Concept-aware geographic information retrieval

Abstract

Textual queries are largely employed in information retrieval to let users specify search goals in a natural way. However, di erences in user and system terminologies can challenge the identi cation of the user's information needs, and thus the generation of relevant results. We argue that the explicit management of ontological knowledge, and of the meaning of concepts (by integrating linguistic and encyclopaedic knowledge in the system ontology), can improve the analysis of search queries, because it enables a exible identi cation of the topics the user is searching for, regardless of the adopted vocabulary.is paper proposes an information retrieval support model based on semantic concept identi cation. Starting from the recognition of the ontology concepts that the search query refers to, this model exploits the quali ers speci ed in the query to select information items on the basis of possibly ne-grained features. Moreover, it supports query expansion and reformulation by suggesting the exploration of semantically similar concepts, as well as of concepts related to those referred in the query through thematic relations. A test on a data-set collected using the OnToMap Participatory GIS has shown that this approach provides accurate results.

Faceted search of heterogeneous geographic information for dynamic map projection

“…Notice also that OnToMap does not assume to work on RDF data in order to comply with more general data sources, like public crowdmapping platforms, thanks to the mediation of its domain ontology. Moreover, it supports: (i) a browsing-based exploration guided by the structure of the domain ontology, which makes it possible to search for information following both IS-A and semantic relations; (ii) the semantic interpretation of free text queries to identify the data categories (ontology concepts) of interest by abstracting from the specific words occurring in the queries, via Natural Language Processing (Ardissono et al, 2016;Mauro et al, 2017). More generally, OnToMap enables search support over a configurable set of data categories; in this way, it enables complex map development on different information domains.…”

Extending a Tag-based Collaborative Recommender with Co-occurring Information Interests

“…Moreover, Huang et al [17] and Chen et al [8] detect term co-occurrence in search sessions to group sets of relevant words that can be mutually suggested. Our work is di erent because we adopt a linguistic interpretation approach (based on lemmatization and Word Sense Disambiguation) to nd the concepts referenced in the queries; see [27]. erefore, we extract information about concept co-occurrence, which is more general than term co-occurrence.…”

A Semantic Retrieval System in Remote Sensing Web Platforms

“…Complexity of queries writing is also a remaining challenge when it comes to ontology uses in knowledge discovery (Munir & Sheraz Anjum, 2018). Some proposition tried to consider textual queries instead of simple words matching between lists (Mauro et al, 2017). Nevertheless, these examples do not reflect human languages complexity and limit their proposition to terms matching.…”