Pasar al contenido principal

DESARROLLO DE UN SISTEMA DE REPRESENTACION SEMANTICO-CONCEPTUAL Y SU IMPLEMENTACION EN UN ALGORITMO DE ENLACE BIDIRECCIONAL SINTAXIS-SEMANTICA

FFI2011-29798-C02-01

•
Nombre agencia financiadora Ministerio de Ciencia e Innovación
Acrónimo agencia financiadora MICINN
Programa Programa Nacional de Proyectos de Investigación Fundamental
Subprograma Subprograma de Proyectos de Investigación Fundamental no Orientada
Convocatoria Proyectos I+D
Año convocatoria 2011
Plan Estatal 2008-2011 Plan Nacional de Investigación Científica, Desarrollo e Innovación Tecnológica
Unidad de gestión Subdirección General de Proyectos de Investigación
Centro beneficiario UNIVERSIDAD NACIONAL DE EDUCACION A DISTANCIA
Identificador persistente http://dx.doi.org/10.13039/501100004837

Resultados relacionados

Resultados totales (Incluyendo duplicados): 10
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

En defensa del procesamiento del lenguaje natural fundamentado en la lingüística teórica, In defence of a linguistic-aware approach to natural language processing

  • Periñán-Pascual, Carlos|||0000-0002-6483-4712
[EN] Although natural language processing can be deemed as a discipline between applied linguistics and artificial intelligence, theoretical linguistics has played a remarkably minor role in this field of research. One of the goals of this paper is to portray the reasons of the failed symbiosis between linguists’ research and that of computer scientists, where probabilistic approaches haven been steadily overshadowing linguistic models. In spite of this discouraging scenario, FunGramKB, a knowledge base particularly designed for natural language understanding systems, serves to illustrate how a language-aware and cognitively-plausible approach to human-like processing can contribute to the development of enhanced knowledgeengineering projects., [ES] A pesar de que podríamos ubicar el procesamiento del lenguaje natural entre la lingüística aplicada y la inteligencia artificial, el papel que ha desempeñado la lingüística teórica a lo largo de la historia de esta disciplina ha sido generalmente poco notorio. uno de los objetivos de este artículo es desgranar las causas de esta malograda simbiosis entre las investigaciones de lingüistas e informáticos, donde los enfoques probabilísticos han ido gradualmente relegando los modelos lingüísticos a un segundo plano, en el mejor de los casos. A pesar de este desalentador panorama, FunGramKB, una base de conocimiento particularmente útil para sistemas que requieran la comprensión del lenguaje, sirve para ilustrar cómo actualmente la lingüística teórica y la ciencia cognitiva pueden contribuir al desarrollo de un proyecto de ingeniería del conocimiento., este trabajo forma parte de dos proyectos de investigación financiados por el ministerio de ciencia y Tecnología de españa, códigos FFi2011-29798-c02-01 y FFi2010-15983. También quiero expresar mi agradecimiento a Francisco cortés Rodríguez, carlos González Vergara y Ricardo mairal usón por sus comentarios sobre el primer borrador de este artículo.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

The underpinnings of a composite measure for automatic term extraction: The case of SRC

  • Periñán-Pascual, Carlos|||0000-0002-6483-4712
The corpus-based identification of those lexical units which serve to describe a given specialized domain usually becomes a complex task, where an analysis oriented to the frequency of words and the likelihood of lexical associations is often ineffective. The goal of this article is to demonstrate that a user-adjustable composite metric such as SRC can accommodate to the diversity of domain-specific glossaries to be constructed from small-and medium-sized specialized corpora of non-structured texts. Unlike for most of the research in automatic term extraction, where single metrics are usually combined indiscriminately to produce the best results, SRC is grounded on the theoretical principles of salience, relevance and cohesion, which have been rationally implemented in the three components of this metric., Financial support for this research has been provided by the DGI, Spanish Ministry of Education and Science, grants FFI2011-29798-C02-01 and FFI2014-53788-C3-1-P.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

