Geoscience Reference
In-Depth Information
adding documents in the corpus remain efficient [MAR 05]. The contributions
presented in this chapter are the result of the work undertaken by the T2I
team of the LIUPPA laboratory, in the framework of the GEOSEM2, PIV and
GEOTOPIA projects (see Chapter 1). This work is mainly discussed in
[LEP 07, GAI 08, LES 07].
This chapter is organized into five sections. Following this introduction,
section 2.2 recalls the research questions raised in Chapter 1, which will be studied
here. Section 2.3 presents propositions found in published literature dealing with the
problem of space and time in the processes of annotation and indexing of texts as
well as in those of IR. Section 2.4 describes our propositions for indexing together
with the spatial and temporal IR. An overview of our contributions and their
perspectives are presented in section 2.5.
2.2. Review of challenges, hypotheses and research objectives
Here, we review a subset of issues, hypotheses and research objectives described
in Chapter 1. The main issue dealt with in this chapter is thus expressed in the
following question: What models of representation and retrieval of spatial and
temporal information should be proposed for the access by geographic content to
textual corpora?
The retained working hypotheses are the following:
- Adedicated spatialinformationretrievalsystem (IRS)givesbetterresults thana
classic thematic IRS for IR composed of only spatial criteria.
- A dedicated temporal IRS gives better results than a classic thematic IRS for IR
composed of only temporal criteria.
- A “rough” coupling of spatial, temporal and thematic IRSs gives better results
than a classic thematic IRS for multicriteria IR despite the numerous possible linked
biases.
Finally, the research objectives corresponding to the presented issues are mainly
aimed at the design and implementation of:
- models supporting the symbolic and numeric representation of spatial and
temporal data;
- process flows of spatial and temporal information extraction, interpretation and
indexing;
- spatial and temporal IR models.
The contribution concerns first of all the proposition of symbolic representation
models of spatial and temporal data. It also concerns the processes aiming at the
Search WWH ::
Custom Search