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.

http://futur.upc.edu/GPLN

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.

http://futur.upc.edu/GPLN

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.

http://futur.upc.edu/GPLN

Enviaments recents

  • Personalized questions, answers and grammars: aiding the search for relevant web information 

    Gatius Vila, Marta (Association for Computational Linguistics, 2017)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    This work is about guiding the user web search by generating most relevant questions, answers and grammars from web documents. The proposed approach is based on the representation of the main domain concepts as a set of ...
  • Técnicas de búsqueda 

    Rodríguez Hontoria, Horacio (Asociación de Técnicos de Informática, 1977-09)
    Article
    Accés obert
  • Lenguajes de representación del conocimiento basados en frames: estudio comparativo 

    Abad Soriano, María Teresa; Armengol Voltas, Eva; Blanco, Miguel Ángel; Castell Ariño, Núria; Delgado, Lourdes; Garijo, Francisco J.; González, Juan; Martí Antonin, Maria Antònia; Ribas Framis, Francesc; Rodríguez Hontoria, Horacio; Urretavizcaya, Maite; Verdejo Maillo, Maria Felisa; Vila Grabulosa, Lluís (1987)
    Report de recerca
    Accés obert
    Este documento es el resultado del seminario de trabajo del grupo G.U.I.A. sobre herramientas de representación del conocimiento llevado a cabo desde Octubre del 86 a Junio del 87. El objetivo principal es establecer una ...
  • Biomedical abbreviation recognition and resolution by PROSA-MED 

    Montalvo, Soto; Oronoz, Maite; Rodríguez Hontoria, Horacio; Martínez, Raquel (CEUR-WS.org, 2017)
    Text en actes de congrés
    Accés obert
    The amount of abbreviations used in biomedical literature increases constantly. Despite the existence of acronym dictionaries, it is not viable to keep them updated with new creations. Thus, in the processing of biomedical ...
  • Mapa de la competencia Sostenibilidad del proyecto EDINSOST 

    Sánchez Carracedo, Fermín; Segalàs Coral, Jorge; Vidal López, Eva María; Martín Escofet, Carme; López Álvarez, David; Climent Vilaró, Joan; Cabré Garcia, José M. (Asociación de Enseñantes Universitarios de la Informática (AENUI), 2017)
    Text en actes de congrés
    Accés obert
    EDINSOST es un proyecto financiado por el Programa Estatal de I+D+i, y está orientado a afrontar los Retos de la Sociedad. El proyecto tiene por objetivo la formación de titulados capaces de liderar la resolución de los ...
  • Aligning textual and graphical descriptions of processes through ILP techniques 

    Sànchez-Ferreres, Josep; Carmona Vargas, Josep; Padró, Lluís (Springer, 2017)
    Comunicació de congrés
    Accés obert
    With the aim of having individuals from different backgrounds and expertise levels examine the operations in an organization, different representations of business processes are maintained. To have these different ...
  • Arabic medical entity tagging using distant learning in a multilingual framework 

    Cotik, Viviana; Rodríguez Hontoria, Horacio; Vivaldi, Jorge (Elsevier, 2017-04-30)
    Article
    Accés obert
    A semantic tagger aiming to detect relevant entities in Arabic medical documents and tagging them with their appropriate semantic class is presented. The system takes profit of a Multilingual Framework covering four languages ...
  • E-assessment of relational database skills by means of LearnSQL 

    Quer Bosor, Maria Carme; Abelló Gamazo, Alberto; Burgués Illa, Xavier; Casany Guerrero, María José; Martín Escofet, Carme; Rodríguez González, M. Elena; Romero Moral, Óscar; Urpí Tubella, Antoni (International Association of Technology, Education and Development (IATED), 2017)
    Text en actes de congrés
    Accés obert
    LearnSQL is a software system that allows the automatic and efficient e-learning and e-assessment of relational database skills. It has been used at the Barcelona School of Informatics for 18 semesters with an average of ...
  • Semantic tagging of French medical entities using distant learning 

    Cotik, Viviana; Rodríguez Hontoria, Horacio; Vivaldi, Jorge (CEUR-WS.org, 2015)
    Comunicació de congrés
    Accés obert
    In this paper we present a semantic tagger aiming to detect relevant entities in French medical documents and tagging them with their appropriate semantic class. These experiments has been carried out in the framework ...
  • Semantic tagging and normalization of French medical entities 

    Cotik, Viviana; Rodríguez Hontoria, Horacio; Vivaldi, Jorge (CEUR-WS.org, 2016)
    Text en actes de congrés
    Accés obert
    In this paper we present two tools for facing task 2 in CLEF eHealth 2016. The first one is a semantic tagger aiming to detect relevant entities in French medical documents, tagging them with their appropriate ...
  • Generating domain-restricted resources for web interaction in several languages: hindi, english and spanish 

    Gatius Vila, Marta; Paliwal, Piyush (2013)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    The aim of our research is to develop domain-restricted resources for web interaction supporting different languages: English, Hindi and Spanish. Many practical natural language systems use linguistic resources adapted to ...
  • Morphological Analysis of the Dravidian Language Family 

    Kumar, Arun; Cotterell, Ryan; Oliver González, Antoni; Padró, Lluís (2017)
    Comunicació de congrés
    Accés obert
    The Dravidian family is one of the most widely spoken set of languages in the world, yet there are very few annotated resources available to NLP researchers. To remedy this, we create DravMorph, a corpus annotated for ...

Mostra'n més