Mining information from sentences through Semantic Web data and Information Extraction tasks

Martinez-Rodriguez, Jose L.; López-Arévalo, Iván; Ríos-Alvarado, Ana B.

doi:10.1177/0165551520934387

Cited by 12 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such solutions could be classified as symbolic or statistical (Liu et al , 2011; Maedche et al , 2002). The challenge is to parse information pieces because the statements that lack specific language descriptions or a structure that computers can comprehend directly (Martinez-Rodriguez et al , 2022). In general, the extraction of concepts and synonyms deals with fewer challenges rather than the extraction of relations.…”

Section: Methodsmentioning

confidence: 99%

Semi-automated ontology development scheme via text mining of scientific records

Tamjid,

Nooshinfard,

Hosseini Beheshti

et al. 2024

View full text Add to dashboard Cite

Purpose The purpose of this study is to develop a domain independent, cost-effective, time-saving and semi-automated ontology generation framework that could extract taxonomic concepts from unstructured text corpus. In the human disease domain, ontologies are found to be extremely useful for managing the diversity of technical expressions in favour of information retrieval objectives. The boundaries of these domains are expanding so fast that it is essential to continuously develop new ontologies or upgrade available ones. Design/methodology/approach This paper proposes a semi-automated approach that extracts entities/relations via text mining of scientific publications. Text mining-based ontology (TmbOnt)-named code is generated to assist a user in capturing, processing and establishing ontology elements. This code takes a pile of unstructured text files as input and projects them into high-valued entities or relations as output. As a semi-automated approach, a user supervises the process, filters meaningful predecessor/successor phrases and finalizes the demanded ontology-taxonomy. To verify the practical capabilities of the scheme, a case study was performed to drive glaucoma ontology-taxonomy. For this purpose, text files containing 10,000 records were collected from PubMed. Findings The proposed approach processed over 3.8 million tokenized terms of those records and yielded the resultant glaucoma ontology-taxonomy. Compared with two famous disease ontologies, TmbOnt-driven taxonomy demonstrated a 60%–100% coverage ratio against famous medical thesauruses and ontology taxonomies, such as Human Disease Ontology, Medical Subject Headings and National Cancer Institute Thesaurus, with an average of 70% additional terms recommended for ontology development. Originality/value According to the literature, the proposed scheme demonstrated novel capability in expanding the ontology-taxonomy structure with a semi-automated text mining approach, aiming for future fully-automated approaches.

show abstract

Section: Methodsmentioning

confidence: 99%

Semi-automated ontology development scheme via text mining of scientific records

Tamjid,

Nooshinfard,

Hosseini Beheshti

et al. 2024

View full text Add to dashboard Cite

show abstract

“…Combining the above features, Spearman's rank correlation coefficient can be well utilized to measure the semantic relevance of English translation in this paper, which can be used to measure the performance of each method by calculating the correlation value of manual annotation, and the rank coefficient of correlation value of each correlation calculation method. Then, comparing the method of this paper, the method of study [9], the method of study [10], the method of study [11] in the same context, the semantic similarity of the randomly selected keyword phrases of English translation in Table II, the results of the comparison of Spearman's rank correlation coefficients are as shown in Fig. 9 Comparing Fig.…”

Section: Candidate Keywordmentioning

confidence: 99%

“…At the same time, when the network ontology structure is large and complex, the computational efficiency may be affected, and it is difficult to apply to largescale data sets. The study in [10] uses RDF triples to evaluate semantic dependencies between entities. If the number of triples available in an RDF data set is limited, semantic correlation analysis based on these triples may suffer from data sparsity, resulting in inaccurate analysis results.…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning-based Method for Determining Semantic Similarity of English Translation Keywords

Zhili,

Qian

2024

ijacsa

View full text Add to dashboard Cite

In the English translation task, the semantics of context play an important role in correctly understanding the subtle differences between keywords. The bidirectional LSTM includes a positive LSTM and a reverse LSTM. When processing sequence data, you can consider the information of the preceding and following text at the same time. Therefore, to capture the subtle semantic differences between English translation keywords and accurately evaluate their similarity, a new semantic similarity determination method for English translation keywords is studied with the bidirectional LSTM neural network in deep learning as the main algorithm. This method introduces an English translation keyword extraction algorithm based on word cooccurrence and uses the co-occurrence relationship between words to identify and extract keywords in English translation. The extracted keywords are input into the bidirectional LSTM neural network keyword semantic similarity judgment model based on deep learning, and the weight of the bidirectional LSTM neural network is set by using the sparrow search algorithm to optimize. After the bidirectional LSTM neural network is trained, the information on keyword word vectors is captured, and the similarity between keyword word vectors is evaluated. The experimental results show that the sentence similarity calculated by the proposed method for English translation is very close to the result of professional manual scoring. The Spearman rank correlation coefficient of the semantic similarity determination result is 1, and the determination result is accurate.

show abstract

“…The origin of the knowledge atlas can be traced back to 1960, when Semantic Network [1] was proposed as a method of knowledge representation, and in 1980, Ontology [2] was proposed to describe the world composed of a set of object types, attributes and relation types. In 1989, Tim Berners-Lee invented the World Wide Web [3] in which people can link their own documents.…”

Section: Development Of Knowledge Graphmentioning

confidence: 99%

The core technique and application of knowledge graph in power grid company administrative duty

feng,

xu,

chen

et al. 2023

Eighth International Symposium on Advances in Electrical, Electronics, and Computer Engineering (ISAEECE 2023)

View full text Add to dashboard Cite

Power knowledge graph of the great application potentials for the power utilities , has become one of the interesting research topics in academia and industry . The power big data onto the deployment of information management system , poses a challenge to the current power grid company's administrative duty system , at the same time , the opportunity for / in applying intelligent management notion into the power grid company has come into being . Based on these above descriptions , the application and exploration of knowledge graph in power grid company administrative duty has been put forward in this paper . Firstly , the on-duty text data is pre-processed ; secondly , entity extraction and relationship extraction are carried out on the processed data ; finally , the data is stored in the graph database to build the knowledge graph.

show abstract

Mining information from sentences through Semantic Web data and Information Extraction tasks

Cited by 12 publications

References 27 publications

Semi-automated ontology development scheme via text mining of scientific records

Semi-automated ontology development scheme via text mining of scientific records

A Deep Learning-based Method for Determining Semantic Similarity of English Translation Keywords

The core technique and application of knowledge graph in power grid company administrative duty

Contact Info

Product

Resources

About