Semantic Modeling Techniques Research Articles

Multi-Modal Hashing for Efficient Multimedia Retrieval: A Survey

With the explosive growth of multimedia contents, multimedia retrieval is facing unprecedented challenges on both storage cost and retrieval speed. Hashing technique can project the high-dimensional data into compact binary hash codes. With it, the most time-consuming semantic similarity computation during the multimedia retrieval process can be significantly accelerated with fast Hamming distance computation, and meanwhile the storage cost can be reduced greatly by the binary embedding. In the light of this, multi-modal hashing has recently received considerable attention to support large-scale multimedia retrieval. Different from uni-modal hashing, the multi-modal hashing focuses on modeling the multi-modal semantics and further preserving them into binary hash codes with hash learning. In this paper, we first systematically review the existing learning to hash methods for efficient multimedia retrieval, categorizing them according to the multimedia retrieval tasks, the specific multi-modal semantic modeling techniques, and hash learning strategies. Thereafter, we present the performance comparison results. We ultimately discuss the challenges and potential research directions that may require further investigation in multi-modal hash learning. To facilitate the research on multi-modal hashing, we develop an open-source performance comparison tool at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/BMC-SDNU/Hashing-Retrieval</uri> .

Lexical typology and semantic maps: Perspectives and challenges

AbstractThe paper outlines the basics of data collection, analysis and visualization under the frame-based approach to lexical typology and illustrates its methodology using the data of cross-linguistic research on verbs of falling. The framework reveals several challenges to semantic map modelling that usually escape researchers’ attention. These are: (1) principles of establishing lexical comparative concepts; (2) the effective ways of visualization for the opposition between direct and figurative meanings of lexical items; (3) the problem of the borderlines between semantic fields, which seem to be very subtle. These problems are discussed in detail in the paper, as well as possible theoretical decisions and semantic modelling techniques that could overcome these bottlenecks.

Riding the tide of sentiment change: sentiment analysis with evolving online reviews

The last decade has seen a rapid growth in the volume of online reviews. A great deal of research has been done in the area of opinion mining, aiming at analyzing the sentiments expressed in those reviews towards products and services. Most of the such work focuses on mining opinions from a collection of reviews posted during a particular period, and does not consider the change in sentiments when the collection of reviews evolve over time. In this paper, we fill in this gap, and study the problem of developing adaptive sentiment analysis models for online reviews. Given the success of latent semantic modeling techniques, we propose two adaptive methods to capture the evolving sentiments. As a case study, we also investigate the possibility of using the extracted adaptive patterns for sales prediction. Our proposal is evaluated on an IMDB dataset consisting of reviews of selected movies and their box office revenues. Experimental results show that the adaptive methods can capture sentiment changes arising from newly available reviews, which helps greatly improve the prediction accuracy.

APPLYING SEMANTIC MODELLING TECHIQUES IN LARGE SCALE PROCESS SIMULATION

Large scale process simulation is used in industry for e.g. process and automation design, automation testing, safety analyses and for operator training and support purposes. In modern computing environments very large dynamic process models of an entire plant can be calculated in real time or even faster than real time. However current process simulation environments are separate tools that rarely have links to the other information management tools of a plant delivery project. In this paper we present an approach where semantic modelling techniques (semantic web) are used within an ontology definition environment. In this environment different plant modelling and simulation ontologies can be mapped and used together without compromising computational speed and scalability. Ontology of one simulation solver type, namely companion model solver, is discussed as an example.

Technologies for data semantic modelling

The explicit modelling of data semantics promises to drive information integration technology to a new level of flexibility and automation. However, nowadays, the inclusion of semantic data modelling into information system development is constrained by the lack of a supporting tool based on appropriate technologies. Our contribution in this paper is based on the specification of modelling languages that make the task of information semantics definition friendly for people who have no background knowledge of semantic modelling techniques, proposed by artificial intelligence techniques. In addition, we present a prototype that implements these languages.

Mapping extended entity relationship model to object modeling technique

A methodology of reengineering existing extended Entity-Relationship(EER) model to Object Modeling Technique(OMT) model is described. A set of translation rules from EER model to a generic Object-Oriented(OO) model of OMT methodology is devised. Such reengineering practices not only can provide us with significant insight to the "interoperability" between the OO and the traditional semantic modelling techniques, but also can lead us to the development of a practical design methodology for object-oriented databases(OODB).