Pasar al contenido principal

DESARROLLO DE UN LABORATORIO VIRTUAL PARA EL PROCESAMIENTO COMPUTACIONAL DEL LENGUAJE NATURAL DESDE UN PARADIGMA FUNCIONAL

FFI2014-53788-C3-1-P

•
Nombre agencia financiadora Ministerio de Economía y Competitividad
Acrónimo agencia financiadora MINECO
Programa Programa Estatal de Fomento de la Investigación Científica y Técnica de Excelencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D (Excelencia / Generación de Conocimiento)
Año convocatoria 2014
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Secretaría de Estado de Educación, Formación Profesional y Universidades
Centro beneficiario UNIVERSIDAD NACIONAL DE EDUCACION A DISTANCIA
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 11
Encontrada(s) 1 página(s)

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)

Crimes against children: an apparently terminological knowledge representation of entities in FunGramKB

  • Alameda Hernández, Ángela
  • Felices Lago, Ángel
[EN] This article describes an example of the difficulties involved in the construction of a term-based satellite (or domain-specific) ontology integrated in FunGramKB –a lexico-conceptual knowledge base for the computational processing of natural language (Periñán-Pascual & Arcas-Túnez 2004, 2007, 2010a; Periñán-Pascual & Mairal-Usón 2009, 2010). The main hypothesis is that the multilevel model of FunGramKB Core Ontology can be connected to terminological satellite ontologies in order to minimize redundancy and maximize information (Periñán-Pascual & Arcas-Túnez 2010b). To this end we follow the four-phase COHERENT methodology (Periñán-Pascual & Mairal-Usón 2011): COnceptualization, HiErarchization, REmodelling and refinemeNT. In doing so, the paper furnishes substantial evidence on the structuring of a set of concepts borrowed from criminal law, an apparently terminological domain (cf. Breuker, Valente & Winkels 2005; Valente 2005; Breuker, Casanovas & Klein 2008). The Globalcrimeterm corpus has been used as an empirical foundation (Felices-Lago & Ureña-Gómez Moreno 2012, 2014). To illustrate this process, we have selected the superordinate basic concept +CRIME_00 (Alameda-Hernández & Felices-Lago 2016) and its basic and terminal subordinate concepts in the domains of organized crime and terrorism (all of them under the metaconcept #ENTITY), particularly those crimes referring predominantly to children or involving children with other vulnerable groups. The creation of specific definitions for the target concepts in this paper uses COREL (a conceptual representation language (Periñán-Pascual & Mairal-Usón 2010)) and the following upper-level conceptual path: #ENTITY> #PHYSICAL> #PROCESS> +OCCURRENCE_00> +CRIME_00. Consequently, the modelling, subsumption and hierarchisation of concepts such as $ABDUCTION_00, $CHILD_ABUSE_00, $CHILD_PORNOGRAPHY_00, $COERCE_D_00, $CHILD_TRAFFICKING_00, $MOLEST_D_00, $FORCED_LABOUR, among others, are presented., This article is based on research carried out within the framework of the Project FFI2014-53788-C3-1-P, which is funded by the Spanish Ministry of Economy and Competitiveness, and entitled: Development of a virtual laboratory for natural language processing from a functional paradigm. It is also based on the previous Project code no. FFI2010-15983: Development of a subontology in a multilingual context (English, Spanish and Italian): Using FunGramKB in the field of international cooperation in criminal matters: Terrorism and organised crime”.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Learning IS-A relations from specialized-domain texts with co-occurrence measures

  • Ureña Gómez-Moreno, Pedro
[EN] Ontology enrichment is a classification problem in which an algorithm categorizes an input conceptual unit in the corresponding node in a target ontology. Conceptual enrichment is of great importance both to Knowledge Engineering and Natural Language Processing, because it helps maximize the efficacy of intelligent systems, making them more adaptable to scenarios where information is produced by means of language. Following previous research on distributional semantics, this paper presents a case study of ontology enrichment using a feature-extraction method which relies on collocational information from corpora. The major advantage of this method is that it can help locate an input unit within its corresponding superordinate node in a taxonomy using a relatively small number of lexical features. In order to evaluate the proposed framework, this paper presents an experiment consisting of the automatic classification of a chemical substance in a taxonomy of toxicology., This article is based on research carried out within the framework of the Project FFI2014-53788-C3-1-P, which is funded by the Spanish Ministry of Economy and Competitiveness, and entitled: Development of a virtual laboratory for natural language processing from a functional paradigm.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Automatically Representing TExt Meaning via an Interlingua-based System (ARTEMIS). A further step towards the computational representation of RRG

