On the evaluation of Geographic Information Retrieval systems

Palacio, Damien; Cabanac, Guillaume; Sallaberry, Christian; Hubert, Gilles

doi:10.1007/s00799-011-0070-z

Cited by 17 publications

(28 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The problem is, as explained in [21], that there is no test collection covering all geographic dimensions (spatial, temporal and topical). So, we propose to evaluate the CMRP framework, implemented in PIV 3 , according to two case studies:…”

Section: Methodsmentioning

confidence: 99%

“…Another important feature of this approach lies in the generalized information representations and retrieval models supported by PIV spatial and PIV temporal primary IRSs [21]. Each IRS supports a tile-based generalization of spatial or temporal information.…”

Section: Piv 3 Meta-engine Implementing Cmrp Frameworkmentioning

confidence: 99%

“…The final scores are not biased since representations and scores were generalized prior to the combination process. We refer the reader to [21] for further explanations on this subject.…”

Section: Piv 3 Meta-engine Implementing Cmrp Frameworkmentioning

confidence: 99%

“…This is reinforced by Larson [14] when he demonstrates the effectiveness of Geographic Information Retrieval (GIR) methods in DLs. In [21] we introduced a system supporting the basic part of such queries (regular part of the query in Fig. 1) with matching operators dedicated to each dimension.…”

Section: Introductionmentioning

confidence: 99%

“…In Sect. 4, we report evaluations through experiments complying with the evaluation framework proposed in [21]. Finally, Sect.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Do Expressive Geographic Queries Lead to Improvement in Retrieval Effectiveness?

Palacio

Sallaberry

Cabanac

et al. 2012

Lecture Notes in Geoinformation and Cartography

Self Cite

View full text Add to dashboard Cite

Abstract. In an information retrieval (IR) context, users usually issue queries with few terms and no operators (e.g., and, or, +). However, most of users' information needs involve more expressiveness (e.g., 'Potato famine in Ireland, but not in Cork' ). Our work deals with this category of queries that may be processed by geographic IR (GIR) systems to parse digital libraries according to spatial, temporal and topical criteria. We propose a GIR framework that supports expressive queries and aggregates results of a multi-criteria search. We also conduct experiments to verify that this approach improves the effectiveness of such search engines (improvement of 27% for topical criteria only, and of 54% for spatial and temporal criteria).

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Piv 3 Meta-engine Implementing Cmrp Frameworkmentioning

confidence: 99%

“…The final scores are not biased since representations and scores were generalized prior to the combination process. We refer the reader to [21] for further explanations on this subject.…”

Section: Piv 3 Meta-engine Implementing Cmrp Frameworkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…In Sect. 4, we report evaluations through experiments complying with the evaluation framework proposed in [21]. Finally, Sect.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Do Expressive Geographic Queries Lead to Improvement in Retrieval Effectiveness?

Palacio

Sallaberry

Cabanac

et al. 2012

Lecture Notes in Geoinformation and Cartography

Self Cite

View full text Add to dashboard Cite

show abstract

Bibliography

2013

Geographical Information Retrieval in Textual Corpora

View full text Add to dashboard Cite

iAggregator: Multidimensional relevance aggregation based on a fuzzy operator

Moulahi

Tamine

Yahia

2014

Asso for Info Science & Tech

View full text Add to dashboard Cite

Recently, an increasing number of information retrieval studies have triggered a resurgence of interest in redefining the algorithmic estimation of relevance, which implies a shift from topical to multidimensional relevance assessment. A key underlying aspect that emerged when addressing this concept is the aggregation of the relevance assessments related to each of the considered dimensions. The most commonly adopted forms of aggregation are based on classical weighted means and linear combination schemes to address this issue. Although some initiatives were recently proposed, none was concerned with considering the inherent dependencies and interactions existing among the relevance criteria, as is the case in many real-life applications. In this article, we present a new fuzzy-based operator, called iAggregator, for multidimensional relevance aggregation. Its main originality, beyond its ability to model interactions between different relevance criteria, lies in its generalization of many classical aggregation functions. To validate our proposal, we apply our operator within a tweet search task. Experiments using a standard benchmark, namely, Text REtrieval Conference Microblog, 1 emphasize the relevance of our contribution when compared with traditional aggregation schemes. In addition, it outperforms state-of-the-art aggregation operators such as the Scoring and the And prioritized operators as well as some representative learning-to-rank algorithms. IntroductionMulticriteria aggregation is an issue that has been thoroughly addressed in social choice (Arrow, 1974;Condorcet, 1785;Fishburn, 1972), engineering design (Keeney & Raiffa, 1993;Neumann & Morgenstern, 1953), and computer vision applications (Dubois & Prade, 2004;Torra, 2005), to cite but a few. The multicriteria aggregation arises when for a given task there are several alternatives that have to be ordered with respect to different criteria and we are faced with the problem of combining them to figure out a ranking over the set of alternatives. The need to aggregate several inputs into a single representative output allowed successful applications of aggregation functions to fields as diverse as information retrieval (IR) (Farah & Vanderpooten, 2007) multiple criteria decision analysis (Grabisch, Kojadinovic, & Meyer, 2008;Steuer, 1986), data fusion (Ah-Pine, 2008;Vogt & Cottrell, 1999), and database retrieval (Le Calvè & Savoy, 2000). In this article, we are more interested in the IR field. Because ranking and relevance are at the heart of IR systems (Hawking, Craswell, Bailey, & Griffiths, 2001), a great deal of research has triggered a resurgence of interest in revisiting the concept of relevance considering several criteria. In fact, many of the proposed state-of-the-art early IR models rank documents by computing single scores separately with respect to one single objective criterion, rather than considering other relevance dimensions encompassing contextual features with respect to users or documents (Borlund, 2003). This most commonly used crit...

show abstract

On the evaluation of Geographic Information Retrieval systems

Cited by 17 publications

References 65 publications

Do Expressive Geographic Queries Lead to Improvement in Retrieval Effectiveness?

Do Expressive Geographic Queries Lead to Improvement in Retrieval Effectiveness?

Bibliography

iAggregator: Multidimensional relevance aggregation based on a fuzzy operator

Contact Info

Product

Resources

About