# Relation Extraction on ACE 2005 (351/80/80)

Source: [Relation Extraction on ACE 2005 (351/80/80)](<https://www.sota2.com/research/sota/relation-extraction-on-ace-2005-351-80-80>)

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

Data updated: 2026-02-26T05:58:42.929Z

Evaluation of Relation Extraction performance on the ACE 2005 dataset, using the specific partition defined by (351/80/80).

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 | Relation Extraction |
| Dataset (including any stated split) | ACE 2005 (351/80/80) |
| Metric | Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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/relation-extraction-on-ace-2005-351-80-80.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/relation-extraction-on-ace-2005-351-80-80.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/relation-extraction-on-ace-2005-351-80-80.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| Li and Ji | 68.9 | Not recorded | 68fa65161e209131cea08264 |
| Hierarchical Multi-task Model | 68.66 | Not recorded | 68fa65161e209131cea08264 |
| Hierarchical Multi-task Model | 68.53 | Not recorded | 68fa65161e209131cea08264 |
| Hierarchical Multi-task Model | 65.57 | Not recorded | 68fa65161e209131cea08264 |
| Hierarchical Multi-task Model | 63.32 | Not recorded | 68fa65161e209131cea08264 |
| Hierarchical Multi-task Model | 60.47 | Not recorded | 68fa65161e209131cea08264 |
| Katiyar and Cardie | 57.9 | Not recorded | 68fa65161e209131cea08264 |
| Miwa and Bansal | 57.2 | Not recorded | 68fa65161e209131cea08264 |

### Li and Ji

Precision: 68.9. Result ID: 699ab4eb5698665ec442ac8f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

Recorded evaluation configuration: {"Model":"Li and Ji 2014"}. This record does not assert independent reproduction.

### Hierarchical Multi-task Model

Precision: 68.66. Result ID: 699ab4eb5698665ec442ac92.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

Recorded evaluation configuration: {"Setup":"(G)","Model":"EMD + RE"}. This record does not assert independent reproduction.

### Hierarchical Multi-task Model

Precision: 68.53. Result ID: 699ab4eb5698665ec442ac90.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

Recorded evaluation configuration: {"Setup":"(A)","Model":"Full Model"}. This record does not assert independent reproduction.

### Hierarchical Multi-task Model

Precision: 65.57. Result ID: 699ab4eb5698665ec442ac93.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

Recorded evaluation configuration: {"Setup":"(I)","Model":"NER + EMD + RE"}. This record does not assert independent reproduction.

### Hierarchical Multi-task Model

Precision: 63.32. Result ID: 699ab4eb5698665ec442ac94.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

Recorded evaluation configuration: {"Setup":"(L)","Model":"EMD + NER + RE + CR"}. This record does not assert independent reproduction.

### Hierarchical Multi-task Model

Precision: 60.47. Result ID: 699ab4eb5698665ec442ac91.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

Recorded evaluation configuration: {"Setup":"(D)","Model":"RE"}. This record does not assert independent reproduction.

### Katiyar and Cardie

Precision: 57.9. Result ID: 699ab4eb5698665ec442ac8d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

Recorded evaluation configuration: {"Model":"Katiyar and Cardie 2017"}. This record does not assert independent reproduction.

### Miwa and Bansal

Precision: 57.2. Result ID: 699ab4eb5698665ec442ac8e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa65161e209131cea08264.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62871e209131ce9f9ed4.md>)

Recorded evaluation configuration: {"Model":"Miwa and Bansal 2016"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
