arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.09371cs.CLcs.LG
收藏

提高NLP系统选择性预报能力的研究

Towards Improving Selective Prediction Ability of NLP Systems

Arizona State University(亚利桑那州立大学)

Neeraj Varshney, Swaroop Mishra, Chitta Baral

摘要:

与其回答错误,不如说“我不能回答”。这种选择性的预测能力对于NLP系统在现实世界中的可靠部署至关重要。先前的工作已经表明,现有的选择性预测技术不能很好地执行,特别是在域外设置。在这项工作中,我们提出了一种方法,通过使用预测置信度和实例的难度得分来校准模型,从而提高模型的概率估计。使用这两个信号,我们首先注释出的实例,然后训练校准器来预测模型预测正确性的可能性。我们实例化我们的方法与自然语言推理(NLI)和重复检测(DD)的任务,并评估它在域(IID)和域外(OOD)设置。在(IID,OOD)设置中,我们表明,我们的校准器学习的表示结果在NLI和DD任务上分别比“MaxProb”(选择性预测基线)提高了(15.81%,5.64%)和(6.19%,13.9%)。

英文摘要:

It's better to say "I can't answer" than to answer incorrectly. This selective prediction ability is crucial for NLP systems to be reliably deployed in real-world applications. Prior work has shown that existing selective prediction techniques fail to perform well, especially in the out-of-domain setting. In this work, we propose a method that improves probability estimates of models by calibrating them using prediction confidence and difficulty score of instances. Using these two signals, we first annotate held-out instances and then train a calibrator to predict the likelihood of correctness of the model's prediction. We instantiate our method with Natural Language Inference (NLI) and Duplicate Detection (DD) tasks and evaluate it in both In-Domain (IID) and Out-of-Domain (OOD) settings. In (IID, OOD) settings, we show that the representations learned by our calibrator result in an improvement of (15.81%, 5.64%) and (6.19%, 13.9%) over 'MaxProb' -- a selective prediction baseline -- on NLI and DD tasks respectively.

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。

↑