首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 91 毫秒
1.
基于转移的音字转换纠错规则获取技术   总被引:4,自引:1,他引:3  
文中描述了一种在音字转换系统中从规模不限的在线文本中自动获取纠错规则的机器学习技术。该技术从音字转换结果中自动获取误转换结果及其相应的上下文信息,从而生成转移规则集。该转移规则集应用于音字转换的后处理模块,使音字转换系统率进一步提高,并使系统具备了很强的灵活性和可扩展性。  相似文献   

2.
李奕  施鸿宝 《软件学报》1996,7(7):435-441
本文为解决知识系统构造过程中瓶颈问题--知识获取,提出了一种基于神经网络NN的自动获取多级推理产生规则的N-4方法,该方法采用了特有的NN结构模型和相应的学习算法,使得NN在学习过程中动态确定隐层节点数的同时,也产生了样例集中没有定义的新概念,学习后的NN能用本文提出的转换算法转换成推理网络,最终方便地得到了产生式规则集。  相似文献   

3.
李奕  施鸿宝 《软件学报》1996,7(7):435-441
本文为解决知识系统构造过程中的瓶颈问题──知识获取,提出了一种基于神经网络NN(neuralnetwork)的自动获取多级推理产生式规则的N-R方法,该方法采用了特有的NN结构模型和相应的学习算法,使得NN在学习过程中动态确定隐层节点数的同时,也产生了样例集中没有定义的新概念,学习后的NN能用本文提出的转换算法转换成推理网络,最终方便地得到产生式规则集.  相似文献   

4.
在英语语音合成中,由于英语有着几乎无限多的词汇,我们不可能创建包含所有词汇的词库。因而对于未包含在词库中的英语单词,通过“字素转换成音素(G2P)”算法自动生成其音标是一个最好的解决办法。为此,论文提出了一种动态有限泛化法(DFGA)的机器学习算法,用于进行字素/音素转换规则的学习。用于学习的词典库有27040个单词,其中90%的词用于规则学习,剩下的10%用于测试。经过10轮交叉验证,学习集和测试集的平均字素转换正确率为99.78%和93.14%,平均单词转换正确率为99.56%和73.51%。  相似文献   

5.
章森 《计算机学报》2007,30(7):1145-1153
汉语音字转换是中文键盘输入、汉语语音识别和中文信息处理的基础,也是一个非常具有挑战性的问题.文中分析了汉语音字转换的研究现状和存在的问题,提出了基于混合字词网格的汉语音字转换方法,给出了系统实现的架构,研究了混合2-gram模型的有关问题以及字词网格的求解算法,最后讨论了自动预测与系统学习功能的实现.在此基础上设计了原型系统并与Windows XP上的微软拼音输入系统进行了比较,在拼音到汉字的自动转换正确率方面有显著的提高.  相似文献   

6.
基于转换的时间-事件关系映射   总被引:5,自引:5,他引:0  
近些年来,中文时间信息抽取和处理已经变得越来越重要。然而,很少有研究者关注中文文本中事件信息所对应的时间信息的识别和分析。本文的目的就是确定文本中时间信息和事件信息之间的映射关系。区别于传统的基于规则的方法,本文采用了一种机器学习的方法—基于转换的错误驱动学习—来确定事件相应的时间表达,这种学习算法可以自动的获取和改进规则。使用训练得到的转换规则集后,系统的时间-事件映射错误率减少了9.74%,实验结果表明本系统对基于规则的方法有很好的改进效果。  相似文献   

7.
介绍了一个基于知识刺绣编程系统。描术字该系统的结构,数据结构和主要实现技术,该系统融合了图象处理,人工智能和计算机辅助设计等多种技术,引入了丰富的刺绣知识、编针规则和有效的推理机制,具有自动推理编针能力,实现了图案处理,编针,优化和数据转换的一体化与自动化,提高了刺绣编程质量和效率。  相似文献   

8.
提出了一种基于迭代的有限状态转录机的字素音素转换学习语料库的自动生成算法,针对一个德语单词及其音标进行基于形态规则和语音规则的迭代,最终将字素和音素完全一一对应起来。经过抽样测试,算法的正确率可以达到98.6%。  相似文献   

9.
形音匹配是指字素与音素相互转换的过程,它是语音识别、语音合成的基础.许多研究学者采用深度学习模型来提高形音匹配的准确率,但所得到的匹配模式比较复杂,不利于人的学习.针对上述问题,提出一种基于HMM的时序与模式可视分析方法,用于分析窗口大小与方向对字素发音的影响,以获取得到高频发音模式.将模式与机器学习方法相结合以更好地揭示形音匹配的隐藏规律,且对不同字素的影响模式进行比较分析.该方法可以有效提高学习者对单词的解码能力和拼写能力.  相似文献   

