Ontology lexicalization: Relationship between content and meaning in the context of Information Retrieval

Abstract

The proposal presented in this study seeks to properly represent natural language to ontologies and vice-versa. Therefore, the semi-automatic creation of a lexical database in Brazilian Portuguese containing morphological, syntactic, and semantic information that can be read by machines was proposed, allowing the link between structured and unstructured data and its integration into an information retrieval model to improve precision. The results obtained demonstrated that the methodology can be used in the risco financeiro (financial risk) domain in Portuguese for the construction of an ontology and the lexical-semantic database and the proposal of a semantic information retrieval model. In order to evaluate the performance of the proposed model, documents containing the main definitions of the financial risk domain were selected and indexed with and without semantic annotation. To enable the comparison between the approaches, two databases were created based on the texts with the semantic annotations to represent the semantic search. The first one represents the traditional search and the second contained the index built based on the texts with the semantic annotations to represent the semantic search. The evaluation of the proposal was based on recall and precision. The queries submitted to the model showed that the semantic search outperforms the traditional search and validates the methodology used. Although more complex, the procedure proposed can be used in all kinds of domains. Keywords: Information Science. Ontology. Information retrieval. Representation of information. Semantic Web. Resumo Esta proposta visa representar a linguagem natural na forma adequada às ontologias e vice-versa. Para tanto, propõe-se à criação semiautomática de base de léxicos em português brasileiro, contendo informações morfológicas, sintáticas e semânticas apropriadas para a leitura por máquinas, permitindo vincular dados estruturados e não estruturados, bem como integrar a leitura em modelo de recuperação da informação para aumentar a precisão. Os resultados alcançados demonstram a utilização da metodologia, no domí-

Sentence-Level Aspect-Based Sentiment Analysis for Classifying Adverse Drug Reactions (ADRs) Using Hybrid Ontology-XLNet Transfer Learning

“…Also, the lexicalized domain ontology reasoner is applied to extend the classical ontology and remove the vague ontology. The proposed approach uses ontology for two main purposes: 1) ontology contains a set of drug-related entities and their relationships that are utilized to extract entities from social data, and 2) lexicalized ontology infers indirect relationships between entities and their properties and determines the polarity of drug features of an aspect in conjunction with direct relationships in reviews, posts, or tweets [37], [38]. After building the ontology, the proposed approach uses XLNet word embeddings model to determine the embeddings sentence, which is concatenated with each embeddings word to produce a more comprehensive context and enhance feature extraction performance.…”

“…Also, the proposed approach utilized lexical ontology by mapping opinion data in SentiWordNet (SWN) to user reviews in order to identify sentiment directions. Furthermore, the procedure of lexicalized ontology extracts the ontology labels (concepts and relations) based on POS tag extraction, followed by a search in ontology to find occurrences in the corpus and eliminate the irrelevant aspects [38]. The recognized semantic similarity determines searching in SWN and calculates the features aspect polarity and the corresponding sentiment values.…”

Literature Survey: Analysis on Semantic Web Information Retrieval Methodologies

“…The system uses the typed query by using ontology so that the search can be focused. [12][23] [29] [30] Semantic search engines can mix more than one approach to fulfill different functions. There is room for a variety of search engine which means it does not fit into any type.…”

“…This model was designed to develop a standard RDF format of linguistic information, [30] which includes declarative specifications of a machine readable lexicon that captures morphological, syntactic, and semantic aspects of the lexical items related to ontology. This model consists of following modules:…”

Enhanced Neuro-Fuzzy-Based Crop Ontology for Effective Information Retrieval

“…The ontology usage to mitigate the precincts of keyword-related search has been heralded as one of the stimuli of the Semantic Web from its occurrence in the late 1990s. Web ontology language (OWL) was premeditated for highly intricate class structures and properties [11]. Enormous assistances occurred in the preceding years; however, most accomplishments were either fractional usage of the complete expressive power in ontology-related knowledge representation or Boolean retrieval-based models, thereby lacking an apt ranking model for measuring massive information sources [12].…”