# AMR-to-text on LDC2017T10 (test) Source: [AMR-to-text on LDC2017T10 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:09:11.744Z Evaluation of AMR-to-text performance on the test split of the LDC2017T10 dataset, using chrF++, BS (F1), and MS 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 | AMR-to-text | | Dataset (including any stated split) | LDC2017T10 AMR17 (test) | | Metric | chrF++ | | 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 - [chrF++](): Higher is better; unit: PERCENT. - [BS (F1)](): Higher is better; unit: PERCENT. - [MS](): Higher is better; unit: PERCENT. ## Recorded results | Method | chrF++ | Result date | Report paper | | --- | --- | --- | --- | | T5-large + STA (2M) | 74.79 | Not recorded | 68fa6add1e209131cea2ae83 | | T5-large + STA (200K) | 74.09 | Not recorded | 68fa6add1e209131cea2ae83 | | BART-large + STA (2M) | 73.58 | Not recorded | 68fa6add1e209131cea2ae83 | | T5-large + LMA | 72.83 | Not recorded | 68fa6add1e209131cea2ae83 | | T5-large | 72.57 | Not recorded | 68fa6add1e209131cea2ae83 | | BART-large + STA (200K) | 72.26 | Not recorded | 68fa6add1e209131cea2ae83 | | BART-large + LMA | 71.14 | Not recorded | 68fa6add1e209131cea2ae83 | | BART-large | 71.06 | Not recorded | 68fa6add1e209131cea2ae83 | | T5-base | 70.81 | Not recorded | 68fa6add1e209131cea2ae83 | | T5-small | 68.78 | Not recorded | 68fa6add1e209131cea2ae83 | | BART-base | 66.65 | Not recorded | 68fa6add1e209131cea2ae83 | | Wang et al. | 65.8 | Not recorded | 68fa6add1e209131cea2ae83 | | Yao et al. | 65.6 | Not recorded | 68fa6add1e209131cea2ae83 | | Zhu et al. | 64.05 | Not recorded | 68fa6add1e209131cea2ae83 | | Mager et al. | 63.89 | Not recorded | 68fa6add1e209131cea2ae83 | | Cai and Lam | 59.4 | Not recorded | 68fa6add1e209131cea2ae83 | | Guo et al. | 57.3 | Not recorded | 68fa6add1e209131cea2ae83 | ### T5-large + STA (2M) chrF++: 74.79. Result ID: 698e4010ffc3901de09c0369. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"T5-large","Task-adaptive pretraining":"STA","Pretraining samples":"2M"}. This record does not assert independent reproduction. ### T5-large + STA (200K) chrF++: 74.09. Result ID: 698e4010ffc3901de09c0368. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"T5-large","Task-adaptive pretraining":"STA","Pretraining samples":"200K"}. This record does not assert independent reproduction. ### BART-large + STA (2M) chrF++: 73.58. Result ID: 698e4010ffc3901de09c0367. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BART-large","Task-adaptive pretraining":"STA","Pretraining samples":"2M"}. This record does not assert independent reproduction. ### T5-large + LMA chrF++: 72.83. Result ID: 698e4010ffc3901de09c0365. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"T5-large","Task-adaptive pretraining":"LMA"}. This record does not assert independent reproduction. ### T5-large chrF++: 72.57. Result ID: 698e4010ffc3901de09c0363. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"T5-large"}. This record does not assert independent reproduction. ### BART-large + STA (200K) chrF++: 72.26. Result ID: 698e4010ffc3901de09c0366. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BART-large","Task-adaptive pretraining":"STA","Pretraining samples":"200K"}. This record does not assert independent reproduction. ### BART-large + LMA chrF++: 71.14. Result ID: 698e4010ffc3901de09c0364. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BART-large","Task-adaptive pretraining":"LMA"}. This record does not assert independent reproduction. ### BART-large chrF++: 71.06. Result ID: 698e4010ffc3901de09c0360. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BART-large"}. This record does not assert independent reproduction. ### T5-base chrF++: 70.81. Result ID: 698e4010ffc3901de09c0362. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"T5-base"}. This record does not assert independent reproduction. ### T5-small chrF++: 68.78. Result ID: 698e4010ffc3901de09c0361. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"T5-small"}. This record does not assert independent reproduction. ### BART-base chrF++: 66.65. Result ID: 698e4010ffc3901de09c035f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BART-base"}. This record does not assert independent reproduction. ### Wang et al. chrF++: 65.8. Result ID: 698e4010ffc3901de09c035c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Yao et al. chrF++: 65.6. Result ID: 698e4010ffc3901de09c035d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Zhu et al. chrF++: 64.05. Result ID: 698e4010ffc3901de09c035a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Mager et al. chrF++: 63.89. Result ID: 698e4010ffc3901de09c035e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"type":"based on PLMs"}. This record does not assert independent reproduction. ### Cai and Lam chrF++: 59.4. Result ID: 698e4010ffc3901de09c035b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Guo et al. chrF++: 57.3. Result ID: 698e4010ffc3901de09c0359. [Reporting paper]() [Method origin paper]() 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.