Towards new information resources for public health—From WordNet to MedicalWordNet

Abstract

In the last two decades, WordNet has evolved as the most comprehensive computational lexicon of general English. In this article, we discuss its potential for supporting the creation of an entirely new kind of information resource for public health, viz. MedicalWordNet. This resource is not to be conceived merely as a lexical extension of the original WordNet to medical terminology; indeed, there is already a considerable degree of overlap between WordNet and the vocabulary of medicine. Instead, we propose a new type of repository, consisting of three large collections of (1) medically relevant word forms, structured along the lines of the existing Princeton WordNet; (2) medically validated propositions, referred to here as medical facts, which will constitute what we shall call MedicalFactNet; and (3) propositions reflecting laypersons' medical beliefs, which will constitute what we shall call the MedicalBeliefNet. We introduce a methodology for setting up the MedicalWordNet. We then turn to the discussion of research challenges that have to be met to build this new type of information resource. We build a database of sentences relevant to the medical domain. The sentences are generated from WordNet via its relations as well as from medical statements broken down into elementary propositions. Two subcorpora of sentences are distinguished, MedicalBeliefNet and MedicalFactNet. The former is rated for assent by laypersons; the latter for correctness by medical experts. The sentence corpora will be valuable for a variety of applications in information retrieval as well as in research in linguistics and psychology with respect to the study of expert and non-expert beliefs and their linguistic expressions. Our work has to meet several considerable challenges. These include accounting for the distinction between medical experts and laypersons, the social issues of expert-layperson communication in different media, the linguistic aspects of encoding medical knowledge, and the reliability, volume, and emergence of medical knowledge. The work described here has been tested in a small pilot experiment and awaits large-scale implementation.

Semantic Retrieval of Trademarks Based on Conceptual Similarity

“…Nouns, verbs, adjectives, and adverbs are grouped into sets of cognitive synonyms that act as building blocks known as synsets [24]. Each synset represents a distinct concept and is linked by lexical relationships, such as synonymy, antonymy, hyponymy, and meronymy [25].…”

“…[26][27][28][29][30]. Additionally, the WordNet ontology has been utilized as an external knowledge source in various domains, such as in medical and inventive design [24,31,32]. The latest version of WordNet, WordNet 3.0, contains 155,287 strings and 117,659 synsets [33].…”

Towards knowledge modeling and manipulation technologies: A survey

“…WordNet (WN) is another large scale electronic lexical database conceived based on human semantic organization, where words and their meanings are related to one another via semantic and lexical similarities (Fellbaum et al, 2006). WN is a "proposal for a more effective combination of traditional lexicographic information and modern high-speed computation" (Miller et al, 1990).…”

“…WN is a "proposal for a more effective combination of traditional lexicographic information and modern high-speed computation" (Miller et al, 1990). Unlike FN, this model was constructed based on word association norms, where given a lexical stimulus such as a noun, verb or adjective, responses often remain in specific semantic relations such as synonyms (similar), antonyms (opposite), hyponyms (subordinate) / hypernyms (superior) and meronyms (part) / holonyms (whole) (Fadaee et al, 2013;Fellbaum et al, 2006;Lindén & Niemi, 2014;Marrafa, 2002). For example, "bird" can elicit its hypernym "animal" or its meronym "feather".…”

How to link ontologies and protein-protein interactions to literature: text-mining approaches and the BioCreative experience

“…A simple approach for measuring semantic similarity can be the calculation of the distance between two terms in the graph path underlying the ontology. Semantic similarity calculations have been promising for resources like WordNet (50,51), which is essentially a lexical database of English words together with their semantic relation types with practical usage for text analysis. This resource differs therefore in scope from GO or the PSI-MI ontology, whose primary use is for annotation of gene products.…”