the intent of this paper is to summarize and analyze the data and experience earned from a practical implementation of online language learning approach specifically targeted to Qur'anic Arabic learning. the found...
详细信息
ISBN:
(纸本)9781509045211
the intent of this paper is to summarize and analyze the data and experience earned from a practical implementation of online language learning approach specifically targeted to Qur'anic Arabic learning. the foundation of this work is based on the fact that in the current world, almost 80% of the Muslims are non-native speakers/users of Arabic language. As a religious obligation, a part of the Arabic Qur'an must be memorized by each of them to recite during the formal prayers. While for native Arabic speaking people, it is relatively easy to understand, this approach of ours aims at achieving a level of understanding of the recited Arabic words even for the non-native users. the power of information and Communications technology (ICT) is effectively used in this domain. the experience could be expanded to cover other language learning approaches;however, our web-based software does have some solid rationale-base to make it specific for Qur'anic Arabic only. Alongside presenting the gained results, we provide necessary backgrounds, theoretical analysis and modeling, and details about the practical implementation of the prototype. We discuss the design of different natural languageprocessing algorithms for analyzing the Qur'anic corpus in order to identify and extract frequently occurring common language patterns to automate the production of educational material for the system. We also present some feedback of the user community built around the initial prototype which serves as a framework for capturing requirements from the world-wide user base (for each iteration) which is an essential component for the design based research methodology of the work.
Model complexity selection is important in the task of speaker identification. A Bayesian information Criterion (BIC) based approach for model complexity selection is proposed in this paper. the speaker models are tra...
详细信息
ISBN:
(纸本)9780769532738
Model complexity selection is important in the task of speaker identification. A Bayesian information Criterion (BIC) based approach for model complexity selection is proposed in this paper. the speaker models are trained withthe speech features. then the BIC values of speaker models are calculated. In order to reduce the computation of training speaker models with different complexity, the greedy strategy is used to search the locally optimal model complexity. the experiments compare the model complexity selection effect of the proposed approach to the fixed size fashion and other model selection methods. the results demonstrate the effectiveness of the proposed approach.
this paper proposes an automatic web services composition method that satisfies the user's request efficiently. Use the method, the available services in a local repository described in OWL-S are translated into a...
详细信息
ISBN:
(纸本)9780769532738
this paper proposes an automatic web services composition method that satisfies the user's request efficiently. Use the method, the available services in a local repository described in OWL-S are translated into a set of production rules, and the dependency rules of the web services are established using interface matchmaking. We choose reasoning Petri nets (RPN) as the model of this set of production rules. then we design a web services composition reasoning algorithm based on the RPN model. the reasoning process of web services composition is accomplished more simply, quickly, and its efficiency is also improved due to the parallel operation ability of Petri net.
TagHelper is a verbal data analysis application. It is based on the use of the Weka toolkit. It is able to classify sentences as one of a set of categories previously introduced into the system. TagHelper has been use...
详细信息
ISBN:
(纸本)9789896740252
TagHelper is a verbal data analysis application. It is based on the use of the Weka toolkit. It is able to classify sentences as one of a set of categories previously introduced into the system. TagHelper has been used to support data analysis in English, German, and Chinese. TagHelper has been recently extended to support Spanish too. the Will Tools are a set of web-based learning tools able to automatically assess students' free-text answers written in Spanish or in English. In this paper, we describe a new procedure to generate a conceptual assessment course in the format required by the Will Tools automatically from web data using TagHelper in Spanish. the procedure has been successfully implemented, and two different courses have already been generated.
Withthe growth of the Semantic web and its applications, the need to use it in different languages, such as Arabic, is becoming more important. Two of the challenges withthe Semantic web technologies are the lack of...
