论文标题
关于神经机译的推理校准
On the Inference Calibration of Neural Machine Translation
论文作者
论文摘要
旨在使模型预测等于真正的正确性度量的置信校准对于神经机器翻译(NMT)很重要,因为它能够在生成的输出中提供有用的翻译错误指标。虽然先前的研究表明,在基地真相训练数据上对经过标签平滑训练的NMT模型进行了良好的校准,但由于训练和推理之间的差异,在推断期间,误校准仍然对NMT仍然是一个严重的挑战。通过仔细设计三个语言对的实验,我们的工作提供了对校准与翻译性能之间的相关性以及误导的语言特性之间相关性的深入分析,并报告了许多有趣的发现,可以帮助人类更好地分析,理解和改善NMT模型。基于这些观察结果,我们进一步提出了一种新的渐变标签平滑方法,可以提高推理校准和翻译性能。
Confidence calibration, which aims to make model predictions equal to the true correctness measures, is important for neural machine translation (NMT) because it is able to offer useful indicators of translation errors in the generated output. While prior studies have shown that NMT models trained with label smoothing are well-calibrated on the ground-truth training data, we find that miscalibration still remains a severe challenge for NMT during inference due to the discrepancy between training and inference. By carefully designing experiments on three language pairs, our work provides in-depth analyses of the correlation between calibration and translation performance as well as linguistic properties of miscalibration and reports a number of interesting findings that might help humans better analyze, understand and improve NMT models. Based on these observations, we further propose a new graduated label smoothing method that can improve both inference calibration and translation performance.