可解释性

On basis of analyzing the present research situation and existing question of Web knowledge acquisition, this dissertation mainly studies the essential technologies of concept semantic generation, the common text classification methods, user profile construction and approximate query technique based on concept. The main research works are shown as follows.

本文在分析网络知识获取相关技术的研究现状和存在问题的基础上，研究了概念语义生成技术、文本分类方法、典型用户会话模板生成方法以及基于概念的近似查询技术，主要取得以下研究成果：(1)借助NMF算法的分解结果具有实现上的简便性以及分解形式和分解结果可解释性的优点，提出一种基于NMF的概念语义生成方法。

In this article, we introduce a new effective method for evaluation of DP based on generalized additive models.

研究表明，广义可加违约概率模型不仅具有很高的预测精度，而且具有良好的可解释性和计算效率。

The Geographic Information System spatial interpolation technology was applide in the assessment therefore to make the results more rational and explicable.

将地理信息系统的空间插值技术应用于评价中，可以改善结果的合理性及可解释性。

Then, we define an input variable selection criterion to select and sequent candidate variables.

定义了一种同时考虑了模糊模型的精确性和可解释性的模糊模型目标函数，用于确定模型结构。

This can improve interpretability and reduce bias.

这能够提高可解释性并减少偏差。

In data mining, lots of clustering algorithms have been developed, and most of them are limited by scalability and interpretability.

在数据挖掘研究领域，现有的大多数聚类算法都受到数据可伸缩性和结果可解释性的限制。

In addition, to discover and analyze knowledge based on concepts, this model can improve the interpretability of clustering results, and facilitate to interact with users.

另外，该模型基于概念进行知识的发现与分析，能够提高聚类结果的可解释性，便于与用户交互。

But initially the lack of precise standards made it more difficult than expected until further work on interpretability standards and middleware made the integration now seamless enough, secure and manageable while performing well.

但起初由于缺乏精确的标准，使更多的困难比预料的，直到进一步的工作，对可解释性标准，并取得了中间件一体化无缝现在不够的，安全的和可管理的，而表现良好。

The former four types of features are represented in the lexicon and are interpretable, while formal features are uninterpretable and must be checked immediately after they enter the computation, if they are strong, i.e.

前四种特征都是可解释性特征，无需得到核查；而后一种特征，即形式特征，是不可解释性特征，如果它是强特征的话，就必须在进入运算后立即被核查掉，否则会导致表达式&失败&。

Chapter 3 elucidates on the Principle of Highly Interpretable and Enjoyable Incongruities explanatory of the laughter-eliciting mechanisms of humor as linguistically related to six prototypical butts of laughter, lower degrees of defamiliarization and higher interpretability, enjoyability and high human interest value.

第三章阐述幽默致笑机制的说明性原则：高可解释度和可欣赏性不协调原则。结合此原则从语言意义和形式的角度提出并考察了六类笑的对象原型、幽默不一致现象低度陌生化和高度可解释性、以及可欣赏性和人情味因素。

The absorption and distribution of chromium were studied in ryeusing nutrient culture technique and pot experiment.

采用不同浓度K2CrO4(0，0.4，0.8和1.2 mmol/L)的Hoagland营养液处理黑麦幼苗，测定铬在黑麦体内的亚细胞分布、铬化学形态及不同部位的积累。

By analyzing theory foundation of mathematical morphology in the digital image processing, researching morphology arithmetic of the binary Image, discussing two basic forms for the least structure element: dilation and erosion.

通过分析数学形态学在图像中的理论基础，研究二值图像的形态分析算法，探讨最小结构元素的两种基本形态：膨胀和腐蚀；分析了数学形态学复杂算法的基本原理，把数学形态学的部分并行处理理念引入到家实际应用中。