A Comparative Evaluation of Full-text, Concept-based, and Context-sensitive Search

Abstract

The study demonstrated usefulness of concept-based and context-sensitive queries for enhancing the precision of retrieval from a digital library of semi-structured clinical guideline documents. Concept-based searches outperformed free-text queries, especially when baseline precision was low. In general, the more ontological elements used in the query, the greater the resulting precision.

NCBO Resource Index: Ontology-Based Search and Mining of Biomedical Resources

“…There are however other tools in the biomedical domain that use semantics internally including MedicoPort [30], which uses UMLS semantics to expand user queries; the work of Moskovitch and colleagues [4], who use ontologies for annotation (concept based search) and demonstrate the importance of the context (context-sensitive search) when annotating structured documents. HealthCyberMap [31] uses ontologies and semantic distances for visualizing biomedical resources information.…”

“…Users can search data elements using AND and OR constructs. 4 She is presented with a list of search results (as snippets) as well as a tag cloud of related terms (selected in the top 10 results) to help refine her search further. For each identified element, a user can see the details of the annotations highlighted in the original text and link back to the URLs of the original data elements.…”

“…However, the metadata that describe the information in data resources are usually unstructured, often come in the form of freetext descriptions, and are rarely labelled or tagged using terms from ontologies that are available for the domains. Users often prefer labels from ontologies because they provide a clear point of reference during their search and mining tasks [4,5,6]. For example, researchers and curators widely use the Gene Ontology to describe the molecular functions, cellular location, and biological processes of gene products.…”

Un service Web pour l’annotation sémantique de données biomédicales avec des ontologies

“…Le problème est que ces descriptions textuelles sont rarement structurées et que le plus souvent elles n'utilisent pas des termes définis dans des ontologies biomédicales. Il existe donc un challenge qui consiste à produire pour ces descriptions textuelles des annotations (ou labels, tags) qui utilisent des termes d'ontologies et faciliteront la recherche et l'indexation de ces données ainsi que leur intégration [4] [5]. Par exemple, une recherche des essais cliniques pour le concept carcinoma doit considérer également les éléments indexés avec les termes Malignant epithelial tumor et Epithelial Neoplasm car l'ontologie SNOMED-CT nous précise que le premier terme est un synonyme du concept carcinoma et l'ontologie NCI Thesaurus nous précise que ce concept est un sous type (is_a) de Epithelial Neoplasm.…”

A System for Ontology-Based Annotation of Biomedical Data

“…An element is identifiable and can be linked by a specific URL/URI (id), and it has a structure that defines the metadata contexts for the element (title, description, abstract, and so on). Our system retrieves 4 and downloads (through specific access tools) the element text metadata from resources, and keeps a track from both the original metadata context and element id. At the annotation level, the system uses a concept recognition tool called mgrep (developed by Univ.…”