Semantic Agent Research Articles

Towards a Semantic Based Workflow Model for Composition of OWL-S Based Atomic Processes

Due to the insertion of semantics to the Web services, meeting user demands will be possible through logical deductions and achieving resolutions automatically. With the application of semantic description in content of Web services it is easier to discover and compose suitable Web services during analyzing, searching and matching processes. We proposed a framework of an Inference-based Semantic Composition Agent (SCA) of atomic processes that employs process similarity matching and inference techniques. SCA synthesizes new services from existing ones in an automatic fashion. A powerful matching mechanism is needed to find fitting tasks in order to attain the required composition by each client. An innovative Semantic Matching Step (SMS) of SCA helps to find the fitting tasks while constituting workflow to achieve required composition. Additionally, SCA composes available OWL-S atomic processes utilizing Revised Armstrong's Axioms (RAA) in inferring functional dependencies. Experiments show that SCA System produces atomic process sequences as a workflow in achieving the required composition plan that satisfies user's requirements as a complex task. The novelty of the SCA System is that for the first time Armstrong's Axioms are revised and used for semantic-based planning and inferencing of services.

A SomAgent statistical machine translation

Abstract The paper describes the process by which the word alignment task performed within SOMAgent works in collaboration with the statistical machine translation system in order to learn a phrase translation table. We studied improvements in the quality of translation using syntax augmented machine translation. We also experimented with different degrees of linguistic analysis from the lexical level to a syntactic or semantic level, in order to generate a more precise alignment. We developed a contextual environment using the Self-Organizing Map, which can model a semantic agent (SOMAgent) that learns the correct meaning of a word used in context in order to deal with specific phenomena such as ambiguity, and to generate more precise alignments that can improve the first choice of the statistical machine translation system giving linguistic knowledge.

How the NETofANs-model explains representation, intentionality, and much of the process that generates the contents of awareness

The first and essential step in the process that generates the contents of awareness is the establishment of representational brain features—according to the NETofANs-model, this occurs through a process of multi-level self-organization and emergence in a “network of attractor-dominated networks of neurons” or NETofANs. We analyze how processes involving representational brain features can result in intelligent behaviors, including categorization of reality-features, conceptualization of percepts, existential-problem solving, imagination, and thought. The NETofANs-model explains "representation" and "intentionality" in terms of dynamical systems and thereby establishes a theoretical basis for the naturalization of semantics and the construction of semantic agents.

Tracking Reported Vehicles in Traffic Management and Information System using Intelligent Junctions

This study highlights a security scenario involving vehicles in a Traffic Management and Information System (TMIS) network. TMIS and its nodal architecture, nicknamed Intelligent Junction (IJ), are summarized from our recent work. System design sets an example to a software architecture implementing autonomous semantic agents through semantic web services, junction-based sensor networks, local- and wide-area networking through wire/wireless integrated communication infrastructure. It is so construed as to provide (near-) real-time services throughout the network. This introduction is with reference to the SOA of Cooperative Labyrinth Discovery Robotics and Traffic Management and Information System Projects. This also takes up several issues including realtime goal-oriented coordination of semantic web services. Especially described are its essential functions crucial to aid security applications. A security scenario concerning tracking and routing reported, say missing, vehicles is considered and shown how to graft it onto TMIS network. Simulation results show promising outcomes. Performance of the system in terms of mean response time is analytically derived. Simulation and analytical results agree. Research involving similar development base is suggested.

Implementation of Semantic Web Mining on E-Learning

Semantic Web is a product of Web 2.0 (second generation of web) that is supported with automated semantic agents for processing user data to help the user on ease of use and personalization of services. Web Mining is an application of data mining which focuses on discovering patterns from Web logs and data. The semantic structure can be built with the pattern or relation results discovered via web mining. By combining those two applications of both disciplines, it's possible to achieve Semantic Web Mining which is a recent hot topic in educational research. This paper gives an overview of current applications of Semantic Web Mining on e-learning which already became a base component of education.

Creating automated plans for Semantic Web applications through planning as model checking

The uncertainties of planning engendered by nondeterminism and partial observability have led to a melding of model checking and artificial intelligence. The result is planning as model checking. Because planning as model checking tests sets of states and sets of transitions at once, rather than single states, the method remains robust and viable in domains of large state spaces and varying levels of uncertainty. We develop a test bench for Semantic Web agents and use model-based planning to derive strong plans, strong cyclic plans, and weak plans. Our results suggest potential robustness and efficacy in devising plans for agent actions in the Semantic Web environment.