DEXTER: Automatic Extraction of Domain-Specific Glossaries for Language Teaching

  • Periñán-Pascual, Carlos|||0000-0002-6483-4712
  • Mestre-Mestre, Eva M.|||0000-0001-5409-2025
[EN] Many researchers emphasize the importance of corpora in the design of Language-for-Specific-Purposes courses in higher education. However, identifying those lexical units which belong to a given specific domain is often a complex task for language teachers, where simple introspection or concordance analysis does not really become effective. The goal of this paper is to describe DEXTER, an open-access platform for data mining and terminology management, whose aim is not only the search, retrieval, exploration and analysis of texts in domain-specific corpora but also the automatic extraction of specialized words from the domain., Financial support for this research has been provided by the DGI, Spanish Ministry of Education and Science, grant FFI2011-29798-C02-01.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A knowledge-engineering approach to the cognitive categorization of lexical meaning

  • Periñán-Pascual, Carlos|||0000-0002-6483-4712
[EN] A key challenge in natural language processing is to develop intelligent agents which can retrieve and manage knowledge efficiently as well as simulate human-level reasoning. Undoubtedly, the knowledge base plays a crucial role in such a cognitive architecture. The problem lies in the fact that most approaches to the computational treatment of the meaning of words are restricted to systems of binary lexical relations. The goal of this article is to describe, from the view of linguistics and cognitive science, the theoretical foundation which underlies the construction of the deep semantic representations in FunGramKB, a multipurpose lexico-conceptual knowledge base to be implemented in natural language understanding systems. Thus, the conceptual schemata of thematic frames and meaning postulates may not only provide a full-fledged formalization of lexical semantics in natural language processing but can also facilitate the comprehension of linguistic realizations in artificial intelligence., [ES] Uno de los grandes retos del procesamiento del lenguaje natural es el desarrollo de agentes inteligentes que nos permitan no sólo recuperar información y gestionar el conocimiento de forma más eficaz sino también simular el razonamiento humano. En este escenario, la base de conocimiento desempeña un papel crucial dentro de la arquitectura cognitiva. El problema radica en que la mayoría de los enfoques para el tratamiento computacional del significado léxico se limitan a sistemas de relaciones léxicas binarias. El objetivo de este artículo es describir, desde el prisma de la lingüística y la ciencia cognitiva, la fundamentación teórica sobre la que se construyen las representaciones semánticas en FunGramKB, una base de conocimiento léxico-conceptual multipropósito para su implementación en sistemas que requieran la comprensión del lenguaje. De esta manera, los esquemas conceptuales de los marcos temáticos y los postulados de significado no sólo proporcionan una formalización detallada de la semántica léxica en el procesamiento del lenguaje natural sino además facilitan la comprensión de las realizaciones lingüísticas en la inteligencia artificial., Financial support for this research has been provided by the DGI, Spanish Ministry of Education and Science, grant FFI2011-29798-C02-01.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Multilingualism and conceptual modelling

  • Mairal-Usón, Ricardo
  • Periñán-Pascual, Carlos|||0000-0002-6483-4712
[EN] One of the leading motivations behind the multilingual semantic web is to make resources accessible digitally in an online global multilingual context. Consequently, it is fundamental for knowledge bases to find a way to manage multilingualism and thus be equipped with those procedures for its conceptual modelling. In this context, the goal of this paper is to discuss how common-sense knowledge and cultural knowledge are modelled in a multilingual framework. More particularly, multilingualism and conceptual modelling are dealt with from the perspective of FunGramKB, a lexico-conceptual knowledge base for natural language understanding. This project argues for a clear division between the lexical and the conceptual dimensions of knowledge. Moreover, the conceptual layer is organized into three modules, which result from a strong commitment towards capturing semantic knowledge (Ontology), procedural knowledge (Cognicon) and episodic knowledge (Onomasticon). Cultural mismatches are discussed and formally represented at the three conceptual levels of FunGramKB., We would like to thank Guadalupe Aguado-de-Cea, Christopher Butler, Lachlan Mackenzie, Elena Montiel-Ponsoda and Brian Nolan for detailed comments on the first draft of this paper. Any error is ours. Financial support for this research has been provided by the Spanish Ministry of Education and Science, grants FFI2011-29798-C02-01 and FFI2014-53788-C3-1-P.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Automatic domain-specific learning: towards a methodology for ontology enrichment

