A base de dados lexical e a interface web do TeP 2.0

Maziero, Erick Galani; Pardo, Thiago Alexandre Salgueiro; Felippo, Ariani Di; Dias-da-Silva, Bento Carlos

doi:10.1145/1809980.1810076

Cited by 43 publications

(10 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Linguistic resources and probabilistic techniques are used in the proposed approach to better represent the sentences and to pursue better opportunities for similarity identification. Regarding the linguistic aspects, the concepts of antonymy, hypernymy, hyponymy and synonymy were used through the TeP (Maziero et al, 2008) and PULO (Simões and Guinovart, 2014) resources, which are Brazilian Portuguese versions of WordNet. Considering the probabilistic scope, the concepts of VSM, TF-IDF and PCA were explored.…”

Section: Methodsmentioning

confidence: 99%

“…We integrate a set of linguistic resources and probabilistic techniques to better represent the phrases as means to maximize similarity classification assertiveness between sentence pairs. The linguistic relations antonymy, hyperonym, hyponymy and synonymy were explored under the aegis of the TeP synonymous database (Maziero et al, 2008) and the Portuguese Unified Lexical Ontology (PULO) (Simões and Guinovart, 2014). Resources achieved with the use of Vector Space Model, a metric of Term Frequency-Inverse Document Frequency (TF-IDF) and Principal Component Analysis (PCA) were applied in the method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Brazilian Portuguese Textual Entailment Recognition with a Hybrid Approach

Silva¹,

Rigo²

2018

Journal of Computer Science

View full text Add to dashboard Cite

Previous work on textual entailment has not fully exploited aspects of deep linguistic relations, which have been shown as containing important information for entailment identification. In this study, we present a new method to compute semantic textual similarity between two sentences. Our proposal relies on the integration of a set of deep linguistic relations, lexical aspects and distributed representational resources. We used our method with a large set of annotated data available from the ASSIN Workshop in the PROPOR 2016 event. The achieved results score among the best-known results in the literature. A perceived advantage of our approach is the ability to generate good results even with a small corpus on training tasks.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Enhancing Brazilian Portuguese Textual Entailment Recognition with a Hybrid Approach

Silva¹,

Rigo²

2018

Journal of Computer Science

View full text Add to dashboard Cite

show abstract

“…Dois deles possuem mestrado e o terceiro possui doutorado. Cada anotador filtrou, de uma lista de sinônimos previamente capturada do TeP (Thesaurus eletrônico para o Português do Brasil) (Maziero et al, 2008), quais palavras eram apropriadas para substituir a palavra complexa original. Eles também sugeriram substituições que não foram listadas.…”

Section: O Córpus Simplex-pb 30unclassified

Adaptação Lexical Automática em Textos Informativos do Português Brasileiro para o Ensino Fundamental

Hartmann

Aluísio²

2021

Linguamática

View full text Add to dashboard Cite

A Adaptação Textual é uma grande área de pesquisa do Processamento de Línguas Naturais (PLN), bastante conhecida como prática educacional, e possui duas grandes abordagens: a Simplificação e a Elaboração Textual. Não há muitos trabalhos na literatura de PLN que tratam todas as fases da Adaptação Lexical para implementação de sistemas. Vários trabalhos tratam independentemente as tarefas de Simplificação e Elaboração Lexicais, trazendo contribuições parciais, já que cada uma das tarefas possuem seus próprios desafios. Este trabalho propôs um pipeline para a Adaptação Lexical e apresenta contribuições para três das quatro etapas do pipeline, sendo elas: (i) proposta e avaliação de métodos para a tarefa de Identificação de Palavras Complexas; (ii) análise de córpus para levantamento de padrões de Elaboração Lexical do tipo definição; (iii) disponibilização do córpus SIMPLEX-PB 3.0, contendo em sua nova versão definições curtas extraídas de dicionário que foram revisadas manualmente, anotações de termos técnicos extraídas de dicionário, e métricas linguísticas de complexidade lexical; e (iv) proposta e avaliação de métodos para Simplificação Lexical, estabelecendo um novo SOTA para a tarefa aplicada no Português Brasileiro.

show abstract

“…There are different initiatives to create lexical ontologies, linked or not with the original Princeton WordNet [9] (WordNet.Pr). Examples of such initiatives are Onto.PT [4], PA-PEL [5], TeP [8] or Open WordNet-PT [10]. Along with these, another initiative born some months ago: the Portuguese Unified Lexical Ontology (PULO) [12].…”

Section: Introductionmentioning

confidence: 99%

“…In these and next examples, the authors decided not to translate the variant itself, as a direct translation will lose part of the cultural/usage meaning 8. Given the obtained accuracy and the lack of human resources for a through validation, the authors decided to include the obtained variants without further analysis.…”

mentioning

confidence: 99%

Experiments on Enlarging a Lexical Ontology

Simões

Almeida

2015

Communications in Computer and Information Science

View full text Add to dashboard Cite

This paper presents two simple experiments performed in order to enlarge the coverage of PULO, a Lexical Ontology, based and aligned with the Princeton WordNet. The first experiment explores the triangulation of the Galician, Catalan and Castillian wordnets, with translation dictionaries from the Apertium project. The second, explores Dicionário-Aberto entries, in order to extract synsets from its definitions. Although similar approaches were already applied for different languages, this document aims at documenting their results for the PULO case.

show abstract

A base de dados lexical e a interface web do TeP 2.0

Cited by 43 publications

References 2 publications

Enhancing Brazilian Portuguese Textual Entailment Recognition with a Hybrid Approach

Enhancing Brazilian Portuguese Textual Entailment Recognition with a Hybrid Approach

Adaptação Lexical Automática em Textos Informativos do Português Brasileiro para o Ensino Fundamental

Experiments on Enlarging a Lexical Ontology

Contact Info

Product

Resources

About