Using the NIFSTD Ontology to Improve PubMed Search Results
Filed under:
Infrastructural and portal services
Hitesh Sabnani (University of California San Diego), Anita Bandrowski (University of California San Diego), Amarnath Gupta (University of California San Diego)
The goal of the Neuroscience Information Framework (NIF) is to provide a comprehensive portal that enables neuroscientists to discover neuroscience resources, access and analyze neuroscience data. To achieve this goal, the NIF system uses a comprehensive OWL ontology that has over 60000 terms related to Neuroscience and a large number of relationships among them. The ontology connects all of NIF's information content into a common fabric. One use of the NIF ontology is to perform a semantic search over NIF's data and literature holdings which is a combination of PubMed abstracts and PubMed Central full-text articles. This abstract describes a recent advancement we have made to improve the quality of literature search in the NIF system.
The standard NIF literature search facility deconstructs an article into its constituent parts (Title, Abstract etc.) and measures the relevance of a search query by combining partial scores of the match between the query term vector and each component term vector into a combined matching score. The ranking function produces better search results than PubMed, but provides no semantic context to interpret the search results. One can compute "clustered results" where an algorithm post-processes the results to partition the results groups so that results within a group a "similar" to each other (e.g., using a cosine-distance metric) than between groups. We show that this form of "blind" similarity-based clustered ranking gives no insight into the search results because the clusters often center around arbitrary concepts that often have no bearing on neuroscience. To improve the quality of results, we use the NIF ontology in a novel way. For every result (i.e., abstract) returned from the search, we perform an automatic mapping of terms to the NIF ontology such that each abstract maps to more than one ontology term. After all terms are mapped, we perform a novel graph clustering method on the mapped nodes of ontology from the entire result set. The method allows overlapping of clusters and takes into account taxonomic and partonomic relationships amongst terms such that the number of conceptual overlaps between related terms (e.g., hippocampus and CA1) is minimized. The cluster centers are assigned to terms with the largest betweenness centrality. Results within a cluster are ranked in the standard way.
We show that this technique offers a deeper insight into the neuroscientific connection between the query and search results.
The standard NIF literature search facility deconstructs an article into its constituent parts (Title, Abstract etc.) and measures the relevance of a search query by combining partial scores of the match between the query term vector and each component term vector into a combined matching score. The ranking function produces better search results than PubMed, but provides no semantic context to interpret the search results. One can compute "clustered results" where an algorithm post-processes the results to partition the results groups so that results within a group a "similar" to each other (e.g., using a cosine-distance metric) than between groups. We show that this form of "blind" similarity-based clustered ranking gives no insight into the search results because the clusters often center around arbitrary concepts that often have no bearing on neuroscience. To improve the quality of results, we use the NIF ontology in a novel way. For every result (i.e., abstract) returned from the search, we perform an automatic mapping of terms to the NIF ontology such that each abstract maps to more than one ontology term. After all terms are mapped, we perform a novel graph clustering method on the mapped nodes of ontology from the entire result set. The method allows overlapping of clusters and takes into account taxonomic and partonomic relationships amongst terms such that the number of conceptual overlaps between related terms (e.g., hippocampus and CA1) is minimized. The cluster centers are assigned to terms with the largest betweenness centrality. Results within a cluster are ranked in the standard way.
We show that this technique offers a deeper insight into the neuroscientific connection between the query and search results.
Preferred presentation format:
Poster
Topic:
Infrastructural and portal services
Latest news for Neuroinformatics 2011
Follow INCF on Twitter
