KPQA: A Metric for Generative Question Answering Using Word Weights

For the automatic evaluation of Generative Question Answering (genQA) systems, it is essential to assess the correctness of the generated answers. However, n-gram similarity metrics, which are widely used to compare generated texts and references, are prone to misjudge fact-based assessments. Moreover, there is a lack of benchmark datasets to measure the quality of metrics in terms of the correctness. To study a better metric for genQA, we collect high-quality human judgments of correctness on two standard genQA datasets. Using our human-evaluation datasets, we show that existing metrics based on n-gram similarity do not correlate with human judgments. To alleviate this problem, we propose a new metric for evaluating the correctness of genQA. Specifically, the new metric assigns different weights on each token via keyphrase prediction, thereby judging whether a predicted answer sentence captures the key meaning of the human judge's ground-truth. Our proposed metric shows a significantly higher correlation with human judgment than widely used existing metrics.