Problem Of Semantic Annotation Research Articles

Основні аспекти семантичного анотування великих даних

Semantic annotations, due to their structure, are an in­teg­ral part of the effective solution of big data problems. However, the problem of defining semantic annotations is not trivial. Manual annotation is not acceptable for big data due to their size and heterogeneity, as well as the complexity and cost of the annotation process, the auto­ma­tic annotation task for big data has not yet decision. So, resolving the problem of semantic annotation requires modern mixed approaches, which would be based on and using the existing theoretical apparatus, namely methods and models of machine learning, statistical learning, wor­king with content of different types and formats, natural lan­guage processing, etc. It also should provide solutions for main annotation tasks: discovering and extracting en­ti­ties and relationships from content of any type and de­fi­ning semantic annotations based on existing sources of know­ledge (dictionaries, ontologies, etc.). The obtained an­notations must be accurate and provide a further op­por­tu­nity to solve application problems with the annotated data. Note that the big data contents are very different, as a result, their properties that should be annotated are very dif­ferent too. This requires different metadata to describe the data. It leads to large number of different metadata stan­dards for data of different types or formats appears. How­ever, to effectively solve the annotation problem, it is necessary to have a generalized description of the metadata types, and we have to consider metadata spe­ci­fi­city within this description. The purpose of this work is to define the general classification of metadata and de­ter­mi­nate common aspects and approaches to big data se­man­tic annotation.

Random Walk-Based Semantic Annotation for On-demand Printing Products

Nowadays, the scale of real network is increasing day by day, while also brings sparse problems. It is usually necessary to maintain a large number of product information. To organize this product information, a feasible way is to add semantic tags to the information. In this article, we aim to solve the problem of semantic annotation of on-demand printing products. Based on good properties of random walk in global networks, we deal with the sparsity problem by applying it, and then propose an efficient ProRWR algorithm. Firstly, it processes the text description dataset of printed products based on TF-IDF algorithm, and builds “product-term” bipartite network. Secondly, ProRWR builds square matrix using the TF-IDF weight matrix, rewrite the equation of random walk, and use the normalized square matrix as the input of rewrite ProRWR algorithm. By random walks, terms with the highest convergence probability in each product document are selected as the most relevant feature terms of the product. A large number of experiments have been done on Amazon dataset. The results show that the precision and recall of our algorithm are 73.5% and 60%, respectively, indicating that ProRWR has discovered the potential semantic association and implemented the semantic annotation of on-demand printed products.

BiOSS: A system for biomedical ontology selection

In biomedical informatics, ontologies are considered a key technology for annotating, retrieving and sharing the huge volume of publicly available data. Due to the increasing amount, complexity and variety of existing biomedical ontologies, choosing the ones to be used in a semantic annotation problem or to design a specific application is a difficult task. As a consequence, the design of approaches and tools addressed to facilitate the selection of biomedical ontologies is becoming a priority. In this paper we present BiOSS, a novel system for the selection of biomedical ontologies. BiOSS evaluates the adequacy of an ontology to a given domain according to three different criteria: (1) the extent to which the ontology covers the domain; (2) the semantic richness of the ontology in the domain; (3) the popularity of the ontology in the biomedical community. BiOSS has been applied to 5 representative problems of ontology selection. It also has been compared to existing methods and tools. Results are promising and show the usefulness of BiOSS to solve real-world ontology selection problems. BiOSS is openly available both as a web tool and a web service.

A Hybrid Approach for Solving the Semantic Annotation Problem in Semantic Social Networks

In this paper, we propose a hybrid method that gives a so- lution for the semantic annotation problem. We focus our approach to settle the semantic annotation in social networks. Many approaches use a kind of knowledge representation as taxonomies or ontologies to resolve the annotation problem. Recent works have proposed other probabilistic- based approaches to solve the semantic problem as Bayesian Networks. The nature of the Bayesian learning is given by two phases: the data gathering and the query phase, it can be used to settle the semantic annotation problem viewed as a classication one. This work proposes to combine an ontological approach with a Bayesian learning one applied to give a semantic to publications realized in real time in social networks.

Bridge ontology: A multi-ontologies-based approach for semantic annotation

Representing the relationships between ontologies is the key problem of semantic annotations based on multi-ontologies. Traditional approaches only had the ability of denoting the simple concept subsumption relations between ontologies. Through analyzing and classifying the relationships between ontologies, the idea of bridge ontology was proposed, which had the powerful capability of expressing the complex relationships between concepts and relationships between relations in multi-ontologies. Meanwhile, a new approach employing bridge ontology was proposed to deal with the multi-ontologies-based semantic annotation problem. The bridge ontology is a peculiar ontology, which can be created and maintained conveniently, and is effective in the multi-ontologies-based semantic annotation. The approach using bridge ontology has the advantages of low-cost, scalable, robust in the web circumstance, and avoiding the unnecessary ontology extending and integration.

Senseval/Romanseval: The Framework for Italian

In this paper we present some observations concerning an experiment of (manual/ automatic) semantic tagging of a small Italian corpus performed within the framework of the SENSEVAL/ROMANSEVAL initiative. The main goal of the initiative was to set up a framework for evaluation of Word Sense Disambiguation systems (WSDS) through the comparative analysis of their performance on the same type of data. In this experiment there are two aspects which are of relevance: first, the preparation of the reference annotated corpus, and, second, the evaluation of the systems against it. In both aspects we are mainly interested here in the analysis of the linguistic side which can lead to a better understanding of the problem of semantic annotation of a corpus, be it manual or automatic annotation. In particular, we will investigate, firstly, the reasons for disagreement between human annotators, secondly, some linguistically relevant aspects of the performance of the Italian WSDS and, finally, the lessons learned from the present experiment.