Exploració per tema "Llenguatge natural (Informàtica) -- Processament"

Ara es mostren els items 1-20 de 25

    • A global relaxation labeling approach to coreference resolution 

      Sapena Masip, Emilio; Padró, Lluís; Turmo Borras, Jorge (2010)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      This paper presents a constraint-based graph partitioning approach to coreference resolution solved by relaxation labeling. The approach combines the strengths of groupwise classifiers and chain formation methods in ...

    • A second-order joint Eisner model for syntactic and semantic dependency parsing 

      Lluis Martorell, Xavier; Bott, Stefan Markus; Màrquez Villodre, Lluís (2009)
      Comunicació de congrés
      Accés restringit per política de l'editorial
      We present a system developed for the CoNLL-2009 Shared Task (Hajic et al., 2009). We extend the Carreras (2007) parser to jointly annotate syntactic and semantic dependencies. This state-of-the-art parser factorizes the ...

    • Aging in language dynamics 

      Mukherjee, Animesh; Tria, Francesca; Baronchelli, Andrea; Puglisic, Andrea; Loreto, Vittorio (2011-02-17)
      Article
      Accés obert
      Human languages evolve continuously, and a puzzling problem is how to reconcile the apparent robustness of most of the deep linguistic structures we use with the evidence that they undergo possibly slow, yet ceaseless, ...

    • Aprendizaje y asistencia virtual en red 

      Fuentes Fort, Maria; González Bermúdez, Meritxell; Guardiola Garcia, Marta; Jofre Roca, Lluís; Romeu Robert, Jordi; Vallverdú Bayés, Sisco (2011-01-20)
      Report de recerca
      Accés obert
      Favorecer el uso de las Tecnologías de Información y la Comunicación (TIC) en entornos educativos puede abarcar varios aspectos del proceso de aprendizaje. La incorporación de TICs en las aulas contribuye, por un lado a ...

    • Automatic acquisition of sense examples using Exretriever 

      Fernández, Juan; Castillo Valdés, Mauro; Rigau Claramunt, German; Atserias Batalla, Jordi; Tormo, Jordi (2004)
      Text en actes de congrés
      Accés obert
      A current research line for word sense disambiguation (WSD) focuses on the use of supervised machine learning techniques. One of the drawbacks of using such techniques is that previously sense annotated data is required. ...

    • CoCo, a web interface for corpora compilation 

      España Bonet, Cristina; Vila Rigat, Marta; Rodríguez Hontoria, Horacio; Martí, Maria Antònia (2009)
      Article
      Accés obert
      CoCo es una interfaz web colaborativa para la compilación de recursos lingüísticos. En esta demo se presenta una de sus posibles aplicaciones: la obtención de paráfrasis. / CoCo is a collaborative web interface for the ...

    • Comparing non-parametric ensemble methods for document clustering 

      González Pellicer, Edgar; Turmo Borras, Jorge (Springer Verlag, 2008)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      The biases of individual algorithms for non-parametric document clustering can lead to non-optimal solutions. Ensemble clustering methods may overcome this limitation, but have not been applied to document collections. ...

    • Deliverable 6.1 Infrastructure for Extractive Summarization 

      Saggion, Horacio; Padró, Lluís; Fuentes Fort, Maria (2013-12-30)
      Report de recerca
      Accés obert
      SKATER Internal Report: software of infrastructure for extractive Summarization (work carried out until December 2013)

    • English language learning activity using spoken language and intelligent computer-assisted technologies 

      Fuentes Fort, Maria; González Bermúdez, Meritxell (2011)
      Comunicació de congrés
      Accés obert
      This paper presents work in progress on language technologies applied to secondary school education. The application presented integrates several state-of-the-art technologies related to spoken language and intelligent ...

    • English-Latvian SMT: the challenge of translating into a free word order language 

      Khalilov, Maxim; Rodríguez Fonollosa, José Adrián; Skadina, Inguna; Bralitis, Edgar; Pretkalnina, Lauma (2010)
      Comunicació de congrés
      Accés obert
      This paper presents a comparative study of two approaches to statistical machine translation (SMT) and their application to a task of English-to-Latvian translation, which is still an open research line in the field of ...

