USE CASE SIBiLS SPARQL endpoint
It provides a way to retrieve scientific publications very accurately. The system uses the SPARQL language to search scientific publications in full text as well as named entities identified in the full text.
Need:
It provides a method to extract scientific statements from the litterature based on standard terminologies and controlled vocabularies
Added Value:
Flexibility, precision.
Competitive Advantage:
Compared to classic text mining, named entities identified in the full text improves the recall of queries by exploiting synonyms and semantic relationships declared in the terminologies, it also increases precision because queries allow to focus of structural elements (given section, paragraph, and / or sentence) on demand.
A qualitative upgrade on the current use of biodiversity data:
Given a topic of interest, the service can be used to extract relevant statements from the literature with a good precision.
Exemplary Use of the Service:
Find biotic interactions described in the lterature between a given species and other ones.
Competencies and Skills that are needed to use the Service:
Knowledge of the SPARQL language is required.
Challenges for the Users:
The SPARQL language is not straightforward for non specialists.
Users Role in the Service Development
The role of the users is important mainly in providing help to design and assess a natural language based query system on top of SPARQL using MMLs.