JaSPICE：基于谓词论元结构的图像字幕模型自动评估指标
JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models
AI总结：
针对现有n元语法类图像字幕评估指标与人类评估相关性低、日语缺乏等效指标的问题，提出基于场景图的日语评估指标JaSPICE，实验证明其与人类评估的相关性优于基线指标。
摘要：
图像字幕研究高度依赖BLEU、METEOR等自动评估指标，但这类基于n元语法的指标已被证实与人类评估的相关性较差，因此学界提出了SPICE等适用于英语的替代指标，不过其他语言尚未建立等效指标。为此，本研究提出名为JaSPICE的自动评估指标，基于场景图评估日语文本字幕。该方法从依存关系与谓词论元结构生成场景图，并利用同义词扩展图结构。我们用在STAIR Captions和PFN-PIC上训练的10个图像字幕模型开展实验，构建了包含103170条人类评估结果的Shichimi数据集。结果显示，在与人类评估的相关系数指标上，本指标优于基线指标。
英文摘要：
Image captioning studies heavily rely on automatic evaluation metrics such as BLEU and METEOR. However, such n-gram-based metrics have been shown to correlate poorly with human evaluation, leading to the proposal of alternative metrics such as SPICE for English; however, no equivalent metrics have been established for other languages. Therefore, in this study, we propose an automatic evaluation metric called JaSPICE, which evaluates Japanese captions based on scene graphs. The proposed method generates a scene graph from dependencies and the predicate-argument structure, and extends the graph using synonyms. We conducted experiments employing 10 image captioning models trained on STAIR Captions and PFN-PIC and constructed the Shichimi dataset, which contains 103,170 human evaluations. The results showed that our metric outperformed the baseline metrics for the correlation coefficient with the human evaluation.
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。
