# Part-of-Speech Tagging on CoNLL 2009 (test)

Source: [Part-of-Speech Tagging on CoNLL 2009 (test)](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll-2009-test>)

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

Data updated: 2026-02-26T05:38:54.485Z

Evaluation of Part-of-Speech Tagging performance on the CoNLL 2009 test set, reporting language-specific scores (Ca, Ch, Cz, En, Ge, Ja, Sp).

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 2009 (test) |
| Metric | Ca Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Ca Accuracy](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll-2009-test.md?metric=Ca%20Accuracy>): Higher is better; unit: PERCENT.

- [Ch Accuracy](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll-2009-test.md?metric=Ch%20Accuracy>): Higher is better; unit: PERCENT.

- [Cz Accuracy](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll-2009-test.md?metric=Cz%20Accuracy>): Higher is better; unit: PERCENT.

- [En Accuracy](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll-2009-test.md?metric=En%20Accuracy>): Higher is better; unit: PERCENT.

- [Ge Accuracy](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll-2009-test.md?metric=Ge%20Accuracy>): Higher is better; unit: PERCENT.

- [Ja Accuracy](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll-2009-test.md?metric=Ja%20Accuracy>): Higher is better; unit: PERCENT.

- [Sp Accuracy](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll-2009-test.md?metric=Sp%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/part-of-speech-tagging-on-conll-2009-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Ca Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Our Global (B=8) | 99.03 | Not recorded | 68fa62871e209131ce9f9edd |
| Our Local (B=1) | 98.91 | Not recorded | 68fa62871e209131ce9f9edd |
| Our Local (B=8) | 98.88 | Not recorded | 68fa62871e209131ce9f9edd |
| Linear CRF | 98.81 | Not recorded | 68fa62871e209131ce9f9edd |
| Ling et al. (2015) | 98.77 | Not recorded | 68fa62871e209131ce9f9edd |

### Our Global (B=8)

Ca Accuracy: 99.03. Result ID: 698bdb0cecace47ef5592b5f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa62871e209131ce9f9edd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62871e209131ce9f9edd.md>)

[Implementation](<http://github.com/tensorflow/models/tree/master/syntaxnet>)

Recorded evaluation configuration: {"Normalization Strategy":"Global","Beam Size (B)":8}. This record does not assert independent reproduction.

### Our Local (B=1)

Ca Accuracy: 98.91. Result ID: 698bdb0cecace47ef5592b5d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa62871e209131ce9f9edd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62871e209131ce9f9edd.md>)

[Implementation](<http://github.com/tensorflow/models/tree/master/syntaxnet>)

Recorded evaluation configuration: {"Normalization Strategy":"Local","Beam Size (B)":1}. This record does not assert independent reproduction.

### Our Local (B=8)

Ca Accuracy: 98.88. Result ID: 698bdb0cecace47ef5592b5e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa62871e209131ce9f9edd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62871e209131ce9f9edd.md>)

[Implementation](<http://github.com/tensorflow/models/tree/master/syntaxnet>)

Recorded evaluation configuration: {"Normalization Strategy":"Local","Beam Size (B)":8}. This record does not assert independent reproduction.

### Linear CRF

Ca Accuracy: 98.81. Result ID: 698bdb0cecace47ef5592b5b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa62871e209131ce9f9edd.md>)

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

### Ling et al. (2015)

Ca Accuracy: 98.77. Result ID: 698bdb0cecace47ef5592b5c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa62871e209131ce9f9edd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa627c1e209131ce9f9812.md>)

[Implementation](<https://github.com/wlin12/JNN>)

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.