# Text Normalization on LexNorm 2015 (test)

Source: [Text Normalization on LexNorm 2015 (test)](<https://www.sota2.com/research/sota/text-normalization-on-lexnorm-2015-test>)

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

Data updated: 2026-02-26T05:58:14.714Z

Evaluation of Text Normalization performance on the test split of the LexNorm 2015 dataset, reporting Precision, Recall, and F1 scores.

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 Normalization |
| Dataset (including any stated split) | LexNorm 2015 (test) |
| Metric | Precision |
| 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

- [Precision](<https://www.sota2.com/research/sota/text-normalization-on-lexnorm-2015-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/text-normalization-on-lexnorm-2015-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/text-normalization-on-lexnorm-2015-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| MoNoise | 93.53 | Not recorded | 68fa659e1e209131cea0b352 |
| Lexicon + LSTM | 91.36 | Not recorded | 68fa659e1e209131cea0b352 |
| Hybrid Seq2Seq (HS2S) | 90.66 | Not recorded | 68fa659e1e209131cea0b352 |
| Random Forest | 90.61 | Not recorded | 68fa659e1e209131cea0b352 |
| ANN | 90.12 | Not recorded | 68fa659e1e209131cea0b352 |

### MoNoise

Precision: 93.53. Result ID: 698cb8378b517eb4331c4292.

[Reporting paper](<https://www.sota2.com/research/paper/68fa659e1e209131cea0b352.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63b51e209131cea002ca.md>)

Recorded evaluation configuration: {"leverages additional textual resources":true}. This record does not assert independent reproduction.

### Lexicon + LSTM

Precision: 91.36. Result ID: 698cb8378b517eb4331c4290.

[Reporting paper](<https://www.sota2.com/research/paper/68fa659e1e209131cea0b352.md>)

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

### Hybrid Seq2Seq (HS2S)

Precision: 90.66. Result ID: 698cb8378b517eb4331c428e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa659e1e209131cea0b352.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa659e1e209131cea0b352.md>)

[Implementation](<https://github.com/Isminoula/TextNormSeq2Seq>)

Recorded evaluation configuration: {"Description":"Hybrid architecture combining sequence-to-sequence model for OOV cases"}. This record does not assert independent reproduction.

### Random Forest

Precision: 90.61. Result ID: 698cb8378b517eb4331c428f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa659e1e209131cea0b352.md>)

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

### ANN

Precision: 90.12. Result ID: 698cb8378b517eb4331c4291.

[Reporting paper](<https://www.sota2.com/research/paper/68fa659e1e209131cea0b352.md>)

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.