Automated Semantic Analysis of Schematic Data

Abstract

Content in numerous Web data sources, designed primarily for human consumption, are not directly amenable to machine processing. Automated semantic analysis of such content facilitates their transformation into machine-processable and richly structured semantically annotated data. This paper describes a learningbased technique for semantic analysis of schematic data which are characterized by being template-generated from backend databases. Starting with a seed set of handlabeled instances of semantic concepts in a set of Web pages, the technique learns statistical models of these concepts using light-weight content features. These models direct the annotation of diverse Web pages possessing similar content semantics. The principles behind the technique find application in information retrieval and extraction problems. Focused Web browsing activities require only selective fragments of particular Web pages but are often performed using bookmarks which fetch the contents of the entire page. This results in information overload for users of constrained interaction modality devices such as small-screen handheld devices. Fine-grained information extraction from Web pages, which are typically performed using page specific and syntactic expressions known as wrappers, suffer from lack of scalability and robustness. We report on the application of our technique This work has been conducted while the author was at Stony Brook University. 428World Wide Web (2008) 11:427-464 in developing semantic bookmarks for retrieving targeted browsing content and semantic wrappers for robust and scalable information extraction from Web pages sharing a semantic domain.

Building a Usable and Accessible Semantic Web Interaction Platform

“…For instance, if there exist different places with the same name, the platform presents all the possible referents and asks the user to choose for the right place the article is referring to. In the domain of news websites due to its implicit structure there have been defined metadata extraction algorithms [13] that exploit such structure.…”

“…This recommendation is based on the fact that, being the accessibility guidelines expressed using natural language, the results provided by different automatic evaluators can differ. In this particular case, TAW 11 , Evalaccess 12 and TotalValidator 13 were used as automatic accessibility evaluation tools.…”

Emergent Semantics and Cooperation in Multi-knowledge Communities: the ESTEEM Approach

“…Domain knowledge already encoded in data schemas can thus be reused in the form of peer ontologies, sensibly reducing the required manual effort. In more recent work, approaches suitable for non-specialist users are being proposed, to generate the peer ontology by relying on the results of semantic annotation of the peer resources (e.g., see [25,31] be obtained by combining fragments of ontologies downloaded from the Semantic Web with other ontology specifications acquired from the network nodes with similar interests. This is especially possible in the healthcare domain, where a number of taxonomies/ontologies are available and can be exploited by a peer to classify its own resources.…”

OntoTrader: An Ontological Web Trading Agent Approach for Environmental Information Retrieval

“…This sort of interaction ( Human-to-Human , HH) requires unified protocol and communication policies for all parts of the system. People and groups of people also interact through the system by using user interfaces (UI), which are generally well suited to their needs [ 5 ]. This type of interaction ( Human-to-Computer , HC) also needs to establish communication protocols among users, profiles, groups, and user interface agents.…”