论文标题
Nubia：基于神经的互换性评估器文本生成评估器
NUBIA: NeUral Based Interchangeability Assessor for Text Generation
论文作者
论文摘要
我们提出了Nubia，这是一种仅使用机器学习模型作为核心组件的文本生成自动评估指标的方法。典型的努比亚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的实施，该实施优于目前用于评估机器翻译，摘要和略微超过/匹配的最先进的指标的指标，该指标与人类对WMT细分级直接评估任务的判断，句子级别级别，句子级别排名和图像字幕评估有关。实施的模型是模块化的，可以解释的，并且可以随着时间的流逝而不断改进。
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.
