El grup de processament del llenguatge natural inicia la seva activitat al 1988. Des dels seus orígens ha sigut un grup interdisciplinari (informàtica i llingüistica). Ha portat a terme una prolífica activitat en diverses àrees d'investigació dins de processament del llenguatge natural i la intel•ligència artificial. En el processament bàsic de la llengua destaquen els camps de desambiguació morfosintàctica, anàlisis sintàctica i semàntica, desambiguació semàntica, etc., amb especial èmfasi en l'aplicació de mètodes estadístics i d'aprenentatge automàtic per resoldre aquestes tasques. Així mateix, apart de la tecnologia bàsica, també s'aborden aplicacions de més alt nivell, com ara traducció automàtica, extracció d'informació, donar resposta a preguntes, resum automàtic, processament de diccionaris, de corpus textuals, i de recursos lingüístics en general.

El grupo de procesamiento del lenguaje natural inicia su actividad en el 1988. Des de sus orígenes ha sido un grupo interdisciplinario (informática y lingüística). Ha llevado a cabo una prolífica actividad en diversas áreas de investigación dentro del procesamiento del lenguaje natural y la inteligencia artificial. En el procesamiento básico de la lengua destacan los campos de desambiguación morfosintáctica, análisis sintáctica y semántica, desambiguación semántica, etc., con especial énfasis en la aplicación de métodos estadísticos y de aprendizaje automático para resolver estas faenas. Así mismo, a parte de la tecnología básica, también se abordan aplicaciones de más alto nivel, como traducción automática, extracción de información, dar respuesta a preguntas, resumen automático, procesamiento de diccionarios, de corpus textuales, y de recursos lingüísticos en general.

The Natural Language Processing Group (GPLN) conducts research into the automatic processing of natural language, particularly those aspects related to the construction and exploitation of multilingual lexical resources and the extraction of information from documents written in natural language and summarisation. Within these research lines, the GPLN focuses its attention on developing language processing tools, such as morphological and syntactical analysers, grammatical labelers, corpus processing systems, and specific machine learning algorithms for natural language processing and on compiling linguistic resources, such as grammars, dictionaries and lexical and conceptual databases. The GPLN has also been working on natural language software specifications for the development of tools for the quality control of software. The GPLN collaborates with the Speech Processing Group in the research of oral translation and the development of dialogue systems.

The Natural Language Processing Group (GPLN) conducts research into the automatic processing of natural language, particularly those aspects related to the construction and exploitation of multilingual lexical resources and the extraction of information from documents written in natural language and summarisation. Within these research lines, the GPLN focuses its attention on developing language processing tools, such as morphological and syntactical analysers, grammatical labelers, corpus processing systems, and specific machine learning algorithms for natural language processing and on compiling linguistic resources, such as grammars, dictionaries and lexical and conceptual databases. The GPLN has also been working on natural language software specifications for the development of tools for the quality control of software. The GPLN collaborates with the Speech Processing Group in the research of oral translation and the development of dialogue systems.

Recent Submissions

  • eHealth Eurocampus: An innovative educational framework to train qualified professionals in the emerging ehealth sector 

    Gonzalez Cid, Yolanda; Guerrero Tomé, Carlos; Lobo, Joao; Tarbal Roquero, Arian; Picking, Richard; Castell Ariño, Núria; Abdelaziz, Salih; Voegel, Bernd; Tous, Xisco; Pattichis, Constantinos; Rigaud, Bernard (International Association of Technology, Education and Development (IATED), 2019)
    Conference lecture
    Open Access
    The aim of this paper is to present the results of an initiative called the eHealth Eurocampus (http://ehealtheurocampus.eu), whose main goal is to define a framework to prepare professionals for the eHealth work environment. ...
  • eHealth Eurocampus Project: preparing innovative ICT professionals 

    Castell Ariño, Núria; Lobo, Joao; Insa, Esther; Picking, Richard; Gonzalez Cid, Yolanda; Abdelaziz, Salih; Voegel, Bernd; Tous, Xisco; Pattichis, Constantinos; Rigaud, Bernard (International Association of Technology, Education and Development (IATED), 2019)
    Conference lecture
    Open Access
    The eHealth Eurocampus project, an EU-funded project, aims at preparing innovative professionals able to cope with the challenge of fostering a spirit of innovation in eHealth in Europe as the way forward to ensure better ...
  • Constant conditional entropy and related hypotheses 

