Abstractive Summarization on CNNDM (test) using Pairwise Quality Metrics
18Factual Consistency (Better Count)QUALS-CONSEQ
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| QUALS-CONSEQbaseline=BART-large MLE, sample_size=100, evaluation_method=human preference (majority vote of 3)2021.05 | 18 | 7 | 75 | 42 | 22 | 36 | 5 | 6 | 89 |