10.
一种多知识源汉语语言模型的研究与实现   总被引:7,自引:0,他引:7  
针对汉语语言模型中知识获取不足的问题,提出了一种统计与多种形式规则信息结合的机制,将规则的表示量化,提出语法语义规则的概念,通过扩充词网络,对其于最大可能性的n元概率值合理调整,将短语构成规则,二元语法语义规则,最少分词原则等融入统计模型框架,构成多知识源语言模型,模型应用于智能拼音汉字转换系统,明显提高了音字转换正确率,并适于处理长距离和递归语言现象。  相似文献   

11.
基于自动子空间划分的高光谱数据特征提取   总被引:7,自引:0,他引:7  
针对遥感高光谱图像数据量大、维数高的特点,提出了一种自动子空间划分方法用于高光谱图像数据量减小处理。该方法主要包括3个处理步骤:数据空间划分,子空间主成分分析和基于类别可分性准则的特征选择。该方法充分利用了高光谱图像各波段数据之间的局部相关性,将整个数据划分为若干个具有较强相关性的独立子空间,然后在子空间内利用主成分分析进行特征提取,根据各类地物间的类别可分性选择有效特征,最后利用地物分类来验证该方法的有效性。实验结果表明,该方法能够有效地实现高光谱图像数据维数减小和特征提取,同现有的自适应子空间分解方法和分段主成分变换方法相比,该方法所提取的特征用于分类时能获得较好的分类精度。利用该方法进行处理,当高光谱数据维数降低了90%时,9类地物分类实验的总体分类精度可以达到80.2%。  相似文献   

12.
Principal component analysis (PCA) is one of the most commonly adopted feature reduction techniques in remote sensing image analysis. However, it may overlook subtle but useful information if applied directly to the analysis of hyperspectral data, especially for discriminating between different vegetation types. In order to accurately map an invasive plant species (horse tamarind, Leucaena leucocephala) in southern Taiwan using Hyperion hyperspectral imagery, this study developed a spectrally segmented PCA based on the spectral characteristics of vegetation over different wavelength regions. The developed algorithm can not only reduce the dimensionality of hyperspectral imagery but also extracts helpful information for differentiating more effectively the target plant species from other vegetation types. Experiments conducted in this study demonstrated that the developed algorithm performs better than correlation‐based segmented principal component transformation (SPCT) and conventional PCA (overall accuracy: 86%, 76%, 66%; kappa value: 0.81, 0.69, 0.57) in detecting the target plant species, as well as mapping other vegetation covers.  相似文献   

13.
We evaluated the performance of airborne HyperSpecTIR (HST) images for detecting and classifying the invasive riparian vegetation saltcedar along the Muddy River in Clark County, Nevada. HyperSpecTIR image reflectance spectra (227 bands, 450–2450 nm) were acquired for the following four vegetation covers: invasive saltcedar, native honey mesquite, grassland patches and crops. We compared five feature reduction approaches: band selection based on Jeffreys–Matusita distance, principal component analysis (PCA), minimum noise fraction (MNF), segmented principal component transform (SPCT) and segmented minimum noise fraction (SMNF). In addition, maximum likelihood (ML) and two spectral angle mapper (SAM) classifiers were applied to all extracted bands or features. Classification accuracies were compared among all classification approaches. Although the overall accuracy of maximal likelihood classifiers generally surpassed that of SAM classifiers, the highest overall accuracy was achieved by a SMNF-SAM combination with adjusted angular thresholds for classes. We concluded that high spectral and spatial resolution imagery can be used to detect and classify invasive saltcedar in this arid area.  相似文献   

14.
移动学习作为一种新型的学习方式正成为研究热点,而基于移动学习的学科主题学习资源相对缺乏。本文阐述了移动学习的概念及特点、主题学习、学科主题学习资源的理论基础,分析了基于移动学习的学科主题学习资源设计的基本原则,最后构建了基于移动学习的学科主题学习资源的设计框架。  相似文献   

15.
With the rapid development of Internet technologies, the conventional computer-assisted learning (CAL) is gradually moving toward to web-based learning. Additionally, instructors typically base their teaching methods to simultaneously interact with all learners in a class based on their professional disciplines in the traditional classroom learning. However, the requirements of individual learners are frequently ignored in the traditional classroom learning. Compared to the conventional classroom learning, individual learners are the focus in web-based learning environments and many web-based learning systems provide personalized learning mechanisms for individual learners. One key problem is that learners have to frequently interact with web-based learning systems even though they lack instructors to monitor their learning attitudes and behavior during learning processes. Hence, a learner’s ability to self-regulated learning is clearly an important factor affecting learning performance in a web-based learning environment. Self-regulated learning is a goal-oriented learning strategy that is very suited to self-managed learning to promote learning performance of individual learners in a web-based learning environment. However, how to assist learners in cultivating self-regulated learning abilities efficiently is an important research issue in the self-regulated learning field. This study presents a novel personalized e-learning system with self-regulated learning assisted mechanisms that help learners enhance their self-regulated learning abilities. The proposed self-regulated learning mechanisms assist learners in becoming lifelong learners who have autonomous self-regulated learning abilities. Additionally, four self-regulated learning types, based on a self-regulated learning competence index and self-regulated learning performance index, are also proposed. Experimental results demonstrate that the proposed self-regulated learning assisted mechanisms aid learners by speeding up their acquisition of self-regulated learning abilities in a personalized e-learning system, and help their learning performance.  相似文献   

