# Addressee and Response Selection on Ubuntu Multiparty Conversation Corpus v1 (test)

Source: [Addressee and Response Selection on Ubuntu Multiparty Conversation Corpus v1 (test)](<https://www.sota2.com/research/sota/addressee-and-response-selection-on-ubuntu-multiparty-conversation-corpus-v1-test>)

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

Data updated: 2026-02-26T05:22:15.497Z

Evaluation of model performance on the test split of the Ubuntu Multiparty Conversation Corpus v1, focusing on Addressee and Response Selection tasks, measured by ADR-RES, ADR, and RES 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 | Addressee and Response Selection |
| Dataset (including any stated split) | Ubuntu Multiparty Conversation Corpus v1 (test) |
| Metric | ADR-RES |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 34 of 34 |
| 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

- [ADR-RES](<https://www.sota2.com/research/sota/addressee-and-response-selection-on-ubuntu-multiparty-conversation-corpus-v1-test.md?metric=ADR-RES>): Higher is better; unit: SCALAR.

- [ADR](<https://www.sota2.com/research/sota/addressee-and-response-selection-on-ubuntu-multiparty-conversation-corpus-v1-test.md?metric=ADR>): Higher is better; unit: SCALAR.

- [RES](<https://www.sota2.com/research/sota/addressee-and-response-selection-on-ubuntu-multiparty-conversation-corpus-v1-test.md?metric=RES>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ADR-RES | Result date | Report paper |
| --- | --- | --- | --- |
| SI-RNN | 67.3 | Not recorded | 68fa63d11e209131cea00ec8 |
| SI-RNN | 65.63 | Not recorded | 68fa63d11e209131cea00ec8 |
| SI-RNN w/o joint selection | 63.4 | Not recorded | 68fa63d11e209131cea00ec8 |
| SI-RNN | 60.69 | Not recorded | 68fa63d11e209131cea00ec8 |
| SI-RNN w/ shared IGRUs | 59.47 | Not recorded | 68fa63d11e209131cea00ec8 |
| Dynamic-RNN | 54.88 | Not recorded | 68fa63d11e209131cea00ec8 |
| Dynamic-RNN | 53.85 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-Hier-RNN | 53.04 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-Hier-RNN | 51.76 | Not recorded | 68fa63d11e209131cea00ec8 |
| Dynamic-RNN | 49.8 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-Hier-RNN | 49.38 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-RNN | 49.27 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-RNN | 48.67 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-RNN | 46.99 | Not recorded | 68fa63d11e209131cea00ec8 |
| Direct-Recent+TF-IDF | 45.76 | Not recorded | 68fa63d11e209131cea00ec8 |
| Recent+TF-IDF | 37.13 | Not recorded | 68fa63d11e209131cea00ec8 |
| SI-RNN | 35.76 | Not recorded | 68fa63d11e209131cea00ec8 |
| SI-RNN | 34.09 | Not recorded | 68fa63d11e209131cea00ec8 |
| SI-RNN w/o joint selection | 32.53 | Not recorded | 68fa63d11e209131cea00ec8 |
| SI-RNN | 30.71 | Not recorded | 68fa63d11e209131cea00ec8 |
| SI-RNN w/ shared IGRUs | 28.45 | Not recorded | 68fa63d11e209131cea00ec8 |
| Dynamic-RNN | 27.19 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-Hier-RNN | 26.62 | Not recorded | 68fa63d11e209131cea00ec8 |
| Dynamic-RNN | 25.95 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-Hier-RNN | 25.83 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-Hier-RNN | 23.75 | Not recorded | 68fa63d11e209131cea00ec8 |
| Dynamic-RNN | 23.72 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-RNN | 23.49 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-RNN | 23.31 | Not recorded | 68fa63d11e209131cea00ec8 |
| Static-RNN | 21.98 | Not recorded | 68fa63d11e209131cea00ec8 |
| Direct-Recent+TF-IDF | 19.5 | Not recorded | 68fa63d11e209131cea00ec8 |
| Recent+TF-IDF | 15.44 | Not recorded | 68fa63d11e209131cea00ec8 |
| Chance | 0.62 | Not recorded | 68fa63d11e209131cea00ec8 |
| Chance | 0.12 | Not recorded | 68fa63d11e209131cea00ec8 |

