Paper: Exploring Graph Structure for Detection of Reliability Zones within Synonym Resources: Experiment with the Gene Ontology

ACL ID W09-1311
Title Exploring Graph Structure for Detection of Reliability Zones within Synonym Resources: Experiment with the Gene Ontology
Venue Workshop on Biomedical Natural Language Processing
Session
Year 2009
Authors
  • Thierry Hamon (CNRS, France; University of Paris 13, Villetaneuse France)
  • Natalia Grabar (University of Paris 5, Paris France; INSERM, Villejuif France)

Computing the semantic similarity between terms relies on existence and usage of seman- tic resources. However, these resources, often composed of equivalent units, or synonyms, must be first analyzed and weighted in or- der to define within them the reliability zones where the semantic cohesiveness is stronger. We propose an original method for acquisition of elementarysynonyms based onexploitation of structured terminologies, analysis of syn- tactic structure of complex (multi-unit) terms and their compositionality. The acquired syn- onyms are then profiled thanks to endogenous lexical and linguistic indicators (other types of relations, lexical inclusions, productivity), which are automatically inferred within the same terminologies. Additionally, synonymy relations are observed within ...