16.
毕松  刁奇  柴小丰  韩存武 《计算机应用》2017,37(8):2229-2233
针对生物神经细胞所具有的非联合型学习机制,设计了具有非联合型学习机制的新型神经元模型——学习神经元。首先,研究了非联合型学习机制中习惯化学习机制和去习惯化学习机制的简化描述;其次,建立了习惯化和去习惯化学习机制的数学模型;最后,基于经典的M-P(McCulloch-Pitts)神经元模型,提出了具有习惯化和去习惯化学习能力的新型神经元模型——学习神经元。经仿真实验验证,学习神经元具有典型的习惯化和去习惯化学习能力,为构建新型神经网络提供良好的基础。  相似文献   

17.
Abstract   A field experiment compares the effectiveness and satisfaction associated with technology-assisted learning with that of face-to-face learning. The empirical evidence suggests that technology-assisted learning effectiveness depends on the target knowledge category. Building on Kolb's experiential learning model, we show that technology-assisted learning improves students' acquisition of knowledge that demands abstract conceptualization and reflective observation but adversely affects their ability to obtain knowledge that requires concrete experience. Technology-assisted learning better supports vocabulary learning than face-to-face learning but is comparatively less effective in developing listening comprehension skills. In addition, according to empirical tests, perceived ease of learning and learning community support significantly predict both perceived learning effectiveness and learning satisfaction. Overall, the results support our hypotheses and research model and suggest instructors should consider the target knowledge when considering technology-assisted learning options or designing a Web-based course. In addition, a supportive learning community can make technology-assisted learning easier for students and increase their learning satisfaction.  相似文献   

18.
Current trends clearly indicate that online learning has become an important learning mode. However, no effective assessment mechanism for learning performance yet exists for e-learning systems. Learning performance assessment aims to evaluate what learners learned during the learning process. Traditional summative evaluation only considers final learning outcomes, without concerning the learning processes of learners. With the evolution of learning technology, the use of learning portfolios in a web-based learning environment can be beneficially adopted to record the procedure of the learning, which evaluates the learning performances of learners and produces feedback information to learners in ways that enhance their learning. Accordingly, this study presents a mobile formative assessment tool using data mining, which involves six computational intelligence theories, i.e. statistic correlation analysis, fuzzy clustering analysis, grey relational analysis, K-means clustering, fuzzy association rule mining and fuzzy inference, in order to identify the key formative assessment rules according to the web-based learning portfolios of an individual learner for the performance promotion of web-based learning. Restated, the proposed method can help teachers to precisely assess the learning performance of individual learner utilizing only the learning portfolios in a web-based learning environment. Hence, teachers can devote themselves to teaching and designing courseware, since they save a lot of time in measuring learning performance. More importantly, teachers can understand the main factors influencing learning performance in a web-based learning environment based on the interpretable learning performance assessment rules obtained. Experimental results indicate that the evaluation results of the proposed scheme are very close to those of summative assessment results and the factor analysis provides simple and clear learning performance assessment rules. Furthermore, the proposed learning feedback with formative assessment can clearly promote the learning performances and interests of learners.  相似文献   

19.
本文以什么是机器学习、机器学习的发展历史和机器学习的主要策略这一线索,对机器学习进行系统性的描述。接着,着重介绍了流形学习、李群机器学习和核机器学习三种新型的机器学习方法,为更好的研究机器学习提供了新的思路。  相似文献   

20.
We study and compare different neural network learning strategies: batch-mode learning, online learning, cyclic learning, and almost-cyclic learning. Incremental learning strategies require less storage capacity than batch-mode learning. However, due to the arbitrariness in the presentation order of the training patterns, incremental learning is a stochastic process; whereas batch-mode learning is deterministic. In zeroth order, i.e., as the learning parameter eta tends to zero, all learning strategies approximate the same ordinary differential equation for convenience referred to as the "ideal behavior". Using stochastic methods valid for small learning parameters eta, we derive differential equations describing the evolution of the lowest-order deviations from this ideal behavior. We compute how the asymptotic misadjustment, measuring the average asymptotic distance from a stable fixed point of the ideal behavior, scales as a function of the learning parameter and the number of training patterns. Knowing the asymptotic misadjustment, we calculate the typical number of learning steps necessary to generate a weight within order epsilon of this fixed point, both with fixed and time-dependent learning parameters. We conclude that almost-cyclic learning (learning with random cycles) is a better alternative for batch-mode learning than cyclic learning (learning with a fixed cycle).  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号