In this paper, we propose FFCI, a framework for fine-grained summarization evaluation that comprises four elements: faithfulness (degree of factual consistency with the source), focus (precision of summary content relative to the reference), coverage (recall of summary content relative to the reference), and inter-sentential coherence (document fluency between adjacent sentences). We construct a novel dataset for focus, coverage, and inter-sentential coherence, and develop automatic methods for evaluating each of the four dimensions of FFCI based on cross-comparison of evaluation metrics and model-based evaluation methods, including question answering (QA) approaches, STS, next-sentence prediction (NSP), and scores derived from 19 pre-trained language models. We then apply the developed metrics in evaluating a broad range of summarization models across two datasets, with some surprising findings.

翻译：在本文中,我们提议FFCI,这是一个精细总结评价框架,由四个要素组成:忠诚(与来源的实际一致性程度)、重点(与参考相比摘要内容的准确性)、覆盖面(参照参考内容的摘要回顾)和实质间的一致性(相邻句子之间的文件流畅程度),我们为重点、覆盖面和内容间的一致性建立一个新的数据集,并根据评价指标的交叉比较和基于模型的评价方法,包括问题回答方法、STS、下句预测和19个预先培训的语言模型的分数,制定自动方法,评估FFCI的四个层面的每一个层面,我们随后在评价两个数据集的广泛汇总模型时采用已开发的衡量标准,并得出一些令人惊讶的结论。