Automated learning of domain taxonomies from text using background knowledge

Hoxha, Julia; Jiang, Guoqian; Weng, Chunhua

doi:10.1016/j.jbi.2016.09.002

Cited by 20 publications

(16 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, creating gold standard labeled datasets is laborious and subjective. Hoxha et al [28] recently developed Ontofier, an unsupervised ontology learning framework that uses the agglomerative hierarchical clustering to learn domain taxonomies. They used agglomerative hierarchical clustering to produce a dendrogram (i.e., a tree diagram) that can be pruned to be a taxonomy with parent-child relations.…”

Section: Related Workmentioning

confidence: 99%

Enriching consumer health vocabulary through mining a social Q&A site: A similarity-based approach

Chen

et al. 2017

Journal of Biomedical Informatics

View full text Add to dashboard Cite

The widely known vocabulary gap between health consumers and healthcare professionals hinders information seeking and health dialogue of consumers on end-user health applications. The Open Access and Collaborative Consumer Health Vocabulary (OAC CHV), which contains health-related terms used by lay consumers, has been created to bridge such a gap. Specifically, the OAC CHV facilitates consumers’ health information retrieval by enabling consumer-facing health applications to translate between professional language and consumer friendly language. To keep up with the constantly evolving medical knowledge and language use, new terms need to be identified and added to the OAC CHV. User-generated content on social media, including social question and answer (social Q&A) sites, afford us an enormous opportunity in mining consumer health terms. Existing methods of identifying new consumer terms from text typically use ad-hoc lexical syntactic patterns and human review. Our study extends an existing method by extracting n-grams from a social Q&A textual corpus and representing them with a rich set of contextual and syntactic features. Using K-means clustering, our method, simiTerm, was able to identify terms that are both contextually and syntactically similar to the existing OAC CHV terms. We tested our method on social Q&A corpora on two disease domains: diabetes and cancer. Our method outperformed three baseline ranking methods. A post-hoc qualitative evaluation by human experts further validated that our method can effectively identify meaningful new consumer terms on social Q&A.

show abstract

Section: Related Workmentioning

confidence: 99%

Enriching consumer health vocabulary through mining a social Q&A site: A similarity-based approach

Chen

et al. 2017

Journal of Biomedical Informatics

View full text Add to dashboard Cite

show abstract

“…The other table is Concept Table (CT), which continues adding concepts to the table as new undefined words are added. [8] At the point when the words captured are feed from the table, the quantity of words is calculated. Checking the count to be lesser than the quantity of words acquired for the table, the technique proceeds.…”

Section: Algorithmmentioning

confidence: 99%

A Knowledge Representation Model using Concept-Relation Graph

P.¹,

Selwyn²

2019

IJEAT

View full text Add to dashboard Cite

Huge volume of relevant and irrelevant information is available from different sources for gaining knowledge about a system. If the required data is in a structured form, then the fact can be easily understood otherwise the process becomes laborious and results are vague after intense analysis. In this paper, we are proposing a framework for fetching knowledge from unstructured source of data. The algorithms proposed identifies the concepts and separates the concepts and relation words, enables to add new concepts and also modify the old concept word with new concept and locate the concept. This Concept-Relation Model enables the system to work according to the users’ connivance and deliveries accurate knowledge. This model does not manipulate or interpret the information provided but only represent and share the desired knowledge.

show abstract

“…For example, our group recently developed an open source text mining tool called simiTerm to identify the terms in a text corpus that are contextually and syntactically similar to existing terms in an ontology [11]. Hoxha et al [8] developed Ontofier, an unsupervised ontology learning framework that uses agglomerative hierarchical clustering to learn domain taxonomies from biomedical texts. These methods, which focused on building lightweight ontologies, do not intend to enrich existing ontologies with new concepts and cannot identify the locations for them in the existing ontology.…”

Section: Background and Related Workmentioning

confidence: 99%

“…The traditional top-down approach for ontology development involves iterative discussions among ontology developers and domain experts, which is labor intensive and time consuming [7]. Thus, automated and semi-automated ontology learning methods, which may ease the burden of ontology developers and accelerate ontology development, are highly desired [8–12].…”

Section: Introductionmentioning

confidence: 99%

Extended Analysis of Topological-Pattern-Based Ontology Enrichment

Keloth

Chen³

et al. 2018

2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

View full text Add to dashboard Cite

Maintenance of biomedical ontologies is difficult. We have previously developed a topological-pattern-based method to deal with the problem of identifying concepts in a reference ontology that could be of interest for insertion into a target ontology. Assuming that both ontologies are parts of the Unified Medical Language System (UMLS), the method suggests approximate locations where the target ontology could be extended with new concepts from the reference ontology. However, the final decision about each concept has to be made by a human expert. In this paper, we describe the universe of cross-ontology topological patterns in quantitative terms. We then present a theoretical analysis of the number of potential placements of reference concepts in a path in a target ontology, allowing for new cross-ontology synonyms. This provides a rough estimate of what expert resources need to be allocated for the task. One insight in previous work on this topic was the large percentage of cases where importing concepts was impossible, due to a configuration called “alternative classification.” In this paper, we confirm this observation. Our target ontology is the National Cancer Institute thesaurus (NCIt). However, the methods can be applied to other pairs of ontologies with hierarchical relationships from the UMLS.

show abstract

Automated learning of domain taxonomies from text using background knowledge

Cited by 20 publications

References 32 publications

Enriching consumer health vocabulary through mining a social Q&A site: A similarity-based approach

Enriching consumer health vocabulary through mining a social Q&A site: A similarity-based approach

A Knowledge Representation Model using Concept-Relation Graph

Extended Analysis of Topological-Pattern-Based Ontology Enrichment

Contact Info

Product

Resources

About