Using a Lexical Dictionary and a Folksonomy to Automatically Construct Domain Ontologies

Macias-Galindo, Daniel; Wong, Wilson; Cavedon, Lawrence; Thangarajah, John

doi:10.1007/978-3-642-25832-9_65

Cited by 4 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To build the set of concept pairs, we sourced concepts from these nine ontologies, ensuring that selected concepts had high relatedness to their respective domains, according to the human judges from the evaluation presented in Macias‐Galindo et al. ().…”

Section: Methodsmentioning

confidence: 99%

“…For our evaluation, we constructed nine ontologies representing the following domains: Beach, Cars, Economy, Food, Museum, Music, School, Sports, and Zoo (some of these were chosen to support the domains of interaction for our conversational agent, with others selected by the authors to broaden the set of domains). To build the set of concept pairs, we sourced concepts from these nine ontologies, ensuring that selected concepts had high relatedness to their respective domains, according to the human judges from the evaluation presented in Macias-Galindo et al (2011).…”

Section: Constructing Domain Ontologiesmentioning

confidence: 99%

See 1 more Smart Citation

Effects of domain on measures of semantic relatedness

Macias-Galindo

Cavedon

Thangarajah

et al. 2015

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

Measures of semantic relatedness have been used in a variety of applications in information retrieval and language technology, such as measuring document similarity and cohesion of text. Definitions of such measures have ranged from using distance‐based calculations over WordNet or other taxonomies to statistical distributional metrics over document collections such as Wikipedia or the Web. Existing measures do not explicitly consider the domain associations of terms when calculating relatedness: This article demonstrates that domain matters. We construct a data set of pairs of terms with associated domain information and extract pairs that are scored nearly identical by a sample of existing semantic‐relatedness measures. We show that human judgments reliably score those pairs containing terms from the same domain as significantly more related than cross‐domain pairs, even though the semantic‐relatedness measures assign the pairs similar scores. We provide further evidence for this result using a machine learning setting by demonstrating that domain is an informative feature when learning a metric. We conclude that existing relatedness measures do not account for domain in the same way or to the same extent as do human judges.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Constructing Domain Ontologiesmentioning

confidence: 99%

Effects of domain on measures of semantic relatedness

Macias-Galindo

Cavedon

Thangarajah

et al. 2015

Asso for Info Science & Tech

Self Cite

View full text Add to dashboard Cite

show abstract

“…A ontologia apoia o processo de raciocínio na resolução da questão, uma vez que a ontologia suporta o processo de inferência. Os trabalhos explicitados por [Ong and Soriano 2014] e [Macías-Galindo et al 2011] reforçam a importância da ontologia na construção da base de conhecimento para que seja possível gerar um diálogo.…”

Section: Qp1: Quais Requisitos Funcionais São Identificados Em Chatbounclassified

“…O VOX System identificou dificuldades de compreensão de significados da Wikipédia, pois apesar dos dados serem bastante estruturados, seu significado não é claro para o computador porquê não é representado em uma má-quina processável (formalmente). Por último, a pesquisa de [Macías-Galindo et al 2011] apresentou dificuldades para extrair dados de um domínio para gerar a base de conhecimento.…”

Section: Qp1: Quais Requisitos Funcionais São Identificados Em Chatbounclassified

Uso de Ontologias para Agentes Conversacionais no Contexto de Ensino-Aprendizagem: Uma Revisão Sistemática da Literatura

Júnior¹,

Francisco²,

Silva³

et al. 2017

Anais Do XXVIII Simpósio Brasileiro De Informática Na Educação (SBIE 2017)

View full text Add to dashboard Cite

Abstract. This paper presents a Systematic Review of Literature (RSL) in order to verify the contribution of Ontologies to Conversational Agents (CA) in the teaching-learning context. The results indicate that the use of Ontologies in CAs is promising, since they allow actions in different domains, with different methods of interaction, inclusion of aspects of affectivity, and the need to meet non functional requirements such as usability and performance. Despite the benefits found, it is known that the creation of ontologies is costly. However, it is necessary to continue the research in a practical and experimental approach to seek the limits of the performance of such systems in real situations.Resumo. Este artigo apresenta uma Revisão Sistemática da Literatura (RSL) com o objetivo de verificar a contribuição das Ontologias para os Agentes Conversacionais (AC) no contexto de ensino-aprendizagem. Os resultados apontam que o uso das Ontologias nos ACs é promissor, pois possibilitam atuações em diferentes domínios, com diferentes métodos de interação, inclusão de aspectos de afetividade, e a necessidade de atender a requisitos não funcionais como usabilidade e performance. Apesar dos benefícios encontrados, sabe-se que é oneroso a criação das ontologias. Entretanto, destaca-se a necessidade da continuidade da pesquisa em uma abordagem prática e experimental visando buscar os limites da atuação de tais sistemas em situações reais.

show abstract

“…Chen et al (2010) show that by using folksonomy tags for creating an ontology based on basic-level concepts the resulting ontology agrees more closely with human thinking than an ontology that was automatically generated from text. Macías-Galindo et al (2011) also use tags from folksonomies to construct a categorization. They conclude that the quality of such a categorization can be enhanced by using a backbone: a set of root domain concepts provided by domain experts instead of using just one root concept.…”

Section: Basic-level Ontologymentioning

confidence: 99%

Engineering ontologies for question answering

et al. 2014

View full text Add to dashboard Cite

Using an ontology to automatically generate questions for ordinary people requires a structure and concepts compliant with human thought. Here we present methods to develop a pragmatic, expert-based and a basic-level ontology and a framework to evaluate these ontologies. Comparing these ontologies shows that expert-based ontologies are most easy to construct but lack required cognitive semantic characteristics. Basic-level ontologies have structure and concepts which are better in terms of cognitive semantics but are most expensive to construct.

show abstract

Using a Lexical Dictionary and a Folksonomy to Automatically Construct Domain Ontologies

Cited by 4 publications

References 15 publications

Effects of domain on measures of semantic relatedness

Effects of domain on measures of semantic relatedness

Uso de Ontologias para Agentes Conversacionais no Contexto de Ensino-Aprendizagem: Uma Revisão Sistemática da Literatura

Engineering ontologies for question answering

Contact Info

Product

Resources

About