面向问题生成的可回答性自动评估
Automatic Answerability Evaluation for Question Generation
AI总结：
本文提出PMAN指标，通过评估生成问题能否由参考答案回答来弥补BLEU等传统指标在QG任务中的不足，实验证明其可靠且与人类评估一致，并基于GPT实现达到最先进性能。
摘要：
为自然语言生成（NLG）任务开发的BLEU和ROUGE等传统自动评估指标，基于衡量生成文本与参考文本之间的n-gram重叠。对于更复杂的任务，例如问题生成（QG），这些简单指标可能不够充分，因为QG要求生成的问题能够由参考答案回答。因此，开发更精细的自动评估指标仍然是QG研究中一个亟待解决的问题。本文提出PMAN（基于提示的可回答性指标，Prompting-based Metric on ANswerability），这是一种新颖的自动评估指标，用于评估QG任务中生成的问题是否能够由参考答案回答。大量实验表明，其评估结果可靠且与人类评估一致。我们进一步将该指标应用于评估QG模型的性能，结果表明我们的指标是对传统指标的有益补充。我们实现的基于GPT的QG模型在生成可回答问题方面达到了最先进的性能。
英文摘要：
Conventional automatic evaluation metrics, such as BLEU and ROUGE, developed for natural language generation (NLG) tasks, are based on measuring the n-gram overlap between the generated and reference text. These simple metrics may be insufficient for more complex tasks, such as question generation (QG), which requires generating questions that are answerable by the reference answers. Developing a more sophisticated automatic evaluation metric, thus, remains an urgent problem in QG research. This work proposes PMAN (Prompting-based Metric on ANswerability), a novel automatic evaluation metric to assess whether the generated questions are answerable by the reference answers for the QG tasks. Extensive experiments demonstrate that its evaluation results are reliable and align with human evaluations. We further apply our metric to evaluate the performance of QG models, which shows that our metric complements conventional metrics. Our implementation of a GPT-based QG model achieves state-of-the-art performance in generating answerable questions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
