A Cognitive Model of Semantic Network Learning

Semantic impairment in patients with Alzheimer's disease (AD) is revealed by tasks of verbal naming, verbal fluency, and semantic knowledge. Causes of the deficit remain unclear in spite of many studies to investigate whether AD patients suffer from the inability to have voluntary access to an almost intact semantic store or from its break down. Word-stem completion (WSC) tasks have been utilized in healthy subjects in order to study semantic memory and network by exploiting the possibility of the involuntary access to them. Available conflicting data refer to the presence of semantic prime in AD patients. To explore the semantic network in AD, patients were requested to complete with the first word that sprang to their mind a stem submitted immediately after presentation of the word prime, as a WSC task. Stems consisted of the three beginning letters of words that were semantically related to primes. We compared data obtained with this task from patients with mild to moderate AD with those from normal controls (NC). AD patients completed less stems (P<0.001) with the expected words than NC, suggesting a break down of the semantic network rather than a deficit in the access to the semantic store.

In this paper is proposed a method for representing semantic data and knowledge. The method is based two foundational concepts: semantic link network and adjacency model. The method allows graph presentations of semantic data and it preserves the semantic relationships between the concepts of the domain. Furthermore with the methodit is possible construct relational model of the semantically rich data. The method proposed in this paper enables the preservation of semantic relationships between elements of the domain and it produces reasoning rules for the domain knowledge. The visualization can be done by using semantic link network (1) and adjacency relation system based graph (2). Adjacency relation systems enable the restriction of search space and thus limit the search times used by queries. In addition adjacency relation systems can be also converted into relational model. In this paper the emphasis is on the construction of semantic link network and adjacency relation system based on the semantic link network. The paper is organized as follows. In the first section the related research is discussed. In the second section the basic conversion method from semantic link network to adjacency relation system is introduced. In the third section visualization method is introduced by small example. Finally concluding remarks are given.

&#x0D; &#x0D; &#x0D; This paper devoted the problem of identifying a semantic similarity degree or difference of text in cybersecurity field. The paper presents a method for comparing text documents based on the formation and comparison of the corresponding semantic networks. The directed weighted network of terms, where the nodes of such networks are key terms of the text, and edges are semantic relationships between these terms in the text are considered as a semantic network. The algorithm for formation semantic networks as one of the types of ontologies is also presented. Formation of network of term includes pre-processing of text data, extraction of key terms, construction of undirected network of terms (using the algorithm of horizontal visibility graph), determining undirected connections between terms, and further determining the directions of connections and their weight values. The Frobenius norm of the difference of matrices corresponding to the semantic networks is considered to compare the semantic networks. An identifying the critically different texts that can have similar keywords but different semantic between them is important to ensure cybersecurity. Also, the proposed approach can be helpful while solving the problem of accumulating text data semantically similar in content. In general, this approach can also be used in systems of automatic information retrieval to determine the degree of similarity or difference in the structure and semantics of texts and identify the sources of information that have a destructive impact on the information space.&#x0D; &#x0D; &#x0D;

A semantic network describing the relations between ten words has been elaborated. The raw-data for the formation of the network were 660 natural-language sentences gained in the following experiment: The ten words were presented to 12 Ss, single, in pairs, and in triplets. Ss had to form, for each given combination, a sentence containing the presented words. The sentences gained by this method were parsed and got uniform codings. Each stimulus word then has been assigned to a node, containing all words or parts of sentences to which it was related in the sentences. Nodes with similar contents have been subsumed under a higher-level node containing the relations which are common to it's constituents. The reaction times in sentence formation strongly depend on the relations between the words in the semantic network. The correlation between association strengths and the proximities between the words in the semantic network augments to 0.70. The limitations due to the purely inductive approach in the formation of the network are discussed.

