NUBIA：基于NeUral的文本生成可互换性评估器
NUBIA: NeUral Based Interchangeability Assessor for Text Generation
摘要：
我们提出了NUBIA，一种方法来建立自动评估指标的文本生成只使用机器学习模型作为核心组件。一个典型的NUBIA模型由三个模块组成：神经特征提取器，聚合器和校准器。我们展示了NUBIA的实现优于目前用于评估机器翻译的指标，总结并略超过/匹配与WMT段级直接评估任务，字幕级排名和图像描述评估的人类判断相关的最先进的指标。实现的模型是模块化的，可解释的，并设置为随着时间的推移不断改进。
英文摘要：
We present NUBIA, a methodology to build automatic evaluation metrics for text generation using only machine learning models as core components. A typical NUBIA model is composed of three modules: a neural feature extractor, an aggregator and a calibrator. We demonstrate an implementation of NUBIA which outperforms metrics currently used to evaluate machine translation, summaries and slightly exceeds/matches state of the art metrics on correlation with human judgement on the WMT segment-level Direct Assessment task, sentence-level ranking and image captioning evaluation. The model implemented is modular, explainable and set to continuously improve over time.
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。