  • Mairal-Usón, Ricardo
  • Cortés-Rodríguez, Francisco
[EN] Within the framework of FUNK Lab – a virtual laboratory for natural language processing inspired on a functionally-oriented linguistic theory like Role and Reference Grammar-, a number of computational resources have been built dealing with different aspects of language and with an application in different scientific domains, i.e. terminology, lexicography, sentiment analysis, document classification, text analysis, data mining etc. One of these resources is ARTEMIS (Automatically Representing TExt Meaning via an Interlingua-Based System), which departs from the pioneering work of Periñán-Pascual (2013) and Periñán-Pascual & Arcas (2014). This computational tool is a proof of concept prototype which allows the automatic generation of a conceptual logical structure (CLS) (cf. Mairal-Usón, Periñán-Pascual and Pérez 2012; Van Valin and Mairal-Usón 2014), that is, a fully specified semantic representation of an input text on the basis of a reduced sample of sentences. The primary aim of this paper is to develop the syntactic rules that form part of the computational grammar for the representation of simple clauses in English. More specifically, this work focuses on the format of those syntactic rules that account for the upper levels of the RRG Layered Structure of the Clause (LSC), that is, the core (and the level-1 construction associated with it), the clause and the sentence (Van Valin 2005). In essence, this analysis, together with that in Cortés-Rodríguez and Mairal-Usón (2016), offers an almost complete description of the computational grammar behind the LSC for simple clauses., Financial support for this research has been provided by the Spanish Ministry of Economy, Competitiveness and Science, grant FFI2014-53788-C3-1-P
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)

Bridging the gap within text-data analytics: A computer environment for data analysis in linguistic research

  • Periñán-Pascual, Carlos|||0000-0002-6483-4712
[EN] Since computer technology became widespread available at universities during the last quarter of the twentieth century, language researchers have been successfully employing software to analyse usage patterns in corpora. However, although there has been a proliferation of software for different disciplines within text-data analytics, e.g. corpus linguistics, statistics, natural language processing and text mining, this article demonstrates that any computer environment intended to support advanced linguistic research more effectively should be grounded on a user-centred approach to holistically integrate cross-disciplinary methods and techniques in a linguist-friendly manner. To this end, I examine not only the tasks that are derived from linguists' needs and goals but also the technologies that appropriately deal with the properties of linguistic data. This research results in the implementation of DAMIEN, an online workbench designed to conduct linguistic experiments on corpora., Financial support for this research has been provided by the DGI, Spanish Ministry of Education and Science, grant FFI2014-53788-C3-1-P.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

A framework of analysis for the evaluation of automatic term extractors

  • Periñán-Pascual, Carlos|||0000-0002-6483-4712
  • Mairal-Usón, Ricardo
[EN] Following previous research on automatic term extraction, the primary aim of this paper is to propose a more robust and consistent framework of analysis for the comparative evaluation of term extractors. Within the different views for software quality outlined in ISO standards, our proposal focuses on the criterion of external quality and in particular on the characteristics of functionality, usability and efficiency together with the subcharacteristics of suitability, precision, operability and time behavior. The evaluation phase is completed by comparing four online open-access automatic term extractors: TermoStat, GaleXtract, BioTex and DEXTER. This latter resource forms part of the virtual functional laboratory for natural language processing (FUNK Lab) developed by our research group. Furthermore, the results obtained from the comparative analysis are discussed., Financial support for this research has been provided by the Spanish Ministry of Economy, Competitiveness and Science, grant FFI2014-53788-C3-1-P.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

The interaction of parsing rules and argument-predicate constructions: implications for the structure of the grammaticon in FunGramKB

