http://precedings.nature.com/tags/search%20engines Recently posted documents tagged with 'search engines' Nature Publishing Group en Nature Precedings http://precedings.nature.com/images/header_logo.gif http://precedings.nature.com http://precedings.nature.com/documents/2315/version/1 Motivation: With the tremendous growth in scientific literature, it is necessary to improve upon the standard pattern matching style of the available search engines. Semantic NLP may be the solution to this problem. Cognition Search (CSIR) is a natural language technology. It is best used by asking a simple question that might be answered in textual data being queried, such as MEDLINE. CSIR has a large English dictionary and semantic database. Cognition’s semantic map enables the search process to be based on meaning rather than statistical word pattern matching and, therefore, returns more complete and relevant results. The Cognition Search engine uses downward reasoning and synonymy which also improves recall. It improves precision through phrase parsing and word sense disambiguation.Result: Here we have carried out several projects to “teach” the CSIR lexicon medical, biochemical and molecular biological language and acronyms from curated web-based free sources. Vocabulary from the Alliance for Cell Signaling (AfCS), the Human Genome Nomenclature Consortium (HGNC), the United Medical Language System (UMLS) Meta-thesaurus, and The International Union of Pure and Applied Chemistry (IUPAC) was introduced into the CSIR dictionary and curated. The resulting system was used to interpret MEDLINE abstracts. Meaning-based search of MEDLINE abstracts yields high precision (estimated at >90%), and high recall (estimated at >90%), where synonym information has been encoded. The present implementation can be found at http://MEDLINE.cognition.com. http://precedings.nature.com/documents/2315/version/1 Mon, 22 Sep 2008 21:15:02 UTC Natural Language Query in the Biochemistry and Molecular Biology Domains Based on Cognition Search™ hdl:10101/npre.2008.2315.1 2008-09-22 Elizabeth J. Goldsmith Nature Precedings 2008-09-22T21:15:02Z Manuscript Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://precedings.nature.com/documents/2101/version/2 With increasing number of bio-literature search engines, scientists and health professionals either make a subjective choice of tool(s) or face a challenge of analyzing multiple features of a plethora of bibliographic software. There is an urgent need for a thorough comparative analysis of the available literature scanning tools, from the user’s perspective. We report results of the first time semi-quantitative comparison of 21 search programs, which can search published (partial or full text) documents in life science areas. The observations can assist life science researchers and medical professionals to make an informed selection among the programs, depending on their search objectives. Some of the important findings are: 1. Most of the hits obtained from Scopus, ReleMed, EBImed, CiteXplore, and HighWire Press were usually relevant (i.e., these tools showed a better precision than other tools). 2. But a very high number of relevant citations were retrieved by HighWire Press, Google Scholar, CiteXplore and Pubmed Central (they had better recall). 3. HWP and CiteXplore seemed to have a good balance of precision and recall efficiencies. 4. PubMed Central, PubMed and Scopus provided the most useful query systems. 5. GoPubMed, BioAsk, EBIMed, ClusterMed could be more useful among the tools that can automatically process the retrieved citations for further scanning of bio-entities such as proteins, diseases, tissues, molecular interactions etc). The authors suggest the use of PubMed, Scopus, Google Scholar and HighWire Press – for better coverage, and GoPubMed – to view the hits categorized based on the MeSH and gene ontology terms. http://precedings.nature.com/documents/2101/version/2 Thu, 24 Jul 2008 15:38:26 UTC How do you choose your literature search tool(s)? hdl:10101/npre.2008.2101.2 2008-07-24 Kshitish K. Acharya Nature Precedings 2008-07-24T15:38:26Z Manuscript Bioinformatics http://creativecommons.org/licenses/by/3.0/ http://precedings.nature.com/documents/2101/version/1 With increasing number of bibliographic software, scientists and health professionals either make a subjective choice of tool(s) that could suit their needs or face a challenge of analyzing multiple features of a plethora of search programs. There is an urgent need for a thorough comparative analysis of the available bio-literature scanning tools, from the user’s perspective. We report results of the first time semi-quantitative comparison of 21 programs, which can search published (partial or full text) documents in life science areas. The observations can assist life science researchers and medical professionals to make an informed selection among the programs, depending on their search objectives. Some of the important findings are: 1. Most of the hits obtained from Scopus, ReleMed, EBImed, CiteXplore, and HighWire Press were usually relevant (i.e. these tools show a better precision than other tools). 2. But a very high number of relevant citations were retrieved by HighWire Press, Google Scholar, CiteXplore and Pubmed Central (they had better recall). 3. HWP and CiteXplore seemed to have a good balance of precision and recall efficiencies. 4. PubMed Central, PubMed and Scopus provided the most useful query systems. 5. GoPubMed, BioAsk, EBIMed, ClusterMed could be more useful among the tools that can automatically process the retrieved citations for further scanning of bio-entities such as proteins, diseases, tissues, molecular interactions, etc. The authors suggest the use of PubMed, Scopus, Google Scholar and HighWire Press – for better coverage, and GoPubMed – to view the hits categorized based on the MeSH and gene ontology terms. The article is relavant to all life science subjects. http://precedings.nature.com/documents/2101/version/1 Tue, 22 Jul 2008 10:50:58 UTC A comparative analysis of 21 literature search engines hdl:10101/npre.2008.2101.1 2008-07-22 Kshitish K. Acharya Nature Precedings 2008-07-22T10:50:58Z Manuscript Bioinformatics http://creativecommons.org/licenses/by/3.0/