# Document Classification on TED corpus en -\> L2 (test) Source: [Document Classification on TED corpus en -\> L2 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:59.205Z Evaluation of Document Classification performance on the test split of the TED corpus, reporting results across 11 specific target languages (L2). 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 | Document Classification | | Dataset (including any stated split) | TED corpus en -\> L2 (test) | | Metric | Arabic | | Unit | PERCENT | | Direction | Higher 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 - [Arabic](): Higher is better; unit: PERCENT. - [German](): Higher is better; unit: PERCENT. - [Spanish](): Higher is better; unit: PERCENT. - [French](): Higher is better; unit: PERCENT. - [Italian](): Higher is better; unit: PERCENT. - [Dutch](): Higher is better; unit: PERCENT. - [Polish](): Higher is better; unit: PERCENT. - [Pt-Br](): Higher is better; unit: PERCENT. - [Romanian](): Higher is better; unit: PERCENT. - [Russian](): Higher is better; unit: PERCENT. - [Turkish](): Higher is better; unit: PERCENT. ## Recorded results | Method | Arabic | Result date | Report paper | | --- | --- | --- | --- | | MT System | 42.9 | Not recorded | 68fa61501e209131ce9f3c05 | | DOC/ADD | 41 | Not recorded | 68fa61501e209131ce9f3c05 | | DOC/ADD | 39.2 | Not recorded | 68fa61501e209131ce9f3c05 | | DOC/BI | 38.9 | Not recorded | 68fa61501e209131ce9f3c05 | | BI | 37.5 | Not recorded | 68fa61501e209131ce9f3c05 | | DOC/BI | 37.2 | Not recorded | 68fa61501e209131ce9f3c05 | | ADD | 32.8 | Not recorded | 68fa61501e209131ce9f3c05 | ### MT System Arabic: 42.9. Result ID: 698c1469f729bc7f68e82bb9. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DOC/ADD Arabic: 41. Result ID: 698c1469f729bc7f68e82bbc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"training\_regime":"single"}. This record does not assert independent reproduction. ### DOC/ADD Arabic: 39.2. Result ID: 698c1469f729bc7f68e82bbe. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"training\_regime":"joint"}. This record does not assert independent reproduction. ### DOC/BI Arabic: 38.9. Result ID: 698c1469f729bc7f68e82bbd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"training\_regime":"single"}. This record does not assert independent reproduction. ### BI Arabic: 37.5. Result ID: 698c1469f729bc7f68e82bbb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"training\_regime":"single"}. This record does not assert independent reproduction. ### DOC/BI Arabic: 37.2. Result ID: 698c1469f729bc7f68e82bbf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"training\_regime":"joint"}. This record does not assert independent reproduction. ### ADD Arabic: 32.8. Result ID: 698c1469f729bc7f68e82bba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"training\_regime":"single"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.