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

  • Male and female politicians on Twitter: A machine learning approach 

    Beltran Jorba, Javier; Gallego Dobón, Aina; Huidobro Torres, Alba; Romero Merino, Enrique; Padró, Lluís (2020-03-17)
    Article
    Restricted access - publisher's policy
    How does the language of male and female politicians differ when they communicate directly with the public on social media? Do citizens address them differently? We apply Lasso logistic regression models to identify the ...
  • Enhancing text spotting with a language model and visual context information 

    Sabir, Ahmed; Moreno-Noguer, Francesc; Padró, Lluís (IOS Press, 2018)
    Conference report
    Open Access
    This paper addresses the problem of detecting and recognizing text in images acquired ‘in the wild’. This is a severely under-constrained problem which needs to tackle a number of challenges including large occlusions, ...
  • Semantic relatedness based re-ranker for text spotting 

    Sabir, Ahmed; Moreno-Noguer, Francesc; Padró, Lluís (2019)
    Conference lecture
    Open Access
    Applications such as textual entailment, plagiarism detection or document clustering rely on the notion of semantic similarity, and are usually approached with dimension reduction techniques like LDA or with embedding-based ...
  • Red queen dynamics, competition and critical points in a model of RNA virus quasispecies 

    Vicente Solé, Ricardo; Ferrer Cancho, Ramon; González García, Isabel; Quer, Josep; Domingo Solans, Esteban (1999-05-07)
    Article
    Restricted access - publisher's policy
    RNA viruses offer a unique opportunity for the study of evolution at the molecular level. Recent experiments involving clonal populations of RNA viruses have shown that competition among virus strains of approximately equal ...
  • Multiple infection dynamics has pronounced effects on the fitness of RNA viruses 

    Miralles Borrego, Rosario; Ferrer Cancho, Ramon; Vicente Solé, Ricardo; Moya, Andres; Elena, Santiago (2001-07)
    Article
    Restricted access - publisher's policy
    Several factors play a role during the replication and transmission of RNA viruses. First, as a consequence of their enormous mutation rate, complex mixtures of genomes are generated immediately after infection of a new ...
  • Some word order biases from limited brain resources: A mathematical approach 

    Ferrer Cancho, Ramon (2008)
    Article
    Open Access
    In this paper, we propose a mathematical framework for studying word order optimization. The framework relies on the well-known positive correlation between cognitive cost and the Euclidean distance between the elements ...
  • Some limits of standard linguistic typology: the case of Cysouw's models for the frequencies of the six possible orderings of S, V and O 

    Ferrer Cancho, Ramon (2008)
    Article
    Open Access
    This article is a critical analysis of Michael Cysouw's comment "Linear order as a predictor of word order regularities".
  • The frequency spectrum of finite samples from the intermittent silence process 

    Ferrer Cancho, Ramon; Gavaldà Mestre, Ricard (2009-04)
    Article
    Open Access
    It has been argued that the actual distribution of word frequencies could be reproduced or explained by generating a random sequence of letters and spaces according to the so-called intermittent silence process. The same ...
  • Efficient coding in dolphin surface behavioral patterns 

    Ferrer Cancho, Ramon; Lusseau, David (2009-05)
    Article
    Open Access
    We show that the law of brevity, i.e. the tendency of words to shorten as their frequency increases, is also found in dolphin surface behavioral patterns. As far as we know, this is the first evidence of the law in another ...
  • The self-organization of genomes 

    Ferrer Cancho, Ramon; Forns Fradera, Núria (2010-05)
    Article
    Open Access
    Menzerath-Altmann law is a general law of human language stating, for instance, that the longer a word, the shorter its syllables. With the metaphor that genomes are words and chromosomes are syllables, we examine if genomes ...
  • Visual re-ranking with natural language understanding for text spotting 

    Sabir, Ahmed; Moreno-Noguer, Francesc; Padró, Lluís (2018)
    Conference lecture
    Open Access
    Many scene text recognition approaches are based on purely visual information and ignore the semantic relation between scene and text. In this paper, we tackle this problem from natural language processing perspective to ...
  • From process models to chatbots 

    López Cuenca, Francisco Anselmo; Sánchez Ferreres, Josep; Carmona Vargas, Josep; Padró, Lluís (Springer, 2019)
    Conference report
    Open Access
    The effect of digital transformation in organizations needs to go beyond automation, so that human capabilities are also augmented. A possibility in this direction is to make formal representations of processes more ...

View more