The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Group work, in certain circumstances, could encourage peer learning and provide the learners an opportunity to clarify and refine their knowledge. However, randomly grouping learners of different level of knowledge and activeness could decrease the effectiveness of a group. In this paper, we present a criterion for recommending the formation of groups of learners. This criterion is based on traces...
Sentiment classification has been a very hot topic in the field of natural language processing (NLP) and understanding in recent years. Recurrent neural networks (RNN) is a widely used tool to deal with the classification problem of variable-length sentences. The standard RNN can only access the preceding context of a sentence. In this paper, a new architecture termed Comprehensive Attention Recurrent...
Community-based Question Answering (CQA) services are becoming popular as the public gets used to look for help and obtain information. Existing CQA services try to recommend someone for answering new questions. On the other hand, people are allowed to exchange information and experience using various collaborative tools. It would be interesting to combine the two approaches to increase the reliability...
Users leave traces when they participate in activities in a collaborative digital environment. These traces in return offer a clue for recommending a user by competency on a subject. This mechanism helps further collaboration because knowing the specialization of users ameliorates distributing tasks reasonably. In this article we propose a semantic model containing activity, trace of interaction and...
These traces in return offer a clue whether a user is competent enough on a subject. This helps further collaboration because knowing the specialization of users helps to distribute tasks reasonably. In this article, we propose a semantic model of traces and analyze classified traces using a Bayes classifier. We exploit the results to offer recommendation on competent users accordingly.
In order to achieve individual or collective goals, users in informational environments collaborate to integrate intellectual resources and knowledge. Thanks to informational environments, users can better organize, realize and record collaboration. Every activity produces a set of traces. Such traces can be recorded and classified, based on a model of traces. With the help of a model of competency,...
Results diversification for keyword search on XML documents has attracted considerable attentions from research community in recent years. Though search results were diversified from different perspectives in the existing methods, the effects were still far away from satisfactory. This paper proposes a new way to diversify search results according to the semantic information of central entities which...
This paper, on the basis of the theories and the fruits of Old Chinse Phonology, uses graph theory and method to describe the initial and rhyme relationships of Old Chinese. The Euclidean distance on the 2-dimensional plane is used to describe the distance of different relationships between words' sounds in the phonological harmony. Although the model is still in its infancy and there is a lot of...
This paper, based on the theories and fruits of Old Chinese Phonology, uses the graph model in mathematics as the method to describe the initial-rhyme relationships of Old Chinese, and the Euclidean distance on 2-dimensional plane to represent the distance between sounds in the phonological harmony. Although the model is still in its infancy and there is still a lot of room for refinement and development...
In this paper, a formal description of knowledge element is given. On the basis of the formal description, a preliminary research about knowledge element acquisition method of emergency management system is proposed. For the characteristics of emergency management knowledge which is multi-field, multidisciplinary, multi-granularity and multi-dimensional, the knowledge element acquisition method is...
We present an approach to recognizing sentiment polarity in Chinese reviews based on topic sentiment sentences. Considering the features of Chinese reviews, we firstly identify the topic of a review using an n-gram matching approach. To extract candidate topic sentiment sentences, we compute the semantic similarity between a given sentence and the ascertained topic and meanwhile determine whether...
The main considerations in the existing XML data dependency models are the structural relevancies of XML nodes but not the information relevancies in XML data which derive from the real world. In this paper, we propose an XML data dependency model (XDDM) based on entity segments. Our main objective is to make XML data dependencies in XDDM match the information relevancies derived from the real world.
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.