Communications (unpublished | non publiées), Research seminars | Séminaires de recherche

Mapping WordNet to the Basic Formal Ontology

“Mapping WordNet to the Basic Formal Ontology”, in Buffalo Ontology Research Group Meeting, State University of New York at Buffalo, NY, June 8, 2015.

[ slides ]

ABSTRACT
We present preliminary work on the mapping of WordNet 3.0 to the Basic Formal Ontology (BFO 2.0). WordNet is a large semantic network linking sets of synonymous words (synsets) by means of semantic relations; it is widely used in natural language processing (NLP) tasks. BFO is a domain-neutral upper-level ontology that represents the types of things that exist in the world and relations between them. BFO serves as an integration hub for more specific ontologies, such as the Ontology for Biomedical Investigations (OBI) and the Cell Line Ontology (CLO). This work aims at creating a lexico‑semantic resource that can be used in NLP tools to perform ontology-related text manipulation tasks. Such tasks include semantic interpretation of natural language texts, word sense disambiguation, and information retrieval. The resource could, for example, be used to find terms in biomedical texts and link them to relevant BFO-based ontologies. Our semi-automatic mapping method consists in using existing mappings between WordNet and an upper-level ontology similar to BFO called KYOTO. The latter allows machines to reason over texts by providing interpretations of the words in ontological terms. Our working hypothesis is that a large portion of WordNet synsets can be semi-automatically mapped to BFO using simple mapping rules from KYOTO to BFO, e.g., ‘accomplishment > process’ and ‘#agentive-social-object > role’. The resulting mappings are to be read as ‘a WN synset X refers to something that is a subtype of BFO type Y’, e.g., the synset ‘immunity.n.02’ refers to a subtype of the BFO type ‘disposition’. We evaluate the method on medical synsets, examine preliminary results, and discuss issues related to the method. We conclude with suggestions for future work.

Standard
Communications (unpublished | non publiées), Research seminars | Séminaires de recherche

Mapping WordNet to the Basic Formal Ontology using the KYOTO ontology

“Mapping WordNet to the Basic Formal Ontology using the KYOTO ontology”, in UB’s 7th Annual Postdoc Research Symposium, State University of New York at Buffalo, NY, June 1, 2015 (Poster).

[ poster ]

ABSTRACT
We present preliminary work on the mapping of WordNet 3.0 to the Basic Formal Ontology (BFO 2.0). WordNet is a large semantic network linking sets of synonymous words (synsets) by means of semantic relations; it is widely used in natural language processing (NLP) tasks. BFO is a domain-neutral upper-level ontology that represents the types of things that exist in the world and relations between them. BFO serves as an integration hub for more specific ontologies, such as the Ontology for Biomedical Investigations (OBI) and the Cell Line Ontology (CLO). This work aims at creating a lexico‑semantic resource that can be used in NLP tools to perform ontology-related text manipulation tasks. Such tasks include semantic interpretation of natural language texts, word sense disambiguation, and information retrieval. The resource could, for example, be used to find terms in biomedical texts and link them to relevant BFO-based ontologies. Our semi-automatic mapping method consists in using existing mappings between WordNet and an upper-level ontology similar to BFO called KYOTO. The latter allows machines to reason over texts by providing interpretations of the words in ontological terms. Our working hypothesis is that a large portion of WordNet synsets can be semi-automatically mapped to BFO using simple mapping rules from KYOTO to BFO, e.g., ‘accomplishment > process’ and ‘#agentive-social-object > role’. The resulting mappings are to be read as ‘a WN synset X refers to something that is a subtype of BFO type Y’, e.g., the synset ‘immunity.n.02’ refers to a subtype of the BFO type ‘disposition’. We evaluate the method on medical synsets, examine preliminary results, and discuss issues related to the method. We conclude with suggestions for future work.

Standard
Communications (unpublished | non publiées), Research seminars | Séminaires de recherche

How the World Shapes the Meanings of Our Terms

“How the World Shapes the Meanings of Our Terms”, in UB’s 6th Annual Postdoc Research Symposium, State University of New York at Buffalo, NY, June 3, 2014.

[ poster ]

ABSTRACT

This interdisciplinary work in the fields of terminology, ontologies, and natural language processing (NLP) is concerned with natural language definitions in specialized dictionaries and ontologies. It focuses on the modeling of definition contents in view of creating language- and domain-independent tools to help terminologists and ontologists write definitions.

The underlying hypothesis for creating such generic definition-content models is that definitions express characteristics of the types of things to which specialized terms refer. Testing this hypothesis requires using a representation of the types of things that exist in the world, i.e. an ontology. This work uses the categories of the realist upper-level Basic Formal Ontology (BFO). Testing the hypothesis also requires applying these models on corpora of existing definitions to see to what extent the models predict definition contents.

The methodology consists in creating the definition models on the basis of the characteristics of the BFO categories, and using these models as a metalanguage to annotate large-scale multilingual and multi-domain corpora of textual definitions. This postdoctoral research aims at producing the necessary resources for such large-scale corpus analyses: the definition models; definition corpora; computer programs for automatic corpus pre-annotations; an annotation manual for an annotation campaign to create validated training-corpora and to obtain preliminary results.

Standard
Communications (unpublished | non publiées), Research seminars | Séminaires de recherche

Contraintes sur la sélection des informations dans les définitions terminographiques: vers des modèles relationnels génériques pertinents

“Contraintes sur la sélection des informations dans les définitions terminographiques: vers des modèles relationnels génériques pertinents”, in Séminaire de recherche, Laboratoire d’Informatique Fondamentale (LIF), Aix Marseille Université, February 24, 2012.

Standard