Enrichment of the phenotypic and genotypic Data Warehouse analysis using Question Answering systems to facilitate the decision making process in cereal breeding programs

Peral, Jesús; Ferrández, Antonio; Gregorio, Elisa de; Trujillo, Juan; Maté, Alejandro; Ferrández, Luis José

doi:10.1016/j.ecoinf.2014.05.003

Cited by 6 publications

(8 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our proposal facilitates the decision making process because it extends our previous work in Peral et al (2015), in which, internal structured information (e.g. the CEREALAB database, Milc et al, 2011) and external unstructured data obtained from the Web (e.g.…”

mentioning

confidence: 78%

“…Our proposal is embedded into our previous work in Peral et al (2015) that provides a framework for integrating unstructured and structured information in a common interface, like a dashboard, where easily the user can interpret his needed information. This framework is depicted in Figure 1.…”

Section: The Integration Of Our Proposal Into An Architecture To Accementioning

confidence: 99%

“…A remarkable issue is that the questions are always classified as the search of concepts marked by the first NP in the question, instead of a question whose answer is just yes/no. Moreover, we should highlight that in our framework (Peral et al, 2015) the user can decide if he/she wishes to consult external data in order to answer the question. In this case, the QA node of the proposed architecture is the responsible to provide the answer.…”

Section: Series Of Context Questionsmentioning

confidence: 99%

“…This case scenario will use our framework in Peral et al (2015), in which the decision maker of the breeding program can easily access to external data about relevant agronomic traits and draw up new molecular protocols to design genetically modified crops in order to increase the productivity of the seed industry. As described in the previous section, our authoring tool to deal with anaphora, ellipsis and context questions is embedded in the GUI module of this framework, in which the user poses the NL questions to query the CEREALAB database (Milc et al, 2011).…”

Section: Descriptionmentioning

confidence: 99%

“…This anaphora resolution tool achieves a precision of 81% in Spanish pronouns, 74% in English, 78% in definite descriptions, all these figures on general purpose corpora. In respect of the implementation of the framework in Peral et al (2015), it is using the open-source BI platform called Pentaho, which provides the necessary OLAP capabilities by means of the Mondrian OLAP server. The OLAP server was connected to a MySQL Server 5.6 DBMS that stores the data for the analysis.…”

Section: Series Of Context Questionsmentioning

confidence: 99%

See 4 more Smart Citations

An authoring tool for decision support systems in context questions of ecological knowledge

Ferrández¹,

Peral²,

Gregorio³

et al. 2015

Ecological Informatics

Self Cite

View full text Add to dashboard Cite

Decision support systems (DSS) support business or organizational decision-making activities, which require the access to information that is internally stored in databases or data warehouses, and externally in the Web accessed by Information Retrieval (IR) or Question Answering (QA) systems. Graphical interfaces to query these sources of information ease to constrain dynamically query formulation based on user selections, but they present a lack of flexibility in query formulation, since the expressivity power is reduced to the user interface design. Natural language interfaces (NLI) are expected as the optimal solution. However, especially for non-expert users, a real natural communication is the most difficult to realize effectively. In this paper, we propose a NLI that improves the interaction between the user and the DSS by means of referencing previous questions or their answers (i.e. anaphora such as the pronoun reference in -What traits are affected by them?‖), or by eliding parts of the question (i.e. ellipsis such as -And to glume colour?‖ after the question -Tell me the QTLs related to awn colour in wheat‖). Moreover, in order to overcome one of the main problems of NLIs about the difficulty to adapt a NLI to a new domain, our proposal is based on ontologies that are obtained semi-automatically from a framework that allows the integration of internal and external, structured and unstructured information. Therefore, our proposal can interface with databases, data warehouses, QA and IR systems. Because of the high NL ambiguity of the resolution process, our proposal is presented as an authoring tool that helps the user to query efficiently in natural language. Finally, our proposal is tested on a DSS case scenario about Biotechnology and Agriculture, whose knowledge base is the CEREALAB database as internal structured data, and the Web (e.g. PubMed) as external unstructured information.

show abstract

mentioning

confidence: 78%

Section: The Integration Of Our Proposal Into An Architecture To Accementioning

confidence: 99%

Section: Series Of Context Questionsmentioning

confidence: 99%

Section: Descriptionmentioning

confidence: 99%

Section: Series Of Context Questionsmentioning

confidence: 99%

See 3 more Smart Citations