A semantic approach for the requirement-driven discovery of web resources in the Life Sciences

Pérez-Catalán, María; Berlanga, Rafael; Sanz, Ismael; Aramburu, María José

doi:10.1007/s10115-012-0498-5

Cited by 12 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To be able to exploit this contextual information, our approach is based on a topic-based ranking model described in [35]. Using this topic-based model, we can estimate the conditional probabilities of each concept c under a pre-defined set of topics t k (1≤ k ≤ n ) (where n is the number of topics) which roughly corresponds to bioinformatics generic tasks [36], such as sequence analysis, protein identification, etc.…”

Section: Methodsmentioning

confidence: 99%

BioUSeR: a semantic-based tool for retrieving Life Science web resources driven by text-rich user requirements

et al. 2013

Self Cite

View full text Add to dashboard Cite

BackgroundOpen metadata registries are a fundamental tool for researchers in the Life Sciences trying to locate resources. While most current registries assume that resources are annotated with well-structured metadata, evidence shows that most of the resource annotations simply consists of informal free text. This reality must be taken into account in order to develop effective techniques for resource discovery in Life Sciences.ResultsBioUSeR is a semantic-based tool aimed at retrieving Life Sciences resources described in free text. The retrieval process is driven by the user requirements, which consist of a target task and a set of facets of interest, both expressed in free text. BioUSeR is able to effectively exploit the available textual descriptions to find relevant resources by using semantic-aware techniques.ConclusionsBioUSeR overcomes the limitations of the current registries thanks to: (i) rich specification of user information needs, (ii) use of semantics to manage textual descriptions, (iii) retrieval and ranking of resources based on user requirements.

show abstract

Section: Methodsmentioning

confidence: 99%

BioUSeR: a semantic-based tool for retrieving Life Science web resources driven by text-rich user requirements

et al. 2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…Compared to other annotation alternatives, this tool offers a clean and simple approach and shows a good trade-off between performance and scalability. The tool has been successfully used in other scenarios, such us in [37], where they annotate the textual descriptions provided by catalogues of Life Science Web Services and align them with the user requirements. It is worth mentioning that this tool does not disambiguate annotations and can make errors.…”

Section: Cma Toolmentioning

confidence: 99%

Exploiting semantic annotations for open information extraction: an experience in the biomedical domain

Nebot

Berlanga

2012

Knowl Inf Syst

Self Cite

View full text Add to dashboard Cite

Abstract.The increasing amount of unstructured text published on the Web is demanding new tools and methods to automatically process and extract relevant information. Traditional information extraction has focused on harvesting domain-specific, pre-specified relations, which usually requires manual labor and heavy machinery. Especially in the biomedical domain the main efforts have been directed towards the recognition of welldefined entities such as genes or proteins, which constitutes the basis for extracting the relations between the recognized entities. The intrinsic features and scale of the Web demand new approaches able to cope with the diversity of documents, where the number of relations is unbounded and not known in advance. This paper presents a scalable method for the extraction of domain-independent relations from text that exploits the knowledge in the semantic annotations. The method is not geared to any specific domain (e.g., protein-protein interactions, drug-drug interactions, etc.) and does not require any manual input or deep processing. Moreover, the method uses the extracted relations to compute groups of abstract semantic relations characterized by their signature types and synonymous relation strings. This constitutes a valuable source of knowledge when constructing formal knowledge bases, as we enable seamless integration of the extracted relations with the available knowledge resources through the process of semantic annotation. The proposed approach has successfully been applied to a large text collection in the biomedical domain and the results are very encouraging.

show abstract

“…Nevertheless, metadata should characterize and describe objects in a relevant manner, which is sometimes (websites in particular) not the case (Ardo 2010). In case of web resources, the data are also very often unstructured and heterogeneous (Perez-Catalan et al 2013). …”

mentioning

confidence: 99%

Using metadata formats and AGROVOC thesaurus for data description in the agrarian sector

Šimek¹,

Vaněk²,

Jarolímek³

et al. 2013

PLANT SOIL ENVIRON

View full text Add to dashboard Cite

The paper deals with a general solution of semantic description related to various electronic data formats in the domains of agriculture, aquaculture, forestry, food industry, environment, horticulture and rural areas. The solution presented was developed on the basis of metadata formats analysis and then complemented with its own software superstructure. It is based on the VOA 3 R metadata application profile (AP) that was developed within the framework of the Virtual Open Access Agriculture and Aquaculture Repository project for the sake of describing research papers and scientific publications. However, thanks to its complexity and comprehensiveness, it is also suitable for different kinds of data and while combining it with the AGROVOC thesaurus, which is elaborated by the Food and Agriculture Organization of the United Nations, it can become a robust and universal tool for data characteristics and semantic description. The potential of the proposed solution is illustrated by means of two examples. While the first example brings a metadata description of a photograph depicting anthocyanin pigmentation of barley straw caused by phosphorus deficiency, the second example is related to a research paper description. The developed system of metadata description is broadly applicable in agriculture such as in precision agriculture, in plant production or in ground cover monitoring and evaluation based on sensor or visual data.

show abstract

A semantic approach for the requirement-driven discovery of web resources in the Life Sciences

Cited by 12 publications

References 49 publications

BioUSeR: a semantic-based tool for retrieving Life Science web resources driven by text-rich user requirements

BioUSeR: a semantic-based tool for retrieving Life Science web resources driven by text-rich user requirements

Exploiting semantic annotations for open information extraction: an experience in the biomedical domain

Using metadata formats and AGROVOC thesaurus for data description in the agrarian sector

Contact Info

Product

Resources

About