Applying Semantic Agents to Message Communication in e-Learning Environment

A traditional distance learning system requires supervisors or teachers always available on online to facilitate and monitor a learner’s progress by answering questions and guiding users. We presents an English chat room system in which students discuss course contents and ask questions to and receive from teachers and other students. The mechanism contains an agent that detects syntax errors in sentences written by the online the user and also checks the semantics of a sentence. The agent can thus offer recommendations to the user and, then, analyze the data of the learner corpus. When users query the system, this system will attempt to find the answers from the knowledge ontology that is stored in the records of previous user comments. With the availability of automatic supervisors, messages can be monitored and syntax or semantic mistakes can be corrected to resolve learner-related problems.

Special Section on Engineering Semantic Agent Systems

Atilla Elcia,∗, Mamadou Tadiou Kone and Tharam S. Dillon aComputer Engineering Department, and Internet Technologies Research Center Eastern Mediterranean University Gazimagusa (TRNC), North Cyprus, Turkey bDepartment of Computer Science, Faculty of Science and Engineering, Laval University, Qu ebec, Canada cDigital Ecosystems and Business Intelligence Institute, Curtin University of Technology, Perth, Australia

Semantic role labeling for protein transport predicates

BackgroundAutomatic semantic role labeling (SRL) is a natural language processing (NLP) technique that maps sentences to semantic representations. This technique has been widely studied in the recent years, but mostly with data in newswire domains. Here, we report on a SRL model for identifying the semantic roles of biomedical predicates describing protein transport in GeneRIFs – manually curated sentences focusing on gene functions. To avoid the computational cost of syntactic parsing, and because the boundaries of our protein transport roles often did not match up with syntactic phrase boundaries, we approached this problem with a word-chunking paradigm and trained support vector machine classifiers to classify words as being at the beginning, inside or outside of a protein transport role.ResultsWe collected a set of 837 GeneRIFs describing movements of proteins between cellular components, whose predicates were annotated for the semantic roles AGENT, PATIENT, ORIGIN and DESTINATION. We trained these models with the features of previous word-chunking models, features adapted from phrase-chunking models, and features derived from an analysis of our data. Our models were able to label protein transport semantic roles with 87.6% precision and 79.0% recall when using manually annotated protein boundaries, and 87.0% precision and 74.5% recall when using automatically identified ones.ConclusionWe successfully adapted the word-chunking classification paradigm to semantic role labeling, applying it to a new domain with predicates completely absent from any previous studies. By combining the traditional word and phrasal role labeling features with biomedical features like protein boundaries and MEDPOST part of speech tags, we were able to address the challenges posed by the new domain data and subsequently build robust models that achieved F-measures as high as 83.1. This system for extracting protein transport information from GeneRIFs performs well even with proteins identified automatically, and is therefore more robust than the rule-based methods previously used to extract protein transport roles.

ArrayWiki: an enabling technology for sharing public microarray data repositories and meta-analyses

BackgroundA survey of microarray databases reveals that most of the repository contents and data models are heterogeneous (i.e., data obtained from different chip manufacturers), and that the repositories provide only basic biological keywords linking to PubMed. As a result, it is difficult to find datasets using research context or analysis parameters information beyond a few keywords. For example, to reduce the "curse-of-dimension" problem in microarray analysis, the number of samples is often increased by merging array data from different datasets. Knowing chip data parameters such as pre-processing steps (e.g., normalization, artefact removal, etc), and knowing any previous biological validation of the dataset is essential due to the heterogeneity of the data. However, most of the microarray repositories do not have meta-data information in the first place, and do not have a a mechanism to add or insert this information. Thus, there is a critical need to create "intelligent" microarray repositories that (1) enable update of meta-data with the raw array data, and (2) provide standardized archiving protocols to minimize bias from the raw data sources.ResultsTo address the problems discussed, we have developed a community maintained system called ArrayWiki that unites disparate meta-data of microarray meta-experiments from multiple primary sources with four key features. First, ArrayWiki provides a user-friendly knowledge management interface in addition to a programmable interface using standards developed by Wikipedia. Second, ArrayWiki includes automated quality control processes (caCORRECT) and novel visualization methods (BioPNG, Gel Plots), which provide extra information about data quality unavailable in other microarray repositories. Third, it provides a user-curation capability through the familiar Wiki interface. Fourth, ArrayWiki provides users with simple text-based searches across all experiment meta-data, and exposes data to search engine crawlers (Semantic Agents) such as Google to further enhance data discovery.ConclusionsMicroarray data and meta information in ArrayWiki are distributed and visualized using a novel and compact data storage format, BioPNG. Also, they are open to the research community for curation, modification, and contribution. By making a small investment of time to learn the syntax and structure common to all sites running MediaWiki software, domain scientists and practioners can all contribute to make better use of microarray technologies in research and medical practices. ArrayWiki is available at .

