# Intra-turn Relation Prediction on CMV (test) Source: [Intra-turn Relation Prediction on CMV (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:15.817Z Evaluation of Intra-turn Relation Prediction performance on the test split of the CMV dataset, measured using Precision, Recall, and F Score. 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 | Intra-turn Relation Prediction | | Dataset (including any stated split) | CMV (test) | | Metric | Precision | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 14 of 14 | | 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](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precision | Result date | Report paper | | --- | --- | --- | --- | | IMHO Context Fine-Tuned BERT + RST Ensemble | 16.7 | Not recorded | 68fa676f1e209131cea1636b | | IMHO Context Fine-Tuned BERT + RST Ensemble | 15.5 | Not recorded | 68fa676f1e209131cea1636b | | IMHO Context Fine-Tuned BERT | 14.3 | Not recorded | 68fa676f1e209131cea1636b | | IMHO Context Fine-Tuned BERT | 13.2 | Not recorded | 68fa676f1e209131cea1636b | | BERT (Devlin et al. 2019) | 12 | Not recorded | 68fa676f1e209131cea1636b | | BERT (Devlin et al. 2019) | 11 | Not recorded | 68fa676f1e209131cea1636b | | Morio and Fujita (2018) | 10 | Not recorded | 68fa676f1e209131cea1636b | | Menini et al. (2018) + RST Features | 7.4 | Not recorded | 68fa676f1e209131cea1636b | | Menini et al. (2018) | 7 | Not recorded | 68fa676f1e209131cea1636b | | RST Features | 6.3 | Not recorded | 68fa676f1e209131cea1636b | | Menini et al. (2018) + RST Features | 6.1 | Not recorded | 68fa676f1e209131cea1636b | | Menini et al. (2018) | 5.9 | Not recorded | 68fa676f1e209131cea1636b | | RST Features | 5.7 | Not recorded | 68fa676f1e209131cea1636b | | All relations | 5 | Not recorded | 68fa676f1e209131cea1636b | ### IMHO Context Fine-Tuned BERT + RST Ensemble Precision: 16.7. Result ID: 698d35318b517eb4331fcb3a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Premise source":"Gold"}. This record does not assert independent reproduction. ### IMHO Context Fine-Tuned BERT + RST Ensemble Precision: 15.5. Result ID: 698d35318b517eb4331fcb3b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Premise source":"Predicted"}. This record does not assert independent reproduction. ### IMHO Context Fine-Tuned BERT Precision: 14.3. Result ID: 698d35318b517eb4331fcb38. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Premise source":"Gold"}. This record does not assert independent reproduction. ### IMHO Context Fine-Tuned BERT Precision: 13.2. Result ID: 698d35318b517eb4331fcb39. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Premise source":"Predicted"}. This record does not assert independent reproduction. ### BERT (Devlin et al. 2019) Precision: 12. Result ID: 698d35318b517eb4331fcb36. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Premise source":"Gold"}. This record does not assert independent reproduction. ### BERT (Devlin et al. 2019) Precision: 11. Result ID: 698d35318b517eb4331fcb37. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Premise source":"Predicted"}. This record does not assert independent reproduction. ### Morio and Fujita (2018) Precision: 10. Result ID: 698d35318b517eb4331fcb35. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Premise source":"Gold"}. This record does not assert independent reproduction. ### Menini et al. (2018) + RST Features Precision: 7.4. Result ID: 698d35318b517eb4331fcb31. [Reporting paper]() Recorded evaluation configuration: {"Premise source":"Gold"}. This record does not assert independent reproduction. ### Menini et al. (2018) Precision: 7. Result ID: 698d35318b517eb4331fcb2f. [Reporting paper]() Recorded evaluation configuration: {"Premise source":"Gold"}. This record does not assert independent reproduction. ### RST Features Precision: 6.3. Result ID: 698d35318b517eb4331fcb33. [Reporting paper]() Recorded evaluation configuration: {"Premise source":"Gold"}. This record does not assert independent reproduction. ### Menini et al. (2018) + RST Features Precision: 6.1. Result ID: 698d35318b517eb4331fcb32. [Reporting paper]() Recorded evaluation configuration: {"Premise source":"Predicted"}. This record does not assert independent reproduction. ### Menini et al. (2018) Precision: 5.9. Result ID: 698d35318b517eb4331fcb30. [Reporting paper]() Recorded evaluation configuration: {"Premise source":"Predicted"}. This record does not assert independent reproduction. ### RST Features Precision: 5.7. Result ID: 698d35318b517eb4331fcb34. [Reporting paper]() Recorded evaluation configuration: {"Premise source":"Predicted"}. This record does not assert independent reproduction. ### All relations Precision: 5. Result ID: 698d35318b517eb4331fcb2e. [Reporting paper]() Recorded evaluation configuration: {"Premise source":"Gold"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.