  • Fumero Pérez, María del Carmen
  • Díaz Galán, Ana
[EN] The Functional Grammar Knowledge Base (FunGramKB), (Periñán-Pascual and Arcas-Túnez 2010) is a multipurpose lexico-conceptual knowledge base designed to be used in different Natural Language Processing (NLP) tasks. It is complemented with the ARTEMIS (Automatically Representing Text Meaning via an Interlingua–based System) application, a parsing device linguistically grounded on Role and Reference Grammar (RRG) that transduces natural language fragments into their corresponding grammatical and semantic structures. This paper unveils the different phases involved in its parsing routine, paying special attention to the treatment of argumental constructions. As an illustrative case, we will follow all the steps necessary to effectively parse a For-Benefactive structure within ARTEMIS. This methodology will reveal the necessity to distinguish between Kernel constructs and L1-constructions, since the latter involve a modification of the lexical template of the verb. Our definition of L1-constructions leads to the reorganization of the catalogue of FunGramKB L1-constructions, formerly based on Levin’s (1993) alternations. Accordingly, a rearrangement of the internal configuration of the L1-Constructicon within the Grammaticon is proposed., Este trabajo ha sido desarrollado en el contexto del proyecto de investigación: “Desarrollo de un laboratorio virtual para el procesamiento computacional de la lengua desde un paradigma funcional”. (UNED) FF2014-53788-C3-1-P.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

The syntactic parsing of ASD-STE100 adverbials in ARTEMIS

  • Cortés-Rodríguez, Francisco J.
  • Rodríguez-Juárez, Carolina
[EN] This paper seeks to offer an update of the syntactic representation of adverbials in the Lexical Constructional Model and the multipurpose lexico-conceptual knowledge base, FunGramKB, and to implement the conditions that are necessary for an effective parsing of such constituents within ARTEMIS, a NLP prototype within FunGramKB for the computational treatment of the syntax and semantics of sentences. As regards the status of adverbials in the Layered Structure of the Clause (LSC) proposed in Role and Reference Grammar, it is striking that they have been somewhat sidelined, despite the programmatic proposal in Van Valin (2005) for a distribution of adjuncts along the different layers in the LSC. Since then, almost no further contribution has been offered to fully expand this new scheme. Thus, our aim is to fully embody a layered approach for adverbials and to adapt our proposal to the conditions imposed by the Grammar Development Environment in ARTEMIS, by developing the rules that are necessary for the parsing of the catalogue of adverbials of a corpus written in the controlled natural language ASD-STE100., This research has been financially supported by the DGI, Spanish Ministry of Education and Science, project No. FFI2014-53788-C3-1-P.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Detecting environmentally-related problems on Twitter

  • Periñán-Pascual, Carlos|||0000-0002-6483-4712
  • Arcas-Túnez, Francisco
[EN] Social media networks such as Facebook and Twitter can be used as a valuable tool to report on environmentally-related problems, e.g. landslides or wildfires, that are about to occur or have just occurred, so that response actions can be promptly executed. The goal of this article is to describe a knowledge-based system that is able to analyse tweets in Spanish to detect a variety of such problems. This research resulted in the implementation of CASPER, a proof-of-concept workbench where multi-domain problem detection has been devised as a two-fold task: topic categorisation and sentiment analysis. (C) 2018 IAgrE. Published by Elsevier Ltd. All rights reserved., Financial support for this research has been provided by the Spanish Ministry of Economy, Industry and Competitiveness [grant number TIN2016-78799-P] (AEI/FEDER, EU) and by the Spanish Ministry of Education and Science [grant number FFI2014-53788-C3-1-P]
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

DEXTER: A workbench for automatic term extraction with specialized corpora

  • Periñán-Pascual, Carlos|||0000-0002-6483-4712
[EN] Automatic term extraction has become a priority area of research within corpus processing. Despite the extensive literature in this field, there are still some outstanding issues that should be dealt with during the construction of term extractors, particularly those oriented to support research in terminology and terminography. In this regard, this article describes the design and development of DEXTER, an online workbench for the extraction of simple and complex terms from domain-specific corpora in English, French, Italian and Spanish. In this framework, three issues contribute to placing the most important terms in the foreground. First, unlike the elaborate morphosyntactic patterns proposed by most previous research, shallow lexical filters have been constructed to discard term candidates. Second, a large number of common stopwords are automatically detected by means of a method that relies on the IATE database together with the frequency distribution of the domain-specific corpus and a general corpus. Third, the term-ranking metric, which is grounded on the notions of salience, relevance and cohesion, is guided by the IATE database to display an adequate distribution of terms., Financial support for this research has been provided by the DGI, Spanish Ministry of Education and Science, grant FFI2014-53788-C3-1-P.