Entity Linking and Lexico-Semantic Patterns for Ontology Learning

Saeeda, Lama; Med, Michal; Ledvinka, Martin; Blaško, Miroslav; Křemen, Petr

doi:10.1007/978-3-030-49461-2_9

Cited by 3 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this manner, documents and web pages linked to the given concept can be listed. TermIt uses Annotace [17], a standalone text analysis service, to discover concept occurrences in documents and suggest new concepts based on their significance in the text. As the service is based on the Czech language for which a gold standard is not available yet, Annotace is only used for concept suggestions -a domain expert has to always review and confirm them.…”

Section: Document Annotation and Web Annotationmentioning

confidence: 99%

See 1 more Smart Citation

TermIt: Managing normative thesauri

Křemen,

Med,

Blaško

et al. 2024

Self Cite

View full text Add to dashboard Cite

Thesauri are popular, as they represent a manageable compromise – they are well-understood by domain experts, yet formal enough to boost use cases like semantic search. Still, as the thesauri size and complexity grow in a domain, proper tracking of the concept references to their definitions in normative documents, interlinking concepts defined in different documents, and keeping all the concepts semantically consistent and ready for subsequent conceptual modeling, is difficult and requires adequate tool support. We present TermIt, a web-based thesauri manager aimed at supporting the creation of thesauri based on decrees, directives, standards, and other normative documents. In addition to common editing capabilities, TermIt offers term extraction from documents, including a web document annotation browser plug-in, tracking term definitions in documents, term quality and ontological correctness checking, community discussions over term meanings, and seamless interlinking of concepts across different thesauri. We also show that TermIt features better fit the E-government scenarios in the Czech Republic than other tools. Additionally, we present the feasibility of TermIt for these scenarios by preliminary user experience evaluation.

show abstract

Section: Document Annotation and Web Annotationmentioning

confidence: 99%

“…Various tools addressing the problems P1-P3 were investigated, which we described in a survey report. 17 For P1, tools that are able to express concepts, i.e. the meaning of terms can be utilized.…”

Section: Related Workmentioning

confidence: 99%

TermIt: Managing normative thesauri

Křemen,

Med,

Blaško

et al. 2024

Self Cite

View full text Add to dashboard Cite

show abstract

“…Research has targeted many different aspects to achieve the goal of structuring the information present on the Internet. Since the outcome of ontology modeling techniques is strongly dependent on the nature of the data itself ( Saeeda et al, 2020 ), researchers have proposed specialized ontologies to better describe various aspects of a domain. As an example, Stolz, Hepp & Hemminger (2017) proposed a vocabulary for the domain of garments that can be used to express web page content and enable the Semantic web.…”

Section: Literature Reviewmentioning

confidence: 99%

Autonomous schema markups based on intelligent computing for search engine optimization

Abbasi

Fatima²,

Mukhtar

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

With advances in artificial intelligence and semantic technology, search engines are integrating semantics to address complex search queries to improve the results. This requires identification of well-known concepts or entities and their relationship from web page contents. But the increase in complex unstructured data on web pages has made the task of concept identification overly complex. Existing research focuses on entity recognition from the perspective of linguistic structures such as complete sentences and paragraphs, whereas a huge part of the data on web pages exists as unstructured text fragments enclosed in HTML tags. Ontologies provide schemas to structure the data on the web. However, including them in the web pages requires additional resources and expertise from organizations or webmasters and thus becoming a major hindrance in their large-scale adoption. We propose an approach for autonomous identification of entities from short text present in web pages to populate semantic models based on a specific ontology model. The proposed approach has been applied to a public dataset containing academic web pages. We employ a long short-term memory (LSTM) deep learning network and the random forest machine learning algorithm to predict entities. The proposed methodology gives an overall accuracy of 0.94 on the test dataset, indicating a potential for automated prediction even in the case of a limited number of training samples for various entities, thus, significantly reducing the required manual workload in practical applications.

show abstract

“…Some research devoted to solving the problem of full automatic or semi-automatic replenishment of the ontology rely on patterns that reflect the linguistic structures found in the texts into similar ontology elements (relations, concepts, samples of instances and relations). These are lexical-syntactic patterns that use lexical representations and syntactic information [16], [17] or lexical-semantic patterns that combine lexical representations with syntactic and semantic information during the extraction process [18], [19].…”

mentioning

confidence: 99%

Approach to automating the construction and completion of ontologies in a scientific subject field

Sadirmekova,

Murzakhmetov,

Abduvalova

et al. 2024

IJECE

View full text Add to dashboard Cite

Domain ontologies facilitate the organization, sharing, and reuse of subject areas. Building a software ontology is labor-intensive and time-consuming. In the process of obtaining a software ontology, it is required to analyze a huge number of scientific publications relevant to the software being modeled. The process of ontology replenishing with information from a huge number of scientific publications can be facilitated and accelerated through the use of lexical-syntactic patterns of ontological design. In this paper, we consider the possibility of automated construction of scientific subject area ontologies based on a heterogeneous patterns system of ontological design. This system includes ontological design patterns and is intended for ontology developers. System also includes automatically built lexical and syntactic patterns, which help to automatic replenishment of the ontology with information extracted from natural language texts.

show abstract

Entity Linking and Lexico-Semantic Patterns for Ontology Learning

Cited by 3 publications

References 14 publications

TermIt: Managing normative thesauri

TermIt: Managing normative thesauri

Autonomous schema markups based on intelligent computing for search engine optimization

Approach to automating the construction and completion of ontologies in a scientific subject field

Contact Info

Product

Resources

About