### SI-RNN

ADR-RES: 67.3. Result ID: 698c0403f729bc7f68e7d3d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Implementation](<https://github.com/ryanzhumich/sirnn>)

Recorded evaluation configuration: {"T":15,"RES-CAND":2}. This record does not assert independent reproduction.

### SI-RNN

ADR-RES: 65.63. Result ID: 698c0403f729bc7f68e7d3d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Implementation](<https://github.com/ryanzhumich/sirnn>)

Recorded evaluation configuration: {"T":10,"RES-CAND":2}. This record does not assert independent reproduction.

### SI-RNN w/o joint selection

ADR-RES: 63.4. Result ID: 698c0403f729bc7f68e7d3d8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Implementation](<https://github.com/ryanzhumich/sirnn>)

Recorded evaluation configuration: {"T":15,"RES-CAND":2}. This record does not assert independent reproduction.

### SI-RNN

ADR-RES: 60.69. Result ID: 698c0403f729bc7f68e7d3d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Implementation](<https://github.com/ryanzhumich/sirnn>)

Recorded evaluation configuration: {"T":5,"RES-CAND":2}. This record does not assert independent reproduction.

### SI-RNN w/ shared IGRUs

ADR-RES: 59.47. Result ID: 698c0403f729bc7f68e7d3d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Implementation](<https://github.com/ryanzhumich/sirnn>)

Recorded evaluation configuration: {"T":15,"RES-CAND":2}. This record does not assert independent reproduction.

### Dynamic-RNN

ADR-RES: 54.88. Result ID: 698c0402f729bc7f68e7d3cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":15,"RES-CAND":2}. This record does not assert independent reproduction.

### Dynamic-RNN

ADR-RES: 53.85. Result ID: 698c0402f729bc7f68e7d3cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":10,"RES-CAND":2}. This record does not assert independent reproduction.

### Static-Hier-RNN

ADR-RES: 53.04. Result ID: 698c0402f729bc7f68e7d3c6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":15,"RES-CAND":2}. This record does not assert independent reproduction.

### Static-Hier-RNN

ADR-RES: 51.76. Result ID: 698c0402f729bc7f68e7d3c5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":10,"RES-CAND":2}. This record does not assert independent reproduction.

### Dynamic-RNN

ADR-RES: 49.8. Result ID: 698c0402f729bc7f68e7d3ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":5,"RES-CAND":2}. This record does not assert independent reproduction.

### Static-Hier-RNN

ADR-RES: 49.38. Result ID: 698c0402f729bc7f68e7d3c4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":5,"RES-CAND":2}. This record does not assert independent reproduction.

### Static-RNN

ADR-RES: 49.27. Result ID: 698c0402f729bc7f68e7d3c0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":15,"RES-CAND":2}. This record does not assert independent reproduction.

### Static-RNN

ADR-RES: 48.67. Result ID: 698c0402f729bc7f68e7d3bf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":10,"RES-CAND":2}. This record does not assert independent reproduction.

### Static-RNN

ADR-RES: 46.99. Result ID: 698c0402f729bc7f68e7d3be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":5,"RES-CAND":2}. This record does not assert independent reproduction.

### Direct-Recent+TF-IDF

ADR-RES: 45.76. Result ID: 698c0402f729bc7f68e7d3bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":15,"RES-CAND":2}. This record does not assert independent reproduction.

### Recent+TF-IDF

ADR-RES: 37.13. Result ID: 698c0402f729bc7f68e7d3ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":15,"RES-CAND":2}. This record does not assert independent reproduction.

