arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1805.04604cs.CL
收藏

神经语义解析的置信度建模

Confidence Modeling for Neural Semantic Parsing

University of Edinburgh(爱丁堡大学);Microsoft Research(微软研究院)

Li Dong, Chris Quirk, Mirella Lapata

摘要:

在这项工作中,我们专注于建立在序列到序列模型上的神经语义解析器的置信度建模。我们概述了不确定性的三个主要原因,并设计了各种指标来量化这些因素。然后,这些度量用于估计置信度分数,该置信度分数指示模型预测是否可能是正确的。除了置信度估计之外,我们还确定输入的哪些部分有助于不确定的预测,允许用户解释他们的模型,并验证或改进其输入。实验结果表明,我们的信心模型显着优于广泛使用的方法,依赖于后验概率,并提高了解释的质量相比,简单地依赖于注意力分数。

英文摘要:

In this work we focus on confidence modeling for neural semantic parsers which are built upon sequence-to-sequence models. We outline three major causes of uncertainty, and design various metrics to quantify these factors. These metrics are then used to estimate confidence scores that indicate whether model predictions are likely to be correct. Beyond confidence estimation, we identify which parts of the input contribute to uncertain predictions allowing users to interpret their model, and verify or refine its input. Experimental results show that our confidence model significantly outperforms a widely used method that relies on posterior probability, and improves the quality of interpretation compared to simply relying on attention scores.

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。

↑