Ontology learning has become a popular research field recently. But most ontology construction methods are semiautomatic, and the construction process of ontology is still a tedious and painstaking task. The cognitive model of ontology learning is an automatic model of ontology construction that simulates the process of human being recognizing the world. Induction is an important step of the model. This paper presents a strategy for the ontology induction in the cognitive model of ontology learning, which includes some generalization principles and the corresponding induction operators. It generates induction hypothesis through a series of operations. As a result, induction hypothesis are generated from the present ontology and it can generalize the existing ontology.

Ontology learning has become a popular research field recently. However, the typical ontology may not be sufficient to represent uncertainty information. Fuzzy ontology is proposed to solve the uncertainty reasoning problems. But the construction of fuzzy ontology is still a tedious and painstaking task. The cognitive model of fuzzy ontology learning is an automatic model of fuzzy ontology construction that simulates the process of human being recognizing the world. Induction is an important step of the model. In this paper, we present a strategy for the fuzzy ontology induction in the cognitive model of ontology learning which includes some generalization principles and the corresponding induction operators. It generates induction hypothesis through a series of operations. As a result, induction hypothesis are generated from the present ontology and it can generalize the existing ontology.

There has been a surge in interest and implementation of immersive virtual reality (IVR)-based lessons in education and training recently, which has resulted in many studies on the topic. There are recent reviews which summarize this research, but little work has been done that synthesizes the existing findings into a theoretical framework. The Cognitive Affective Model of Immersive Learning (CAMIL) synthesizes existing immersive educational research to describe the process of learning in IVR. The general theoretical framework of the model suggests that instructional methods which are based on evidence from research with less immersive media generalize to learning in IVR. However, the CAMIL builds on evidence that media interacts with method. That is, certain methods which facilitate the affordances of IVR are specifically relevant in this medium. The CAMIL identifies presence and agency as the general psychological affordances of learning in IVR, and describes how immersion, control factors, and representational fidelity facilitate these affordances. The model describes six affective and cognitive factors that can lead to IVR-based learning outcomes including interest, motivation, self-efficacy, embodiment, cognitive load, and self-regulation. The model also describes how these factors lead to factual, conceptual, and procedural knowledge acquisition and knowledge transfer. Implications for future research and instructional design are proposed.

Information retrieval systems can be made more effective by providing more expressive query languages for users to specify their information need. This paper argues that this can be achieved through the use of semantic relations as query primitives, and describes a new technique for extracting semantic relations from an online dictionary. In contrast to existing research, this technique involves the composition of basic semantic relations, a process akin to constrained spreading activation in semantic networks. The proposed technique is evaluated in the context of extracting semantic relations that are relevant for retrieval from a corpus of pictures.

Data-driven design is a process to reuse data sources and provide valuable information to provoke creative ideas in the stages of design. However, existing semantic networks for design creativity are built on data sources restricted to technological and scientific information. Existing studies build the edges of a semantic network on statistical or semantic relationships, which are less likely to make full use of the benefits from both types of relationships and discover implicit knowledge for design creativity. Therefore, to overcome the gaps, we constructed WikiLink, a semantic network based on Wikipedia, which is an integrated source of general knowledge and specific knowledge, with broad coverage of disciplines. The weight in WikiLink fuses both the statistic and semantic weights between concepts instead of simply one type of weight, and four algorithms are developed for inspiring new ideas. Evaluation experiments are undertaken, and the results show that the network is characterised by high coverage of terms, relationships and disciplines, which demonstrates and supports the network's effectiveness and usefulness. A demonstration and case study results indicate that WikiLink can serve as an idea generation tool for creativity in conceptual design. The source code of WikiLink and the backend data are provided open-source for more users to explore and develop.

An important obstacle to the success of the Semantic Web is that the establishment of the semantic relationship is labor-intensive. This paper proposes an automatic semantic relationship discovering approach for constructing the semantic link network. The basic premise of this work is that the semantics of a web page can be reflected by a set of keywords, and the semantic relationship between two web pages can be determined by the semantic relationship between their keyword sets. The approach adopts the data mining algorithms to discover the semantic relationships between keyword sets, and then uses deductive and analogical reasoning to enrich the semantic relationships. The proposed algorithms have been implemented. Experiment shows that the approach is feasible.