### SI-RNN

ADR-RES: 35.76. Result ID: 698c0403f729bc7f68e7d3d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Implementation](<https://github.com/ryanzhumich/sirnn>)

Recorded evaluation configuration: {"T":15,"RES-CAND":10}. This record does not assert independent reproduction.

### SI-RNN

ADR-RES: 34.09. Result ID: 698c0403f729bc7f68e7d3d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Implementation](<https://github.com/ryanzhumich/sirnn>)

Recorded evaluation configuration: {"T":10,"RES-CAND":10}. This record does not assert independent reproduction.

### SI-RNN w/o joint selection

ADR-RES: 32.53. Result ID: 698c0403f729bc7f68e7d3d9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Implementation](<https://github.com/ryanzhumich/sirnn>)

Recorded evaluation configuration: {"T":15,"RES-CAND":10}. This record does not assert independent reproduction.

### SI-RNN

ADR-RES: 30.71. Result ID: 698c0403f729bc7f68e7d3d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Implementation](<https://github.com/ryanzhumich/sirnn>)

Recorded evaluation configuration: {"T":5,"RES-CAND":10}. This record does not assert independent reproduction.

### SI-RNN w/ shared IGRUs

ADR-RES: 28.45. Result ID: 698c0403f729bc7f68e7d3d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

[Implementation](<https://github.com/ryanzhumich/sirnn>)

Recorded evaluation configuration: {"T":15,"RES-CAND":10}. This record does not assert independent reproduction.

### Dynamic-RNN

ADR-RES: 27.19. Result ID: 698c0403f729bc7f68e7d3cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":15,"RES-CAND":10}. This record does not assert independent reproduction.

### Static-Hier-RNN

ADR-RES: 26.62. Result ID: 698c0402f729bc7f68e7d3c9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":15,"RES-CAND":10}. This record does not assert independent reproduction.

### Dynamic-RNN

ADR-RES: 25.95. Result ID: 698c0403f729bc7f68e7d3ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":10,"RES-CAND":10}. This record does not assert independent reproduction.

### Static-Hier-RNN

ADR-RES: 25.83. Result ID: 698c0402f729bc7f68e7d3c8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":10,"RES-CAND":10}. This record does not assert independent reproduction.

### Static-Hier-RNN

ADR-RES: 23.75. Result ID: 698c0402f729bc7f68e7d3c7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":5,"RES-CAND":10}. This record does not assert independent reproduction.

### Dynamic-RNN

ADR-RES: 23.72. Result ID: 698c0402f729bc7f68e7d3cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":5,"RES-CAND":10}. This record does not assert independent reproduction.

### Static-RNN

ADR-RES: 23.49. Result ID: 698c0402f729bc7f68e7d3c3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":15,"RES-CAND":10}. This record does not assert independent reproduction.

### Static-RNN

ADR-RES: 23.31. Result ID: 698c0402f729bc7f68e7d3c2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":10,"RES-CAND":10}. This record does not assert independent reproduction.

### Static-RNN

ADR-RES: 21.98. Result ID: 698c0402f729bc7f68e7d3c1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":5,"RES-CAND":10}. This record does not assert independent reproduction.

### Direct-Recent+TF-IDF

ADR-RES: 19.5. Result ID: 698c0402f729bc7f68e7d3bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":15,"RES-CAND":10}. This record does not assert independent reproduction.

### Recent+TF-IDF

ADR-RES: 15.44. Result ID: 698c0402f729bc7f68e7d3bb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"T":15,"RES-CAND":10}. This record does not assert independent reproduction.

### Chance

ADR-RES: 0.62. Result ID: 698c0402f729bc7f68e7d3b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"RES-CAND":2}. This record does not assert independent reproduction.

### Chance

ADR-RES: 0.12. Result ID: 698c0402f729bc7f68e7d3b9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa63d11e209131cea00ec8.md>)

Recorded evaluation configuration: {"RES-CAND":10}. This record does not assert independent reproduction.

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