Parsing, Semantic Networks, and Political Authority Using Syntactic Analysis to Extract Semantic Relations from Dutch Newspaper Articles

Analysis of political communication is an important aspect of political research. Thematic content analysis has yielded considerable success both with manual and automatic coding, but Semantic Network Analysis has proven more difficult, both for humans and for the computer. This article presents a system for an automated Semantic Network Analysis of Dutch texts. The system automatically extracts relations between political actors based on the output of syntactic analysis of Dutch newspaper articles. Specifically, the system uses pattern matching to find source constructions and determine the semantic agent and patient of relations, and name matching and anaphora resolution to identify political actors. The performance of the system is judged by comparing the extracted relations to manual codings of the same material. Results on the level of measurement indicate acceptable performance. We also estimate performance at the levels of analysis by using a case study of media authority, resulting in good correlations between the theoretical variables derived from the automatic and manual analysis. Finally, we test a number of substantive hypotheses with regression models using the automatic and manual output, resulting in highly similar models in each case. This suggests that our method has sufficient performance to be used to answer relevant political questions in a valid way.

Using agents and ontologies for application development on the semantic web

Abstract The Semantic Web provides access to heterogeneous, distributed information, enabling software products to mediate between user needs and the information sources available. Agents are one of the most promising technologies for the development of Semantic Web software products. However, agent-based technologies will not become widespread until there are adequate infrastructures for the development of semantic multi-agent systems (MAS). Some challenges, such as turning software agents into practical abstractions for dealing with ontologies, taking advantage of the distributed nature of the Web to create distributed agents and making a seamless integration with existing Web tools, e.g. the browser, still need to be addressed. This paper describes the main features of the SemantiCore framework, an agent infrastructure to develop semantic MAS. A look at a benchmark Semantic Web application illustrates the SemantiCore potential as an infrastructure for the deployment of semantic agent applications.

Standards for image annotation using Semantic Web

The impetus behind Semantic Web research remains the vision of supplementing availability with utility; that is, the World Wide Web provides availability of digital media, but the Semantic Web will allow presently available digital media to be used in unseen ways. An example of such an application is multimedia retrieval. At present, there are vast amounts of digital media available on the web. Once this media gets associated with machine-understandable metadata, the web can serve as a potentially unlimited supplier for multimedia web services, which could populate themselves by searching for keywords and subsequently retrieving images or articles, which is precisely the type of system that is proposed in this paper. Such a system requires solid interoperability, a central ontology, semantic agent search capabilities, and standards. Specifically, this paper explores this cross-section of image annotation and Semantic Web services, models the web service components that constitute such a system, discusses the sequential, cooperative execution of these Semantic Web services, and introduces intelligent storage of image semantics as part of a semantic link space.

Extensible soft semantic web services agent

Web services technology is critical for the success of business integration and other application fields such as bioinformatics. However, there are two challenges facing the practicality of Web services: (a) efficient location of the Web service registries that contain the requested Web services and (b) efficient retrieval of the requested services from these registries with high quality of service (QoS). The main reason for this problem is that current Web services technology is not semantic-oriented. Several proposals have been made to add semantics to Web services to facilitate discovery and composition of relevant Web services. Such proposals are being referred to as semantic Web services (SWS). However, most of these proposals do not address the second problem of retrieval of web services with high QoS. In this paper, we propose a framework called soft semantic Web services agent (soft SWS agent) for providing high QoS Semantic Web services using soft computing methodology. Since different application domains have different requirement for QoS, it is impractical to use classical mathematical modeling methods to evaluate the QoS of semantic Web services. We use fuzzy neural networks with Genetic Algorithms (GA) as our study case. Simulation results show that the soft computing methodology is practicable to handle fuzzy and uncertain QoS metrics effectively.

CUSTOMIZING THE INSTRUCTIONAL GRID

The Web contains hundreds of thousands of educational resources available any time and any place. However no smart technology is available to help teachers and students locate appropriate resources customized to their needs and social characteristics. When educational resources are indexed, it is often done by demographics, such as student age and grade. This article describes customized Grid Learning Services (GLS) that will personalize instruction based on an individual's presumed knowledge and cognitive and learning needs. The customized GLS will use real-time student modeling, the Semantic Web, intelligent agents, and pre-tests of cognitive, affective, and social characteristics to personalize the selection of educational resources and problems. Components of the customized GLS include an ontology construction agent, goal-based retrieval mechanisms, a lesson planner, and student and pedagogical agents.