  • Ureña Gómez-Moreno, Pedro
  • Mestre-Mestre, Eva M.|||0000-0001-5409-2025
[EN] At the current rate of technological development, in a world where enormous amount of data are constantly created and in which the Internet is used as the primary means for information exchange, there exists a need for tools that help processing, analyzing and using that information. However, while the growth of information poses many opportunities for social and scientific advance, it has also highlighted the difficulties of extracting meaningful patterns from massive data. Ontologies have been claimed to play a major role in the processing of large-scale data, as they serve as universal models of knowledge representation, and are being studied as possible solutions to this. This paper presents a method for the automatic expansion of ontologies based on corpus and terminological data exploitation. The proposed ¿ontology enrichment method¿ (OEM) consists of a sequence of tasks aimed at classifying an input keyword automatically under its corresponding node within a target ontology. Results prove that the method can be successfully applied for the automatic classification of specialized units into a reference ontology., Financial support for this research has been provided by the DGI, Spanish Ministry of Education and Science, grant FFI2011-29798-C0201.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Resolución de anáforas que requieren conocimiento cultural con la herramienta Fungramkb

  • Carrión Varela, María de los Llanos
[EN] While integrating linguistic knowledge of any kind is becoming an almost implicit practice in natural language understanding systems, the inclusion of cultural or world knowledge in these tools might have been neglected sometimes. However, a NLP system or knowledge base enriched with cultural information is a more robust, better cohesioned instrument for natural language understanding processes. The integration of this type of knowledge in NLP systems may be proven to contribute to solving some phenomena that occur in natural language, such as anaphor, metaphor and metonymy, ambiguity or co-reference, amongst others. The objective of this article is to describe the way FunGramKB (a knowledge base) integrates cultural knowledge in its conceptual modules and, in particular, how the information contained in the Onomasticon module of FunGramKB can contribute to maximising the informativeness and completeness of the whole system, thus resolving ambiguity problems in a determined linguistic phenomenon: anaphora., [ES] La integración de diversos tipos de conocimiento lingüístico en sistemas de comprensión o procesamiento del lenguaje natural (PLN) constituye una práctica común. Sin embargo, en habitualmente se ha obviado la inclusión de conocimiento cultural, ya sea por motivos técnicos o teóricos. No obstante, un sistema del PLN enriquecido con información cultural constituye una herramienta más robusta y cohesionada, para llevar a cabo más óptimamente la resolución de problemas vinculados a la comprensión del lenguaje natural como, por ejemplo, la ambigüedad existente en fenómenos lingüísticos como la anáfora, referencia y correferencia o metáfora y metonimia, entre otros. El objetivo de este artículo es describir cómo la base de conocimiento FunGramKB integra el conocimiento cultural a través de sus módulos conceptuales y, en especial, cómo la información del módulo denominado Onomasticón puede contribuir a maximizar la informatividad del sistema completo, para resolver problemas de ambigüedad en un determinado fenómeno lingüístico: la anáfora., Este trabajo forma parte del proyecto de investigación FFI2011-29798-C02-01, financiado por el Ministerio de Ciencia e Innovación
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Low applicatives and optional &quot, se&quot, in spanish non-anticausative intransitive verbs

