Ningning Wu's research while affiliated with University of Arkansas at Little Rock and other places

... We use NLP and standardized techniques, which greatly reduces the burden of manual inspection (22,23). To the best of our knowledge, there have been a few of rule-based quality control studies of medical record, but AI research on the use of medical guidelines for disease quality control is still relatively rare (24). However, some systems or frameworks based on artificial intelligence and knowledge bases have been reported to help doctors make certain clinical decisions (11,25). ...

... The scoring rule setup requires more effort and analysis than using the OYSTER identity (Boolean) rules configuration. The scoring rule is similar to the Boolean rule which specifies a similarity function and optional data preparation function for comparing the values of identity attributes between two entity references [2], [3]. Unlike the Boolean rules in OYSTER, which uses deterministic logic for the similarity matching, the decision in the scoring rule is associated with a numerical value called a "weight" [6]. ...

... Talburt et al. [50] in their formal problem formulation described an entity identification process of determining the "best match" of a single identity fragment 1 extracted from unstructured documents from among a set of possible candidates in entity catalogs. Two of the limitations of this method are the catalog may be replete with many similar identity choices and the catalog may be incomplete, hence the correct identity is not among the choices. ...

... Indeed, it treats strict comparison between terms and considers the text as a sequence of lines. The task of disambiguation in the case of more than one record returned for an entity referenced in the document has been treated by (Wu et al., 2007) that exploited relationships between candidate entities for different fragments (a fragment is defined as entity features extracted from the document using seman- tic patterns) of the same document for identifying the identity of fragments. In contrast, our approach does not remedy ambiguity cases but it avoids them from the beginning. ...

... Education mode reformation must be adapted to the transference from single word to comprehensive sense of participation, from linear knowledge layout to the mesh nonlinear layout, from the static and dynamic to an integrated and many dimensions, from paying attention to students' external behaviors to focus attention on the students' inner experience and learning strategy training [2] . This essay hopes that using Cloud Computing and new mobile technology, integrated with teaching resources and digital resources, and going through interactive teaching network platform to offer service [3] . ...

... The research into the use of open source documents for resolving, identifying, disambiguating and/or updating entities attributes in entity catalogs or proprietary repositories has led to much of the research described in this paper [46][47] [48] [49][50] [51]. In order for organizations to effectively take advantage of the abundant information available online using their current data and analytical tools, the unstructured information must be transformed in to a structure in which the entities of interests within the text can be represented using relational database systems. ...

... Understanding which attributes are most important for any given application is a key step in any data management process (Heien, Wu, & Talburt, 2010). In the context of MDM, each entity type has a set of attributes taking on different values that describe the entities' characteristics. ...

... It is the process of extracting information from different sources, recombining them to identify patterns and deriving information from such digital sources (Grobelnik et al., 2002). Text mining applications rise to support extraction and interpretation of unstructured text format, which in its present form, does not make a suitable input to automatic processing tasks such as information retrieval, document indexing, clustering and text classification (Chiang et al., 2008). Text mining is an intuitive choice of technology particularly in the research and educational field due to its ability to discover new hidden relationships from complex and voluminous body of knowledge published in the literature (Grobelnik et al., 2002), whether in related or non-related field of research. ...