PAPEL: A Dictionary-Based Lexical Ontology for Portuguese

Oliveira, Hugo Gonçalo; Santos, Diana; Gomes, Paulo; Seco, Nuno

doi:10.1007/978-3-540-85980-2_4

Cited by 24 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…• Three wordnets: WordNet.Br [15], OpenWordNet-PT (OWN.PT) [16] and PULO [17]; • Two synset-based thesauri: TeP [18] and OpenThesaurus.PT (http://paginas.fe.up.pt/~arocha/ AED1/0607/trabalhos/thesaurus.txt (January 2018)) (OT.PT); • Three lexical-semantic networks extracted from Portuguese dictionaries: PAPEL [19], relations extracted from Dicionário Aberto (DA) [20], and relations extracted from Wiktionary.PT (http://pt.wiktionary.org (2015 dump)); • Semantic relations available in Port4Nooj [21], a set of linguistic resources.…”

Section: Open Portuguese Lkbsmentioning

confidence: 99%

“…For example, the instance {porta, portão} partOf {automóvel, carro, viatura} resulted in: (porta synonymOf portão), (automóvel synonymOf carro), (automóvel synonymOf viatura), (carro synonymOf viatura), (porta partOf automóvel), (porta partOf carro), (porta partOf viatura), (portão partOf automóvel), (portão partOf carro), (portão partOf viatura)-In English, {door, gate} partOf {automobile, car} resulted in: (door synonymOf gate), (automobile synonymOf car), (door partOf automobile), (door partOf car), (gate partOf automobile), (gate partOf car). Adopted relation names were those defined in the project PAPEL [19], a rich set that covered most relation types in all the LKBs. However, some relation names, in other LKBs, had to be converted to a common name, always considering their semantics.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Portuguese Lexical Knowledge Bases: Contents, Comparison and Combination

Oliveira

2018

Information

View full text Add to dashboard Cite

Abstract:In the last decade, several lexical-semantic knowledge bases (LKBs) were developed for Portuguese, by different teams and following different approaches. Most of them are open and freely available for the community. Those LKBs are briefly analysed here, with a focus on size, structure, and overlapping contents. However, we go further and exploit all of the analysed LKBs in the creation of new LKBs, based on the redundant contents. Both original and redundancy-based LKBs are then compared, indirectly, based on the performance of automatic procedures that exploit them for solving four different semantic analysis tasks. In addition to conclusions on the performance of the original LKBs, results show that, instead of selecting a single LKB to use, it is generally worth combining the contents of all the open Portuguese LKBs, towards better results.

show abstract

Section: Open Portuguese Lkbsmentioning

confidence: 99%

mentioning

confidence: 99%

A Survey on Portuguese Lexical Knowledge Bases: Contents, Comparison and Combination

Oliveira

2018

Information

View full text Add to dashboard Cite

show abstract

“…• PAPEL [32], extracted by exploiting the regularities in the definitions of a comercial Portuguese dictionary; The previous resources cover similar relation types, including synonymy, hypernymy, part-of, causation, purpose-of, property-of and location-of.…”

Section: Word-based Semantic Networkmentioning

confidence: 99%

Distributional and Knowledge-Based Approaches for Computing Portuguese Word Similarity

Oliveira

2018

Information

View full text Add to dashboard Cite

Abstract:Identifying similar and related words is not only key in natural language understanding but also a suitable task for assessing the quality of computational resources that organise words and meanings of a language, compiled by different means. This paper, which aims to be a reference for those interested in computing word similarity in Portuguese, presents several approaches for this task and is motivated by the recent availability of state-of-the-art distributional models of Portuguese words, which add to several lexical knowledge bases (LKBs) for this language, available for a longer time. The previous resources were exploited to answer word similarity tests, which also became recently available for Portuguese. We conclude that there are several valid approaches for this task, but not one that outperforms all the others in every single test. Distributional models seem to capture relatedness better, while LKBs are better suited for computing genuine similarity, but, in general, better results are obtained when knowledge from different sources is combined.

show abstract

“…Dentre elas há a criação da wordnet brasileira (WordNet.Br) (cujo método de criação foi apresentado anteriormente). Outros recursos na linha de wordnets são a MultiWordNet (Pianta et al, 2002), que possui uma versão para o português do Brasil, a WordNet.PT (Marrafa, 2002) (wordnet do português de Portugal) e o PAPEL (Gonçalo Oliveira et al, 2008;Santos et al, 2009) que apresenta as relações presentes em uma wordnet (sinonímia, antonímia, hiperonímia, hiponímia, dentre outras) para várias palavras do português de Portugal. Há também uma iniciativa para a construção de um PropBank para o Português do Brasil (PropBank.Br), no mesmo grupo de pesquisa do mestrado em tela, o NILC 9 , com sede no ICMC-USP 10 (Duran et al, 2010a;Duran et al, 2010b;Duran e Aluísio, 2011;Duran e Aluísio, 2012).…”

Section: Contextualização E Motivaçãounclassified

VerbNet.Br: construção semiautomática de um léxico verbal online e independente de domínio para o português do Brasil

Scarton¹

View full text Add to dashboard Cite

This article describes a semiautomatic method to build a computational verb lexicon for Brazilian Portuguese language (called VerbNet.Br). This lexical resource is based on the computational verb lexicon VerbNet for the English language, built according to Levin verb class theory. The method presented here is based on four steps: one manual and three automatic steps. Automatic steps use existing lexical resources and corpusbased knowledge. Also, this article presents the details of the implementation of one of the steps that uses existing lexical resources. The results of this step are the potential candidates of VerbNet.Br classes, yet without the validation.Resumo. Neste artigo é apresentado o método de criação semiautomática de um recurso léxico computacional de verbos para o português do Brasil, chamado VerbNet.Br, baseado na VerbNet, recurso léxico verbal para a língua inglesa, que segue a teoria das classes de Levin. O método de criação possui quatro etapas: uma manual e três automáticas. Nas etapas automáticas, recursos léxicos já existentes e conhecimento extraído de córpus são usados como informações de entrada. Também são apresentados neste artigo os detalhes de implementação da etapa automática que utiliza recursos léxicos já existentes. Os resultados obtidos, nesta etapa, são os candidatos a verbos membros das classes da VerbNet.Br, ainda sem validação. Tabela 3. Exemplos de candidatos a membros da VerbNet.Br para 5 classes Classe Membros em inglês Candidatos a membros em português Accompany-51.

show abstract

PAPEL: A Dictionary-Based Lexical Ontology for Portuguese

Cited by 24 publications

References 16 publications

A Survey on Portuguese Lexical Knowledge Bases: Contents, Comparison and Combination

A Survey on Portuguese Lexical Knowledge Bases: Contents, Comparison and Combination

Distributional and Knowledge-Based Approaches for Computing Portuguese Word Similarity

VerbNet.Br: construção semiautomática de um léxico verbal online e independente de domínio para o português do Brasil

Contact Info

Product

Resources

About