Spreading Relation Annotations in a Lexical Semantic Network Applied to Radiology

Ramadier, Lionel; Zarrouk, Manel; Lafourcade, Mathieu; Micheau, Antoine

doi:10.1007/978-3-642-54906-9_4

Cited by 3 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…r_synonym synonyms or quasi-synonyms r_syn_strict strict synonyms r_isa generic term r_equiv acronym or abbreviation We use this network because it combines weight and annotations [20] on typed relations between terms. In the network JDM, the relations are weighted, the weight reflects the strength of association between terms.…”

Section: Resourcesmentioning

confidence: 99%

Radiological Text Simplification Using a General Knowledge Base

Ramadier

Lafourcade

2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

In the medical domain, text simplification is both a desirable and a challenging natural language processing task. Indeed, first, medical texts can be difficult to understand for patient, because of the presence of specialized medical terms. Replacing these difficult terms with easier words can lead to improve patient's understanding. In this paper, we present a lexical network based method to simplify health information in French language. We deal with semantic difficulty by replacement difficult term with supposedly easier synonyms or by using semantically related term with the help of a French lexical semantic network. We extract semantic and lexical information present in the network. In this paper, we present such a method for text simplification along with its qualitative evaluation.

show abstract

Section: Resourcesmentioning

confidence: 99%

Radiological Text Simplification Using a General Knowledge Base

Ramadier

Lafourcade

2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…This mechanism has been described in a previous work [10]. [12]. Informal deductive inference scheme with logical blocking.…”

Section: The Contributive Model Of Diko and Relation Annotationsmentioning

confidence: 99%

“…Moreover, to have the most accurate annotation, we need to order the central terms from the most specific to the less specific as we wrote down in [12]. That is to say, we try to reconstitute the taxonomic order related to the hypernym relation (is-a).…”

Section: Using Generic Partial Ordersmentioning

confidence: 99%

Inferring Relations and Annotations in Semantic Network: Application to Radiology

Ramadier

Zarrouk

Lafourcade

et al. 2014

CyS

Self Cite

View full text Add to dashboard Cite

Domain specific ontologies are invaluable despite many challenges associated with their development. In most cases, domain knowledge bases are built with very limited scope without considering the benefits of plunging domain knowledge to a general ontology. Furthermore, most existing resources lack meta-information about association strength (weights) and annotations (frequency information like frequent, rare ... or relevance information like pertinent or irrelevant). In this paper, we are presenting a semantic resource for radiology built over an existing general semantic lexical network (JeuxDeMots). This network combines weight and annotations on typed relations between terms and concepts. Some inference mechanisms are applied to the network to improve its quality and coverage. We extend this mechanism to relation annotation. We describe how annotations are handled and how they improve the network by imposing new constraints especially those founded on medical knowledge.

show abstract

A Taxonomy and Survey of Semantic Approaches for Query Expansion

et al. 2019

View full text Add to dashboard Cite

Conventional approaches to query expansion (QE) rely on the integration of an unstructured corpus and probabilistic rules for the extraction of candidate expansion terms. These methods do not consider search query semantics, thereby resulting in ineffective retrieval of information. The semantic approaches for QE overcome this limitation, whereby a search query is expanded with meaningful terms that accord with user information needs. This paper surveys recent approaches to semantic QE that employ different models and strategies and leverages various knowledge structures. We organize these approaches into a taxonomy that includes linguistic methods, ontology-based methods, and mixed-mode methods. We also discuss the strengths and limitations of each type of semantic QE method. In addition, we evaluate various semantic QE approaches in terms of knowledge structure utilization, corpus collection, baseline model adaptation, and retrieval performance. Finally, future directions in exploiting personalized social information and multiple ontologies for semantic QE are suggested. INDEX TERMS Information retrieval, morphological expansion, ontology, semantic query expansion.

show abstract

Spreading Relation Annotations in a Lexical Semantic Network Applied to Radiology

Cited by 3 publications

References 7 publications

Radiological Text Simplification Using a General Knowledge Base

Radiological Text Simplification Using a General Knowledge Base

Inferring Relations and Annotations in Semantic Network: Application to Radiology

A Taxonomy and Survey of Semantic Approaches for Query Expansion

Contact Info

Product

Resources

About