    • Ethnic adjectives are proper adjectives 

      Arsenijevic, Boban; Boleda Torrent, Gemma; Gehrke, Berit; McNally, Louise (2010)
      Text en actes de congrés
      Accés obert
      In this paper, we challenge the view that ethnic adjectives (EAs) are nouns in disguise. Instead, we propose a unified semantics of the thematic and classificatory uses of EAs that treats them as proper adjectives, but ...

    • Evaluating large-scale knowledge resources across languages 

      Cuadros Oller, Montserrat; Rigau Claramunt, German; Castillo Valdés, Mauro (2007)
      Text en actes de congrés
      Accés obert
      This paper presents an empirical evaluation in a multilingual scenario of the semantic knowledge present on publicly available large-scale knowledge resources. The study covers a wide range of manually and automatically ...

    • FEMsum at DUC 2006: Semantic-based approach integrated in a Flexible Eclectic Multitask Summarizer Architecture 

      Fuentes Fort, Maria; Rodríguez Hontoria, Horacio; Turmo Borras, Jorge; Ferrés Domènech, Daniel (2006)
      Text en actes de congrés
      Accés obert
      In order to face different requirements at TALP Research Center we have built a highly parameterized environment allowing to instantiate specific summarizers for different summarization tasks in different languages. This ...

    • Hacia la interacción en lenguaje natural 

      Fuentes Fort, Maria; González Bermúdez, Meritxell (2011-02-06)
      Article
      Accés obert
      En éste documento se presenta la investigación que está siendo llevada a cabo en el Grupo de Procesamiento de Lenguaje Natural (GPLN) de la Universidad Politécnica de Cataluña (UPC). En concreto, hemos articulado la ...

    • KnowNet: A proposal for building highly connected and dense knowledge bases from the web 

      Cuadros Oller, Montserrat; Rigau Claramunt, German (2008)
      Text en actes de congrés
      Accés obert
      This paper presents a new fully automatic method for building highly dense and accurate knowledge bases from existing semantic resources. Basically, the method uses a wide-coverage and accurate nowledge-based Word Sense ...

    • KnowNet: building a large net of knowledge from the web 

      Cuadros Oller, Montserrat; Rigau Claramunt, German (2008)
      Text en actes de congrés
      Accés obert
      This paper presents a new fully automatic method for building highly dense and accurate knowledge bases from existing semantic resources. Basically, the method uses a wide-coverage and accurate knowledge-based Word Sense ...

    • Linking a domain thesaurus to WordNet and conversion to WordNet-LMF 

      Toral, Antonio; Monachini, Monica; Soria, Claudia; Cuadros Oller, Montserrat; Rigau Claramunt, German; Bosma, Wauter; Vossen, Piek (2010)
      Text en actes de congrés
      Accés obert
      We present a methodology to link domain thesauri to general-domain lexica. This is applied in the framework of the KYOTO project to link the Species2000 thesaurus to the synsets of the English WordNet. Moreover, we ...

    • N-gram-based statistical machine translation versus syntax augmented machine translation: comparison and system combination 

      Khalilov, Maxim; Rodríguez Fonollosa, José Adrián (2009-03-30)
      Comunicació de congrés
      Accés obert
      In this paper we compare and contrast two approaches to Machine Translation (MT): the CMU-UKA Syntax Augmented Machine Translation system (SAMT) and UPC-TALP N-gram-based Statistical Machine Translation (SMT). SAMT ...

    • RelaxCor : a global relaxation labeling approach to coreference resolution 

      Sapena Masip, Emilio; Padró, Lluís; Turmo Borras, Jorge (2010)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      This paper describes the participation of RelaxCor in the Semeval-2010 task number 1: "Coreference Resolution in Multiple Languages". RelaxCor is a constraint-based graph partitioning approach to coreference resolution ...

    • RelaxCor participation in CoNLL shared task on coreference resolution 

      Sapena Masip, Emilio; Padró, Lluís; Turmo Borras, Jorge (2011)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      This paper describes the participation of RelaxCor in the CoNLL-2011 shared task: "Modeling Unrestricted Coreference in Ontonotes". RELAXCOR is a constraint-based graph partitioning approach to coreference resolution solved ...