Modeling of cell signaling pathways in macrophages by semantic networks

BackgroundSubstantial amounts of data on cell signaling, metabolic, gene regulatory and other biological pathways have been accumulated in literature and electronic databases. Conventionally, this information is stored in the form of pathway diagrams and can be characterized as highly "compartmental" (i.e. individual pathways are not connected into more general networks). Current approaches for representing pathways are limited in their capacity to model molecular interactions in their spatial and temporal context. Moreover, the critical knowledge of cause-effect relationships among signaling events is not reflected by most conventional approaches for manipulating pathways.ResultsWe have applied a semantic network (SN) approach to develop and implement a model for cell signaling pathways. The semantic model has mapped biological concepts to a set of semantic agents and relationships, and characterized cell signaling events and their participants in the hierarchical and spatial context. In particular, the available information on the behaviors and interactions of the PI3K enzyme family has been integrated into the SN environment and a cell signaling network in human macrophages has been constructed. A SN-application has been developed to manipulate the locations and the states of molecules and to observe their actions under different biological scenarios. The approach allowed qualitative simulation of cell signaling events involving PI3Ks and identified pathways of molecular interactions that led to known cellular responses as well as other potential responses during bacterial invasions in macrophages.ConclusionsWe concluded from our results that the semantic network is an effective method to model cell signaling pathways. The semantic model allows proper representation and integration of information on biological structures and their interactions at different levels. The reconstruction of the cell signaling network in the macrophage allowed detailed investigation of connections among various essential molecules and reflected the cause-effect relationships among signaling events. The simulation demonstrated the dynamics of the semantic network, where a change of states on a molecule can alter its function and potentially cause a chain-reaction effect in the system.

Saute ça / “Jump this!”

Do young Bengali-speaking children learning French as a second language at preschool follow the same developmental path as French first language children with respect to the acquisition of the French faire faire causative? As an initial step toward answering this question, a flexible semi-structured play protocol was developed for the elicitation of the faire faire causative from both first and second language learners. In the first part of the study, longitudinal data were collected from eight monolingual children acquiring French as a first language in Montreal. The children were audio- and video-taped in their homes for 30 to 45 minutes every two to four weeks for at least six months, and their data were analyzed for occurrences of causative constructions, such as Je fais sauter la grenouille , and single-agent infinitival complement constructions such as Je veux jouer in which the same argument (agent or actor) applies to both modal and infinitive. Causative constructions are double-agent; the grammatical subject of the sentence (and semantic agent of the verb faire ) and the grammatical object of faire (and semantic agent of the following infinitive) are two distinct arguments. The argument structure of causative constructions is therefore more complex than that of single-agent infinitival complement constructions. Both kinds of constructions emerged at the same time in the speech of the French-L1 children, sometime between the second and fourth birthdays. In the second part of the study, cross-sectional data from 24 Bengali-L1 children aged 5 and 6 were analyzed. A standardized measure of receptive vocabulary in French was taken from each L2 child, as well as a 30-minute naturalistic speech sample incorporating the causative elicitation procedure. The L2 children's receptive vocabulary and their ability to form single-agent infinitival complement constructions resembled that of the 2and 3-year-old French monolingual children, but their ability to form causative constructions lagged far behind. Some possible explanations for this finding are suggested. Differences in the input to the two groups, aspects of the syntax of causativization in French, and first language influence may all be implicated.

Semantic agents, syntactic subjects, and discourse topics

The Salishan language Lushootseed has been claimed to lack both syntactic subjects and morphosyntactically transitive clauses, a problematic stance from a universalist/typological point of view. This paper offers evidence both for the syntactic role of subject in Lushootseed and the existence of transitive clauses, and examines the sentence- and discourse-level properties of Lushootseed subjects that make them essential for the grounding of events and discourse in both space and time. Their centrality to the discourse-organization of the language, and hence their recoverability, allows their frequent — and, in transitive clauses, obligatory — elision from the surface form of sentences.

Accessing sentence participants: The advantage of first mention

We investigate the following finding concerning the order in which participants are mentioned in sentences: In a probe recognition task, probe words are responded to considerably more rapidly when they are the names of the first- as opposed to the second-mentioned participants. Seven experiments demonstrated that this advantage is not attributable to the tendency in English for first-mentioned participants to be semantic agents; neither is it due to the fact that in many of our experiments, the first-mentioned participants were also the initial words of their stimulus sentences. Furthermore, the advantage is not attenuated when the first- and second-mentioned participants share syntactic subjecthood, or even when the first-mentioned participants are not the syntactic subjects. In sum, the effect does not appear to be attributable to linguistic factors. We suggest instead that it is the result of cognitive processes: Building a coherent mental representation requires first laying a foundation and then mapping subsequent information onto the developing representation. First-mentioned participants are more accessible because they form the foundations for their sentence-level representations and because it is through them that subsequent information gets mapped onto the developing representations.