Dataset Information

Combining lexical and context features for automatic ontology extension.

ABSTRACT: BACKGROUND:Ontologies are widely used across biology and biomedicine for the annotation of databases. Ontology development is often a manual, time-consuming, and expensive process. Automatic or semi-automatic identification of classes that can be added to an ontology can make ontology development more efficient. RESULTS:We developed a method that uses machine learning and word embeddings to identify words and phrases that are used to refer to an ontology class in biomedical Europe PMC full-text articles. Once labels and synonyms of a class are known, we use machine learning to identify the super-classes of a class. For this purpose, we identify lexical term variants, use word embeddings to capture context information, and rely on automated reasoning over ontologies to generate features, and we use an artificial neural network as classifier. We demonstrate the utility of our approach in identifying terms that refer to diseases in the Human Disease Ontology and to distinguish between different types of diseases. CONCLUSIONS:Our method is capable of discovering labels that refer to a class in an ontology but are not present in an ontology, and it can identify whether a class should be a subclass of some high-level ontology classes. Our approach can therefore be used for the semi-automatic extension and quality control of ontologies. The algorithm, corpora and evaluation datasets are available at https://github.com/bio-ontology-research-group/ontology-extension.

SUBMITTER: Althubaiti S

PROVIDER: S-EPMC6958746 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Combining lexical and context features for automatic ontology extension.

Althubaiti Sara S Kafkas Şenay Ş Abdelhakim Marwa M Hoehndorf Robert R

Journal of biomedical semantics 20200113 1

<h4>Background</h4>Ontologies are widely used across biology and biomedicine for the annotation of databases. Ontology development is often a manual, time-consuming, and expensive process. Automatic or semi-automatic identification of classes that can be added to an ontology can make ontology development more efficient.<h4>Results</h4>We developed a method that uses machine learning and word embeddings to identify words and phrases that are used to refer to an ontology class in biomedical Europe ...[more]

PMID: 31931870

Similar Datasets

Project description:BACKGROUND: Caused by intracellular Gram-negative bacteria Brucella spp., brucellosis is the most common bacterial zoonotic disease. Extensive studies in brucellosis have yielded a large number of publications and data covering various topics ranging from basic Brucella genetic study to vaccine clinical trials. To support data interoperability and reasoning, a community-based brucellosis-specific biomedical ontology is needed. RESULTS: The Brucellosis Ontology (IDOBRU: http://sourceforge.net/projects/idobru), a biomedical ontology in the brucellosis domain, is an extension ontology of the core Infectious Disease Ontology (IDO-core) and follows OBO Foundry principles. Currently IDOBRU contains 1503 ontology terms, which includes 739 Brucella-specific terms, 414 IDO-core terms, and 350 terms imported from 10 existing ontologies. IDOBRU has been used to model different aspects of brucellosis, including host infection, zoonotic disease transmission, symptoms, virulence factors and pathogenesis, diagnosis, intentional release, vaccine prevention, and treatment. Case studies are typically used in our IDOBRU modeling. For example, diurnal temperature variation in Brucella patients, a Brucella-specific PCR method, and a WHO-recommended brucellosis treatment were selected as use cases to model brucellosis symptom, diagnosis, and treatment, respectively. Developed using OWL, IDOBRU supports OWL-based ontological reasoning. For example, by performing a Description Logic (DL) query in the OWL editor Protégé 4 or a SPARQL query in an IDOBRU SPARQL server, a check of Brucella virulence factors showed that eight of them are known protective antigens based on the biological knowledge captured within the ontology. CONCLUSIONS: IDOBRU is the first reported bacterial infectious disease ontology developed to represent different disease aspects in a formal logical format. It serves as a brucellosis knowledgebase and supports brucellosis data integration and automated reasoning.

Project description:In this paper, we discuss the results of two experiments, one off-line (acceptability judgment) and the other on-line (eye-tracking), targeting Object Cleft (OC) constructions. In both experiments, we used the same materials presenting a manipulation on person features: second person plural pronouns and plural definite determiners alternate in introducing a full NP ("it was [DP1 the/you [NP bankers]]i that [DP2 the/you [NP lawyers]] have avoided _i at the party") in a language, Italian, with overt person (and number) subject-verb agreement. As results, we first observed that the advantage of the bare pronominal forms reported in previous experiments (Gordon et al., 2001; Warren and Gibson, 2005, a.o.) is lost when the full NP (the "lexical restriction" in Belletti and Rizzi, 2013) is present. Second, an advantage for the mismatch condition, Art 1 -Pro 2, in which the focalized subject is introduced by the determiner and the OC subject by the pronoun, as opposed to the matching Pro 1 -Pro 2 condition, is observed, both off-line (higher acceptability and accuracy in answering comprehension questions after eyetracking) and on-line (e.g., smaller number of regressions from the subject region); third, we found a relevant difference between acceptability and accuracy in comprehension questions: despite similar numerical patterns in both off-line measures, the difference across conditions in accuracy is mostly not significant, while it is significant in acceptability. Moreover, while the matching condition Pro 1 -Pro 2 is perceived as nearly ungrammatical (far below the mean acceptability across-conditions), the accuracy in comprehension is still high (close to 80%). To account for these facts, we compare different formal competence and processing models that predict difficulties in OC constructions: similarity-based (Gordon et al., 2001, a.o.), memory load (Gibson, 1998), and intervention-based (Friedmann et al., 2009) accounts are compared to processing oriented ACT-R-based predictions (Lewis and Vasishth, 2005) and to top-down Minimalist derivations (Chesi, 2015). We conclude that most of these approaches fail in making predictions able to reconcile the competence and the performance perspective in a coherent way to the exception of the top-down model that is able to predict correctly both the on-line and the off-line main effects obtained.

Dataset Information

Combining lexical and context features for automatic ontology extension.

Publications

Combining lexical and context features for automatic ontology extension.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets