Deriving a representative vector for ontology classes with instance word vector embeddings

Jayawardana, Vindula; Silva, Nisansa de; Perera, Amal Shehan; Sugathadasa, Keet; Ayesha, Buddhi

doi:10.1109/intech.2017.8102426

Cited by 18 publications

(18 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As defined by Thomas R. Gruber [2], 'ontologies are an explicit and formal specifications of the terms in the domain and the relations among them'. Ontologies have been expanding out from the realm of Artificial-Intelligence to domain specific tasks such as: Linguistics [4,5,9,21,22], Law [19], Medicine [10,11,13,14,16]. Ontologies have become common on the semantic iteration of the World-Wide Web [12].…”

Section: A Ontologiesmentioning

confidence: 99%

“…Gerhard Wohlgenannt et al [32]'s approach to emulate a simple ontology using word2vec and Harmen Prins [33]'s usage of word2vec extension: node2vec [34], to overcome the problems in vectorization of an ontology, are two major works that have been carried out in relation to ontologies with the use of word2vec. More recently, there have been successful studies on using word2vec on the legal domain [19,20].…”

Section: B Word Vector Embeddingsmentioning

confidence: 99%

“…Therefore, Sugathadasa et al [20] have introduced a domain specific semantic similarity measure that has been created by the synergistic union of word2vec, a word embed-ding method that is used for semantic similarity calculation and lexicon based (lexical) semantic similarity methods. According to Sugathadasa et al, while for word context learning, Word Embedding method, word2vec [19,24]. has been used, number of lexical semantic similarity measures [38][39][40] have been used to augment and improve the results.…”

Section: E Domain Specific Semantic Similaritymentioning

confidence: 99%

“…We obtained a large legal text corpus from Findlaw [46] and built a word2vec model using the corpus. The reason for selecting word2vec word embedding for this study is the success demonstrated by other studies such as [19] and [20] in the legal domain that uses word2vec as the word embedding method. The text corpus consisted of legal cases under 78 law categories.…”

Section: B Training Word Embeddingsmentioning

confidence: 99%

“…We use these vectors as a method of arriving at instance population in an ontology. For this purpose, we built an iterative model based on the class representative vector for ontology classes [19]. In our implementation, we built multiple models based on different methodologies.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Word Vector Embeddings and Domain Specific Semantic based Semi-Supervised Ontology Instance Population

Jayawardana

Silva

Perera

et al. 2018

Int J on Adv. in ICT for Emerging Countries

Self Cite

View full text Add to dashboard Cite

Abstract-An ontology defines a set of representational primitives which model a domain of knowledge or discourse. With the arising fields such as information extraction and knowledge management, the role of ontology has become a driving factor of many modern day systems. Ontology population, on the other hand, is an inherently problematic process, as it needs manual intervention to prevent the conceptual drift. The semantic sensitive word embedding has become a popular topic in natural language processing with its capability to cope with the semantic challenges. Incorporating domain specific semantic similarity with the word embeddings could potentially improve the performance in terms of semantic similarity in specific domains. Thus, in this study, we propose a novel way of semi-supervised ontology population through word embeddings and domain specific semantic similarity as the basis. We built several models including traditional benchmark models and new types of models which are based on word embeddings. Finally, we ensemble them together to come up with a synergistic model which outperformed the candidate models by 33% in comparison to the best performed candidate model.

show abstract

Section: A Ontologiesmentioning

confidence: 99%

Section: B Word Vector Embeddingsmentioning

confidence: 99%

Section: E Domain Specific Semantic Similaritymentioning

confidence: 99%

Section: B Training Word Embeddingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Word Vector Embeddings and Domain Specific Semantic based Semi-Supervised Ontology Instance Population

Jayawardana

Silva

Perera

et al. 2018

Int J on Adv. in ICT for Emerging Countries

Self Cite

View full text Add to dashboard Cite

show abstract

Legal Document Retrieval Using Document Vector Embeddings and Deep Learning

Sugathadasa

Ayesha

Silva

et al. 2018

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

Domain specific information retrieval process has been a prominent and ongoing research in the field of natural language processing. Many researchers have incorporated different techniques to overcome the technical and domain specificity and provide a mature model for various domains of interest. The main bottleneck in these studies is the heavy coupling of domain experts, that makes the entire process to be time consuming and cumbersome. In this study, we have developed three novel models which are compared against a golden standard generated via the on line repositories provided, specifically for the legal domain. The three different models incorporated vector space representations of the legal domain, where document vector generation was done in two different mechanisms and as an ensemble of the above two. This study contains the research being carried out in the process of representing legal case documents into different vector spaces, whilst incorporating semantic word measures and natural language processing techniques. The ensemble model built in this study, shows a significantly higher accuracy level, which indeed proves the need for incorporation of domain specific semantic similarity measures into the information retrieval process. This study also shows, the impact of varying distribution of the word similarity measures, against varying document vector dimensions, which can lead to improvements in the process of legal information retrieval.

show abstract

Ontology Matching for Product Lifecycle Management

Smirnov¹,

Teslya²

2020

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Every product goes through many stages of the life cycle from manufacturing through usage to utilization. Some stages can change its properties, which in turn changes its description. To describe the product and its life cycle many ontologies have been created with varying levels of detail. Ontologies usage at different product lifecycle management (PLM) stages provides a better match to these stages since they provide properties of the product important only for this stage. During the transition between stages, the data should be integrated across all systems in manufacturing domain to provide semantic interoperability. Therefore, an issue arises of matching descriptions presented with ontologies of lifecycle stages. This is especially critical if ontologies for different stages are created by various specialists (for example, designer, technology engineer, retailer, maintainer, etc.). The paper proposes the method of matching ontologies for the formation of a common PLM ontology based on the automatic matching of ontologies referred to PLM stages. It allows to overcome heterogeneity and ensure interoperability in the process of tracking the product through the PLM stages. The matching process is based on the identification of common concepts by which ontologies will be combined into one. To identify common concepts, the ontology matching method is used, based on a combination of a context-based matching with neural network to find similarities of concepts (name, characteristics names and their string values) and study the ontology structure to identify common design patterns.

show abstract

Deriving a representative vector for ontology classes with instance word vector embeddings

Cited by 18 publications

References 20 publications

Word Vector Embeddings and Domain Specific Semantic based Semi-Supervised Ontology Instance Population

Word Vector Embeddings and Domain Specific Semantic based Semi-Supervised Ontology Instance Population

Legal Document Retrieval Using Document Vector Embeddings and Deep Learning

Ontology Matching for Product Lifecycle Management

Contact Info

Product

Resources

About