Background. The current context of increasingly complex nursing care requires a high level of clinical reasoning in nursing practice. Still, teaching clinical reasoning in nursing remains a challenge for educators in the field. Although several studies have been conducted to try to understand clinical reasoning in nursing, neither its developmental stages nor the corresponding critical milestones have been uncovered. Therefore, nursing educators cannot rely on a cognitive learning model (a description of how people learn and develop a specific competency) to facilitate the learning of this crucial competency. Objectives. This study was conducted to develop a cognitive learning model of clinical reasoning in nursing, from the beginning of education to the development of expertise, highlighting the critical milestones corresponding to each stage. Design. A descriptive design based on the think aloud method was used. Settings and participants. The study was held in one university and two associated hospitals. Individual interviews were conducted with 45 undergraduate nursing students and 21 registered nurses (RNs). Participants were asked to think aloud, using five clinical scenarios that were validated in a previous study. Analysis. Interviews were transcribed verbatim and subsequently analyzed using the protocol analysis method recommended for think aloud studies. Results. Five developmental stages and their related critical milestones were identified and used in the elaboration of a cognitive learning model for clinical reasoning in nursing: (1) internalization of the idea that nursing is a scientific profession; (2) learning to read and use scientific literature in care planning and nursing interventions; (3) learning to move from data collection to hypothesis generation to nursing interventions; (4) integrating wards’ routines and protocols; (5a) towards professional expertise or (5b) towards task-oriented practice. Conclusion. Recommendations for teaching and learning clinical reasoning in nursing during initial and continuing education in nursing are suggested.

With the development of big data, the heuristic query based on the semantic relationship network has become a hot topic, which attracts much attention. Due to the complex relationship between data records, the traditional query technologies cannot satisfy the requirements of users. To this end, this paper proposes a heuristic query method based on the semantic relationship network, which first constructs the semantic relationship model, and then expands the query based on the constructed semantic relationship network. The experiments demonstrate the reasonableness, high precision of our method.