    Ferrer Cancho, Ramon; Debowski, Lukasz; Moscoso del Prado Martín, Fermín (Institute of Physics (IOP), 2013-07-04)
    Article
    Open Access
    Constant entropy rate (conditional entropies must remain constant as the sequence length increases) and uniform information density (conditional probabilities must remain constant as the sequence length increases) are two ...
  • The law of brevity in macaque vocal communication is not an artifact of analysing mean call durations 

    Semple, Stuart; Hsu, Minna J.; Agoramoorthy, Govindasamy; Ferrer Cancho, Ramon (2013-07-04)
    Article
    Open Access
    Words follow the law of brevity, i.e. more frequent words tend to be shorter. From a statistical point of view, this qualitative definition of the law states that word length and word frequency are negatively correlated. ...
  • The span of correlations in dolphin whistle sequences 

    Ferrer Cancho, Ramon; McCowan, Brenda (Institute of Physics (IOP), 2012-06-11)
    Article
    Open Access
    Long-range correlations are found in symbolic sequences from human language, music and DNA. Determining the span of correlations in dolphin whistle sequences is crucial for shedding light on their communicative complexity. ...
  • Learning based on challenges in the context of multidisciplinary teamwork in ehealth: an evaluation of the students' experience 

    Graells, Ariadna; Castell Ariño, Núria; Insa, Esther (International Association of Technology, Education and Development (IATED), 2019)
    Conference report
    Open Access
    Education in eHealth is becoming of transcendental importance in the European social context. The progressive aging of the population has generated an increase in the prevalence of people with disabilities who demand more ...
  • Hubiness, length, crossings and their relationships in dependency trees 

    Ferrer Cancho, Ramon (RAM-Verlag, 2013-05-29)
    Article
    Open Access
    Here tree dependency structures are studied from three different perspectives: their degree variance (hubiness), the mean dependency length and the number of dependency crossings. Bounds that reveal pairwise dependencies ...
  • The challenges of statistical patterns of language: the case of Menzerath's law in genomes 

    Ferrer Cancho, Ramon; Forns Fradera, Núria; Hernández Fernández, Antonio; Bel Enguix, Gemma; Baixeries i Juvillà, Jaume (2013-01)
    Article
    Open Access
    The importance of statistical patterns of language has been debated over decades. Although Zipf's law is perhaps the most popular case, recently, Menzerath's law has begun to be involved. Menzerath's law manifests in ...
  • Information content versus word length in random typing 

    Ferrer Cancho, Ramon; Moscoso del Prado Martín, Fermín (Institute of Physics (IOP), 2011-12)
    Article
    Open Access
    Recently, it has been claimed that a linear relationship between a measure of information content and word length is expected from word length optimization and it has been shown that this linearity is supported by a strong ...
  • Random texts do not exhibit the real Zipf's law-like rank distribution 

    Ferrer Cancho, Ramon; Elvevag, Brita (Public Library of Science (PLOS), 2010-03-09)
    Article
    Open Access
    Background: Zipf's law states that the relationship between the frequency of a word in a text and its rank (the most frequent word has rank , the 2nd most frequent word has rank ,…) is approximately linear when plotted on ...
  • The small-world of human language 

    Ferrer Cancho, Ramon; Vicente Solé, Ricardo (The Royal Society, 2001-11-07)
    Article
    Open Access
    Words in human language interact in sentences in non–random ways, and allow humans to construct an astronomic variety of sentences from a limited number of discrete units. This construction process is extremely fast and ...
  • Control de calidad de las especificaciones de software escritas en lenguaje natural 

    Castell Ariño, Núria; Slavkova Hernández, Ólga; Tuells, Antoni; Toussaint, Yannick (Asociación de Técnicos de Informática, 1994-06)
    Article
    Open Access
    La complejidad creciente de los sistemas informáti­cos. ligada a una evolución muy rápida del hardware, ha originado en la Ingeniería del Software dos problemas importantes: la calidad del software desarrollado y la ...

View more