  • Teomiro García, Ismael Iván
[EN] This work revolves around a very peculiar set of Spanish verbs ("caer[se]", "morir[se]", "tropezar[se]", and "encallar[se]", among others), which optionally allow the clitic "se" without any significant change of meaning. These verbs do not enter the transitive-inchoative alternation (i.e. they are non-anticausative). Besides, the presence of the clitic has little semantic contribution, if any at all. They are problematic because they cannot be integrated in existing analyses that account for other instances of pronominal verbs like anticausatives and reflexives. What it is proposed in this work is that these verbs are optionally selected by a low applicative head. Moreover, the clitic "se" is thought of as a nominal item. This allows the integration of these verbs in broader analyses of pronominal verbs that consider the clitic a nominal item (whether argumental or expletive-like)., * This work has partially been funded by the Ministry of Economy and Competitiveness of Spain (Ministerio de Economía y Competitividad de España, grants FFI2011- 23829/FILO and FFI2011-29798-C02-01). We want to thank Ricardo Mairal Usón, María Beatriz Pérez Cabello de Alba, Linda Escobar, and Florian Schäffer for their useful comments
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Developing a knowledge base for preposition sense disambiguation: A view from Role and Reference Grammar and FunGramKB

  • Hernández-Pastor, Diana
  • Periñán-Pascual, Carlos|||0000-0002-6483-4712
Prepositions represent a grammatical category of frequent use in many European languages. The combination of their semantics with other lexical categories usually makes them difficult to be computationally tractable. As far as natural language processing is concerned, some studies have contributed to make progress on the usage of prepositions. However, there still exists a need to develop a model that allows tackling the problems which result from the disambiguation of prepositional semantics. The goal of this paper is to describe a lexico-conceptual model which can store the knowledge required to disambiguate predicate prepositions, as well as how this model can be exploited by a parser to extract the semantic representation of a text. The theoretical foundation of this approach, which is grounded on the premises of Role and Reference Grammar and FunGramKB, is illustrated with temporal adjuncts expressed by prepositional phrases in English., Financial support for this research has been provided by the DGI, Spanish Ministry of Education and Science, grant FFI2011-29798-C02-01. Moreover, much of this work has resulted from the first author's ongoing PhD thesis "La desambiguacion semantica de los sintagmas prepositivos como adjuntos perifericos en el marco de la Gramatica del Papel y la Referencia: un enfoque desde la linguistica computacional y la ingenieria del conocimiento", to be presented in Universidad Nacional de Educacion a Distancia (UNED).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

La ingeniería del conocimiento en el dominio legal: La construcción de una Ontología Satélite en FunGramKB, Knowledge engineering in the legal domain: The construction of a FunGramKB Satellite Ontolog y

  • Periñán-Pascual, Carlos|||0000-0002-6483-4712
  • Arcas Túnez, Francisco
[ES] Una de las tareas más tediosas en la labor diaria de los profesionales del derecho es la búsqueda de información en el ámbito jurídico. Con el fin de implementar aplicaciones avanzadas del procesamiento del lenguaje natural en este dominio, hemos desarrollado un modelo de representación del conocimiento especializado orientado a la semántica profunda dentro del marco de FunGramKB, una base de conocimiento léxicoconceptual multilingüe de propósito general. Más concretamente, el resultado de esta investigación ha dado como fruto una ontología terminológica sobre derecho penal en el dominio del terrorismo y el crimen organizado transnacional para ser utilizada en sistemas inteligentes que permitan la comprensión automática del discurso legal. El objetivo de este artículo es la descripción de la metodología empleada en el desarrollo de dicha ontología, centrándonos en la descripción de la herramienta que asiste al lingüista en el proceso de adquisición y conceptualización de los términos., [EN] One of the most time-consuming tasks in the daily work of legal professions is the search for information in the field of law. To implement advanced computer-based applications of natural language processing in this regard, we have developed a model of specialized knowledge representation driven by the deep semantics of FunGramKB, a multilingual general-purpose lexico-conceptual knowledge base. In particular, our research results in a terminological ontology on criminal law in the domain of transnational terrorism and organized crime to be implemented in intelligent systems which aim to understand legal discourse automatically. The objective of this paper is to describe the methodology used in the development of that ontology, focusing on the computerised tool to assist linguists in the process of terminological acquisition and conceptualization., Este trabajo forma parte de diversos proyectos de investigación financiados por el Ministerio de Ciencia y Tecnología, códigos FFI2011-29798-C02-01, FFI2010-17610 y FFI2010-15983.