f6c1e209131cea45774.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ab1e209131cea57bd2.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.