# Response Selection on MWOZ 2.1 Source: [Response Selection on MWOZ 2.1]() Collection index: [llms.txt]() Data updated: 2026-02-27T08:21:54.020Z Evaluation of model performance in selecting the appropriate response given a dialogue context from the MWOZ 2.1 dataset, measured using 1-to-100 and 3-to-100 accuracy metrics. 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 | Response Selection | | Dataset (including any stated split) | MWOZ 2.1 | | Metric | Accuracy (1/100) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [Accuracy (1/100)](): Higher is better; unit: PERCENT. - [Accuracy (3/100)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy (1/100) | Result date | Report paper | | --- | --- | --- | --- | | FutureTOD | 68.5 | Not recorded | 68fa6fcd1e209131cea47827 | | TOD-BERT | 65.8 | Not recorded | 68fa6fcd1e209131cea47827 | | SimCSE | 64.2 | Not recorded | 68fa6fcd1e209131cea47827 | | DSE | 63.3 | Not recorded | 68fa6fcd1e209131cea47827 | | FutureTOD | 50 | Not recorded | 68fa6fcd1e209131cea47827 | | BERT-mlm | 48.1 | Not recorded | 68fa6fcd1e209131cea47827 | | BERT | 47.5 | Not recorded | 68fa6fcd1e209131cea47827 | | SimCSE | 37.2 | Not recorded | 68fa6fcd1e209131cea47827 | | FutureTOD | 35.8 | Not recorded | 68fa6fcd1e209131cea47827 | | DialoGPT | 35.7 | Not recorded | 68fa6fcd1e209131cea47827 | | DSE | 24.8 | Not recorded | 68fa6fcd1e209131cea47827 | | BERT-mlm | 22.3 | Not recorded | 68fa6fcd1e209131cea47827 | | BERT | 20.9 | Not recorded | 68fa6fcd1e209131cea47827 | | SimCSE | 17.2 | Not recorded | 68fa6fcd1e209131cea47827 | | BERT-mlm | 13 | Not recorded | 68fa6fcd1e209131cea47827 | | DSE | 7.9 | Not recorded | 68fa6fcd1e209131cea47827 | | BERT | 7.8 | Not recorded | 68fa6fcd1e209131cea47827 | ### FutureTOD Accuracy (1/100): 68.5. Result ID: 69a1540d35dfcabb00e64d23. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"Full Data"}. This record does not assert independent reproduction. ### TOD-BERT Accuracy (1/100): 65.8. Result ID: 69a1540d35dfcabb00e64d21. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training data setting":"Full Data"}. This record does not assert independent reproduction. ### SimCSE Accuracy (1/100): 64.2. Result ID: 69a1540d35dfcabb00e64d20. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"Full Data"}. This record does not assert independent reproduction. ### DSE Accuracy (1/100): 63.3. Result ID: 69a1540d35dfcabb00e64d22. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training data setting":"Full Data"}. This record does not assert independent reproduction. ### FutureTOD Accuracy (1/100): 50. Result ID: 69a1540d35dfcabb00e64d1c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"10% Data"}. This record does not assert independent reproduction. ### BERT-mlm Accuracy (1/100): 48.1. Result ID: 69a1540d35dfcabb00e64d1f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"Full Data"}. This record does not assert independent reproduction. ### BERT Accuracy (1/100): 47.5. Result ID: 69a1540d35dfcabb00e64d1d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"Full Data"}. This record does not assert independent reproduction. ### SimCSE Accuracy (1/100): 37.2. Result ID: 69a1540d35dfcabb00e64d1a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"10% Data"}. This record does not assert independent reproduction. ### FutureTOD Accuracy (1/100): 35.8. Result ID: 69a1540d35dfcabb00e64d17. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"1% Data"}. This record does not assert independent reproduction. ### DialoGPT Accuracy (1/100): 35.7. Result ID: 69a1540d35dfcabb00e64d1e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training data setting":"Full Data"}. This record does not assert independent reproduction. ### DSE Accuracy (1/100): 24.8. Result ID: 69a1540d35dfcabb00e64d1b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training data setting":"10% Data"}. This record does not assert independent reproduction. ### BERT-mlm Accuracy (1/100): 22.3. Result ID: 69a1540d35dfcabb00e64d19. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"10% Data"}. This record does not assert independent reproduction. ### BERT Accuracy (1/100): 20.9. Result ID: 69a1540d35dfcabb00e64d18. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"10% Data"}. This record does not assert independent reproduction. ### SimCSE Accuracy (1/100): 17.2. Result ID: 69a1540d35dfcabb00e64d15. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"1% Data"}. This record does not assert independent reproduction. ### BERT-mlm Accuracy (1/100): 13. Result ID: 69a1540d35dfcabb00e64d14. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"1% Data"}. This record does not assert independent reproduction. ### DSE Accuracy (1/100): 7.9. Result ID: 69a1540d35dfcabb00e64d16. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Training data setting":"1% Data"}. This record does not assert independent reproduction. ### BERT Accuracy (1/100): 7.8. Result ID: 69a1540d35dfcabb00e64d13. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Training data setting":"1% Data"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.