详细信息
Withthe growth of the Semantic web and its applications, the need to use it in different languages, such as Arabic, is becoming more important. Two of the challenges withthe Semantic web technologies are the lack of multilingual support and the complexity of integrating multiple ontologies used by this technology. the objective of this paper is to present efforts that will help users who use the Arabic language to ask natural language questions and then get their semantic representation in SPARQL that allows them to be executed and get the relevant semantic results. this natural language interface makes more use of the cross-domain ontologies and hence improves the understanding of their inquiries, which is needed in some critical domains such as health and food where precise advice is essential. the approach we followed is multilingual and overcomes the limitations in the published relevant systems. Withthe proposed approach, users who speak Arabic can use the widely published ontologies in English without concern for the translation of their questions. the proposed approach will take care of matching the entered questions withthe relevant ontologies to produce their semantic web queries. the proposed approach has been implemented and empirically evaluated. the experimental results are promising, which will help in improving the awareness and usage of the Semantic web by different lingual and cultural users. (C) 2016 the Authors. Published by Elsevier B.V.
Statistical Machine Translation (SMT) is a part of Natural languageprocessing. this translates one language to another language. SMT consists of language Model (LM), Translation Model (TM) and decoder. the decoder wi...
详细信息
ISBN:
(纸本)9781467382861
Statistical Machine Translation (SMT) is a part of Natural languageprocessing. this translates one language to another language. SMT consists of language Model (LM), Translation Model (TM) and decoder. the decoder will make use of LM and TM to generate the translation. In this, probability of target language sentences is computed by LM, the given source sentence probability of the target sentence is computed by TM and maximizing the probability of translated text is done by Moses. English and Telugu parallel corpus have been used for training the system. Translation mainly depends on quality and quantity of corpus. In this, a model was proposed for translation of Telugu language to English language.
In this paper, we propose the active monitoring model for the workflow of RFID logistics management system, and besides the function of taking materials in and out, technology to handle each step for efficient logisti...
详细信息
ISBN:
(纸本)9780769532738
In this paper, we propose the active monitoring model for the workflow of RFID logistics management system, and besides the function of taking materials in and out, technology to handle each step for efficient logistics management is applied. For the inventory inspection, users take goods in and out in real time by attaching tags on each item and inspects the stored inventory rapidly with stock inspector and input the result automatically in real time. the user interface to display the optimized data process and status in real time environment has been constructed.
In this paper we carried out a bibliographic research concerning distance learning, pedagogical indexing and integration of accessibility in e-Learning platforms. then, to achieve the goals we have chosen "IMS Ac...
详细信息
ISBN:
(纸本)9781479939992
In this paper we carried out a bibliographic research concerning distance learning, pedagogical indexing and integration of accessibility in e-Learning platforms. then, to achieve the goals we have chosen "IMS AccessForALL" as standard to realize our model. the model that we realized is consistent withthe standard followed. We also taken into consideration the guidelines of the WAI (web accessibilty Initiative) presented in WCAG. Finally, for the step of indexing, we started withthe creation of the XML schema, then the indexation of resources in the true sense of the term.
this paper presents our research on automatic question classification for Vietnamese using machine learning approaches. We have experimented with several machine learning algorithms utilizing two kinds of feature grou...
详细信息
Typically web pages always contain a large amount of banner ads, navigation bars, and copyright notices etc. Such irrelevant information is not part Of the main contents of the pages, they will seriously harm web mini...
详细信息
ISBN:
(纸本)9780769532738
Typically web pages always contain a large amount of banner ads, navigation bars, and copyright notices etc. Such irrelevant information is not part Of the main contents of the pages, they will seriously harm web mining and searching. In this paper, we develop and evaluate a method that utilizes boththe visual features and the semantic information to extract informative blocks. We first partition a web page into semantic blocks using vision-based page segmentation. the visual and the semantic information got by LSI (Latent Semantic Indexing) are extracted to form the feature-vector of the block. Second we manually annotate informative or uninformative labels to the blocks. the labeled blocks are used as training dataset to train a classification model. then the informative blocks can be extracted through the model. Our experiments show that the proposed EIBA (Extract Informative Block Arithmetic) is able to dramatically improve the results in near-duplicate detection and classification tasks.
暂无评论