Toward a semantic granularity model for domain-specific information retrieval

Abstract

Both similarity-based and popularity-based document ranking functions have been successfully applied to information retrieval (IR) in general. However, the dimension of semantic granularity also should be considered for effective retrieval. In this paper, we propose a semantic granularity based IR model which takes into account the three dimensions, namely similarity, popularity, and semantic granularity, to improve domain-specific search. In particular, a concept-based computational model is developed to estimate the semantic granularity of documents with reference to a domain ontology. Semantic granularity refers to the levels of semantic detail carried by an information item. The results of our benchmark experiments confirm that the proposed semantic granularity based IR model performs significantly better than the similarity-based baseline in both a bio-medical and an agricultural domain. In addition, a series of user-oriented studies reveal that the proposed document ranking functions resemble the implicit ranking functions exercised by humans. The perceived relevance of the documents delivered by the granularity-based IR system is significantly higher than that produced by a popular search engine for a number of domain-specific search tasks. To the best of our knowledge, this is the first study regarding the application of semantic granularity to enhance domain-specific IR.

Assembling Frameworks for Strategic Innovation Enactment: Enhancing Transformational Agility through Situational Scanning

“…Adding to the misrepresentation, managers define phenomena considered relevant, important, and desirable, based on their beliefs and expectations (Jennings and Lumpkin 1992). Furthermore, only some of the phenomena present in environments under scrutiny are included, because of constraints on a scanner's field of vision (Hambrick and Mason 1984), or because of an information overload and processing limitation (Farhoomand and Drury 2002;Lau et al 2008;Yan et al 2011). Managers also tend to formulate strategies, based on perceptions that deal with their unique situations (Goleman 1985;Starbuck 1976).…”

A Sequential Latent Topic-Based Readability Model for Domain-Specific Information Retrieval

“…A concept-based approach has been proposed by Yan et al [16,17], which takes into account the coverage (Scope) and relatedness (Cohesion) of domain topics (concepts) within a document, with reference to a domain taxonomy. In the taxonomy, the topics are at different abstraction levels and their relationships are organized into a hierarchical tree structure [12].…”

“…They capture the sequential dependency of topics at different granularities, through mapping a document onto an automatically constructed topic taxonomy. Topic Scope, as originally proposed by Yan et al [16], reflects the overall coverage of domain topics in a document. Topic Trace tracks how the sequence of topics occurring in a document traverses on the topic taxonomy.…”

“…In a typical human reading process, the readability of documents can be interpreted at different levels [16,17]. It is argued in [13] that humans' minds appear to go far beyond the data available, which means there will be a complicated process of abstraction in humans' understanding.…”

A Resource Virtualization Mechanism for Cloud Manufacturing Systems

“…The granularity is defined as the measure extent that characterizes the scale or level of problems. Within the field of granular computing, information granularity usually refers to "structural granularity", which signifies the structural abstraction of information items [12]. A structural abstraction can be based on a relatively large information item, such as a document, or its constituent parts.…”