# Part-Of-Speech Tagging on Universal Dependencies (UD) (test) Source: [Part-Of-Speech Tagging on Universal Dependencies (UD) (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:29:54.007Z Evaluation of Part-of-Speech (POS) Tagging performance on the test split of the Universal Dependencies dataset. 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) | Universal Dependencies (UD) (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. - [Accuracy (amh)](): Higher is better; unit: PERCENT. - [Accuracy (lij)](): Higher is better; unit: PERCENT. - [Accuracy (olo)](): Higher is better; unit: PERCENT. - [Accuracy (san)](): Higher is better; unit: PERCENT. - [Accuracy (snd)](): Higher is better; unit: PERCENT. - [Accuracy (sin)](): Higher is better; unit: PERCENT. - [Accuracy (tam)](): Higher is better; unit: PERCENT. - [Accuracy (tgl)](): Higher is better; unit: PERCENT. - [Accuracy (tat)](): Higher is better; unit: PERCENT. - [Average Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | AIN-1O | 94.97 | Not recorded | 68fa68851e209131cea1ca29 | | CRF | 94.91 | Not recorded | 68fa68851e209131cea1ca29 | | AIN-F2O | 94.91 | Not recorded | 68fa68851e209131cea1ca29 | | MaxEnt | 94.84 | Not recorded | 68fa68851e209131cea1ca29 | | AIN-F2O | 94.32 | Not recorded | 68fa68851e209131cea1ca29 | | AIN-1O | 94.29 | Not recorded | 68fa68851e209131cea1ca29 | | CRF | 94.26 | Not recorded | 68fa68851e209131cea1ca29 | | MaxEnt | 94 | Not recorded | 68fa68851e209131cea1ca29 | | AIN-F2O | 93.03 | Not recorded | 68fa68851e209131cea1ca29 | | AIN-1O | 92.84 | Not recorded | 68fa68851e209131cea1ca29 | | CRF | 92.79 | Not recorded | 68fa68851e209131cea1ca29 | | MaxEnt | 90.53 | Not recorded | 68fa68851e209131cea1ca29 | ### AIN-1O Accuracy: 94.97. Result ID: 698d747d8b517eb43321a108. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"WORD-CHAR-BILSTM"}. This record does not assert independent reproduction. ### CRF Accuracy: 94.91. Result ID: 698d747d8b517eb43321a105. [Reporting paper]() Recorded evaluation configuration: {"Encoder":"WORD-CHAR-BILSTM"}. This record does not assert independent reproduction. ### AIN-F2O Accuracy: 94.91. Result ID: 698d747d8b517eb43321a10b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"WORD-CHAR-BILSTM"}. This record does not assert independent reproduction. ### MaxEnt Accuracy: 94.84. Result ID: 698d747d8b517eb43321a102. [Reporting paper]() Recorded evaluation configuration: {"Encoder":"WORD-CHAR-BILSTM"}. This record does not assert independent reproduction. ### AIN-F2O Accuracy: 94.32. Result ID: 698d747d8b517eb43321a10c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"WORD-CNN"}. This record does not assert independent reproduction. ### AIN-1O Accuracy: 94.29. Result ID: 698d747d8b517eb43321a109. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"WORD-CNN"}. This record does not assert independent reproduction. ### CRF Accuracy: 94.26. Result ID: 698d747d8b517eb43321a106. [Reporting paper]() Recorded evaluation configuration: {"Encoder":"WORD-CNN"}. This record does not assert independent reproduction. ### MaxEnt Accuracy: 94. Result ID: 698d747d8b517eb43321a103. [Reporting paper]() Recorded evaluation configuration: {"Encoder":"WORD-CNN"}. This record does not assert independent reproduction. ### AIN-F2O Accuracy: 93.03. Result ID: 698d747d8b517eb43321a10d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"WORD ONLY"}. This record does not assert independent reproduction. ### AIN-1O Accuracy: 92.84. Result ID: 698d747d8b517eb43321a10a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Encoder":"WORD ONLY"}. This record does not assert independent reproduction. ### CRF Accuracy: 92.79. Result ID: 698d747d8b517eb43321a107. [Reporting paper]() Recorded evaluation configuration: {"Encoder":"WORD ONLY"}. This record does not assert independent reproduction. ### MaxEnt Accuracy: 90.53. Result ID: 698d747d8b517eb43321a104. [Reporting paper]() Recorded evaluation configuration: {"Encoder":"WORD ONLY"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.