Senses are the extensions of language and interrelations between word meanings within language and the basis of flexible language use. Computers are basically made to process symbols. Computational linguistics is to simulate part of, if not all of, the natural language competence. From the perspective of computational linguistics, this paper sheds some light on semantic formalization, and proposes tagging of senses along with tagging weight values when processing word meanings. Also, this paper makes attempts to apply sense weight values to sentence processing in computational linguistics. Keywords-semantics, sense, weight, formalization, computational linguistics I. SEMANTIC KNOWLEDGE IN LANGUAGE PROCESSING According to prototype theory, semantic knowledge is part of human’s cognitive and belief systems. Semantics is also the critical research area since its initiation in 1893 by Michael Breal, and then by Trier and Lakoff who contributes to semantic research from both the descriptive and generative perspective. In linguistic semantics, rules and principles explain how literal meaning is coded in language and how to understand the “senses” of an expression or sense-relations that hold between one word and other expressions within the same language (Ceusters et al, 1999). Language is the carrier of both thoughts and forms. Thoughts are to induce, deduce, infer and judge, while senses are the contents and basis of thoughts. Senses are not the repeated addition of forms, rather a psychological process. Semantics is the mapping of cognitive structure from language expressions. Based on concepts, which are the abstract and general categorization of objects, people can apply semantic principles, situational contexts and encyclopedic knowledge to construct cognitive schema of the outside world. With frequent interactions and cognitive strategies, limited forms can be used to express unlimited connotation of thoughts (Tesser and Leone, 1977). For example, same meanings can be expressed with different semantic forms. a) 他这个人真有意思 (funny); b) 于是人们以为他们有了意思 (wish); c) 你向他意思意思 (express)如何; d) .我根本没有那个意思 (thought); e) 他常说人生真没有意思 (nonsense); f) 你们这么说是什么意思 (intention) These sentences are easy to comprehend. People not only use the grammatical structures but also the sense weights to process the words. The sense weight schema are stored in memory, and activated to represent and distill other sense weights. In this chain activation, sense weights are restructured and created to reflect prototypes. For example, “你好?”, “你好么?”, “好么你?”. Different structures are used in the above examples, but their essential meaning remains the same. So, semantic knowledge is of utmost importance in language comprehension. II. THE STATUS QUO OF COMPUTATIONAL LINGUISTICS Three domains and three corresponding levels of study are involved in building natural language processing systems, i.e. theoretical linguistics and grammar level, computational linguistics and formalization level, computer technology and realization level. Among them, grammar level concerns the innate characteristics of language and paves the way for the latter modules. Realization level focuses on how to control computer operation and provides the efficient development tools and environment. Formalization level is the interface of grammar level and realization level, with the task to readjust the general grammar modules to form grammar modules for convenient computer processing. Computational linguists’ mission is to establish formal grammars (Kaufmann and Pfister, 2012). Computational linguistics is also to establish formalized mathematical modules to analyze and process natural language, and develop computer programs to make it possible that machines can simulate part of, if not all of, human behavior and competence. Computers can only be used to process symbols and all those processed by computers are symbolized with no exception of languages (Yushi, 2003). Meanwhile, there have been breakthroughs in processing Chinese characters and phrases, so sentence level processing has become critical. Basic researches in syntactic, semantic and pragmatic knowledge are the frontier studies in Chinese processing. And how to acquire syntactic and semantic knowledge is the key, while the latter constitutes the major difficulty in processing the word level senses. As aforementioned, semantic formalization can take on many impossible missions in artificial intelligence and computational linguistics, and face challenges at the same time. Thus, the researcher will use semantic field to investigate formalization issues. Semantic fields are the sememe systems, which include the semantemes to represent similarities and differences, and are classified by the subordinates, i.e. degree and number of abstraction of Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013) Published by Atlantis Press, Paris, France.

Few-shot object detection has arisen to address the issue of data scarcity due to the long-tail distribution problem. The goal of few-shot object detection is to allow a pre-trained detector to generalize novel objects with few-shot data samples. However, few-shot object detectors misclassify novel objects into pre-trained base classes frequently. Existing methods applied a large margin classifier to address this problem, but they do not work well in data scarcity settings. In this paper, we propose graph convolution network-based semantic relation network to capture the semantic relations for few-shot object detection. Regardless of the amount of data, the semantic relations among object classes remain constant, which can support the classification of novel objects. Semantic relations are trained by the attention-based module adaptively to training data. Graph convolution network updates the object classifier using semantic relations. The object classifier is integrated and trained with the visual features. Through the comparison experiments with Two-stage Fine-tuning Approach (TFA), we observe that our proposed method achieves higher performance on few-shot settings than TFA.

As the technological revolution and industrial changes continue to advance, small and medium-sized enterprises are eager to seek technical assistance from external professionals to address their technological demands. In this paper, a heterogeneous information network (HIN) that includes semantic information is proposed for expert recommendations based on enterprise demands. Firstly, we constructed a weighted HIN consisting of two kinds of vertices (papers and experts) and two kinds of relations (semantic connections, writing relations). Secondly, an improved meta-path-based weighted random wandering strategy is designed to capture wandering sequences with semantic relationships, and we adopted network representation learning methods to compute the feature representations of the nodes. Then we investigated expert long-term and short-term feature representations of the research topics, and when a demand is proposed, it would be added to the proposed heterogeneous information network based on the semantic relationship between the demand and the paper. Finally, we used a meta-path-based unbiased update algorithm to compute the vector of demand nodes and cosine similarity calculations to obtain a list of expert recommendations.