# Word Boundary Recovery on MuCGEC-based learner Chinese benchmark

Source: [Word Boundary Recovery on MuCGEC-based learner Chinese benchmark](<https://www.sota2.com/research/sota/word-boundary-recovery-on-mucgec-based-learner-chinese-benchmark>)

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

Data updated: 2026-05-28T09:01:57.952Z

Evaluation of word boundary recovery performance on the MuCGEC-based learner Chinese benchmark, reporting metrics such as Token F1.

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 | word boundary recovery |
| Dataset (including any stated split) | MuCGEC-based learner Chinese benchmark |
| Metric | Token F1 |
| Unit | PERCENT |
| 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

- [Token F1](<https://www.sota2.com/research/sota/word-boundary-recovery-on-mucgec-based-learner-chinese-benchmark.md?metric=Token%20F1>): Higher is better; unit: PERCENT.

- [Delta Previous](<https://www.sota2.com/research/sota/word-boundary-recovery-on-mucgec-based-learner-chinese-benchmark.md?metric=Delta%20Previous>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Token F1 | Result date | Report paper |
| --- | --- | --- | --- |
| Similarity-based projection | 99.16 | Not recorded | 6a17cc02dbd7150506f81246 |
| Identical-character projection | 98.99 | Not recorded | 6a17cc02dbd7150506f81246 |
| Direct segmentation | 98.91 | Not recorded | 6a17cc02dbd7150506f81246 |

### Similarity-based projection

Token F1: 99.16. Result ID: 6a1803c6fbc373592c11e504.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc02dbd7150506f81246.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc02dbd7150506f81246.md>)

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

### Identical-character projection

Token F1: 98.99. Result ID: 6a1803c6fbc373592c11e503.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc02dbd7150506f81246.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc02dbd7150506f81246.md>)

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

### Direct segmentation

Token F1: 98.91. Result ID: 6a1803c6fbc373592c11e502.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc02dbd7150506f81246.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.