# Part-of-Speech Tagging Throughput on EWT (test)

Source: [Part-of-Speech Tagging Throughput on EWT (test)](<https://www.sota2.com/research/sota/part-of-speech-tagging-throughput-on-ewt-test>)

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

Data updated: 2026-02-26T06:06:25.681Z

Evaluation of Part-of-Speech (POS) Tagging inference speed on the test split of the English Wikipedia Treebank (EWT), measured in sentences processed per second.

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) | EWT (test) |
| Metric | Throughput (sentences/sec) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Throughput (sentences/sec)](<https://www.sota2.com/research/sota/part-of-speech-tagging-throughput-on-ewt-test.md?metric=Throughput%20(sentences%2Fsec)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Throughput (sentences/sec) | Result date | Report paper |
| --- | --- | --- | --- |
| TAPIR-Trf | 3.659 | Not recorded | 68fa6f6c1e209131cea45774 |
| TAPIR-LT | 3.122 | Not recorded | 68fa6f6c1e209131cea45774 |
| Reference Model | 0.819 | Not recorded | 68fa6f6c1e209131cea45774 |

### TAPIR-Trf

Throughput (sentences/sec): 3.659. Result ID: 6990bca93a6c31484902de25.

[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: {"Reviser":"Transformer"}. This record does not assert independent reproduction.

### TAPIR-LT

Throughput (sentences/sec): 3.122. Result ID: 6990bca93a6c31484902de26.

[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: {"Reviser":"Linear Transformer"}. This record does not assert independent reproduction.

### Reference Model

Throughput (sentences/sec): 0.819. Result ID: 6990bca93a6c31484902de24.

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

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

Recorded evaluation configuration: {"Model Type":"Restart-incremental"}. This record does not assert independent reproduction.

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