# Text Classification on EUR-Lex

Source: [Text Classification on EUR-Lex](<https://www.sota2.com/research/sota/text-classification-on-eur-lex>)

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

Data updated: 2026-02-26T05:58:50.781Z

Evaluation of Text Classification performance on the EUR-Lex dataset, measured using Precision and Normalized Discounted Cumulative Gain (NDCG) at ranks 1, 3, and 5.

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 | Text Classification |
| Dataset (including any stated split) | EUR-Lex |
| Metric | Precision@1 |
| 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

- [Precision@1](<https://www.sota2.com/research/sota/text-classification-on-eur-lex.md?metric=Precision%401>): Higher is better; unit: PERCENT.

- [Precision@3](<https://www.sota2.com/research/sota/text-classification-on-eur-lex.md?metric=Precision%403>): Higher is better; unit: PERCENT.

- [Precision@5](<https://www.sota2.com/research/sota/text-classification-on-eur-lex.md?metric=Precision%405>): Higher is better; unit: PERCENT.

- [NDCG@1](<https://www.sota2.com/research/sota/text-classification-on-eur-lex.md?metric=NDCG%401>): Higher is better; unit: PERCENT.

- [NDCG@3](<https://www.sota2.com/research/sota/text-classification-on-eur-lex.md?metric=NDCG%403>): Higher is better; unit: PERCENT.

- [NDCG@5](<https://www.sota2.com/research/sota/text-classification-on-eur-lex.md?metric=NDCG%405>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision@1 | Result date | Report paper |
| --- | --- | --- | --- |
| NLP-Cap | 80.2 | Not recorded | 68fa65e01e209131cea0d09c |
| XML-CNN | 75.65 | Not recorded | 68fa65e01e209131cea0d09c |
| PD-Sparse | 72.1 | Not recorded | 68fa65e01e209131cea0d09c |
| FastText | 71.51 | Not recorded | 68fa65e01e209131cea0d09c |
| CNN-Kim | 68.35 | Not recorded | 68fa65e01e209131cea0d09c |
| FastXML | 68.12 | Not recorded | 68fa65e01e209131cea0d09c |
| Bow-CNN | 64.99 | Not recorded | 68fa65e01e209131cea0d09c |

### NLP-Cap

Precision@1: 80.2. Result ID: 698ccf8c8b517eb4331ce5de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65e01e209131cea0d09c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e01e209131cea0d09c.md>)

[Implementation](<http://bit.ly/311Dcod>)

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

### XML-CNN

Precision@1: 75.65. Result ID: 698ccf8c8b517eb4331ce5dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65e01e209131cea0d09c.md>)

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

### PD-Sparse

Precision@1: 72.1. Result ID: 698ccf8c8b517eb4331ce5d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65e01e209131cea0d09c.md>)

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

### FastText

Precision@1: 71.51. Result ID: 698ccf8c8b517eb4331ce5da.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65e01e209131cea0d09c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62a21e209131ce9fa626.md>)

[Implementation](<https://github.com/facebookresearch/fastText>)

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

### CNN-Kim

Precision@1: 68.35. Result ID: 698ccf8c8b517eb4331ce5dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65e01e209131cea0d09c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa617c1e209131ce9f4631.md>)

[Implementation](<https://code.google.com/p/word2vec/>)

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

### FastXML

Precision@1: 68.12. Result ID: 698ccf8c8b517eb4331ce5d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65e01e209131cea0d09c.md>)

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

### Bow-CNN

Precision@1: 64.99. Result ID: 698ccf8c8b517eb4331ce5db.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65e01e209131cea0d09c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61ca1e209131ce9f5e8d.md>)

[Implementation](<http://riejohnson.com/cnn_download.html>)

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.