Browsing by Subject "Natural language processing (Computer science)"

Now showing items 1-20 of 206

    • 2D to 3D body pose estimation for sign language with Deep Learning 

      Perez Granero, Pol (Universitat Politècnica de Catalunya, 2020-06)
      Bachelor thesis
      Open Access
      This project aims at leveraging the challenge of using 3D poses for Sign Language translation or animation by transforming 2D pose datasets into 3D ones. The goal is, using a 3D dataset of American Sign Language, to train ...

    • A comparison of approaches for measuring cross-lingual similarity of wikipedia articles 

      Barrón-Cedeño, Alberto; Lestari Paramita, Monica; Clough, Paul; Rosso, Paolo (Springer, 2014)
      Conference report
      Open Access
      Wikipedia has been used as a source of comparable texts for a range of tasks, such as Statistical Machine Translation and Cross-Language Information Retrieval. Articles written in different languages on the same topic are ...

    • A declarative control mechanism for parsing within a cooperative framework 

      Díaz de Ilarraza Sánchez, Arantza; Rodríguez Hontoria, Horacio; Verdejo Maillo, Maria Felisa (1990)
      External research report
      Open Access
      A control mechanism for dealing with NL processing is presented. The mechanism is implemented in a Natural Language Understanding System developed in the last years. In our approach, control is handled at two abstraction ...

    • A differentiable BLEU loss. Analysis and first results 

      Casas Manzanares, Noé; Rodríguez Fonollosa, José Adrián; Ruiz Costa-Jussà, Marta (2018)
      Conference report
      Open Access
      In natural language generation tasks, like neural machine translation and image captioning, there is usually a mismatch between the optimized loss and the de facto evaluation criterion, namely token-level maximum likelihood ...

    • A graph-based strategy to streamline translation quality assessments 

      Pighin, Daniele; Formiga Fanals, Lluís; Màrquez Villodre, Lluís (2012)
      Conference report
      Open Access
      We present a detailed analysis of a graph- based annotation strategy that we employed to annotate a corpus of 11,292 real-world En- glish to Spanish automatic translations with relative (ranking) and absolute ...

    • A pipeline for large raw text preprocessing and model training of language models at scale 

      Armengol Estapé, Jordi (Universitat Politècnica de Catalunya, 2021-01-25)
      Master thesis
      Open Access
      Covenantee:   Universitat de Barcelona / Universitat Rovira i Virgili
      The advent of Transformer-based (i.e., based on self-attention architectures) language models has revolutionized the entire field of Natural Language Processing (NLP). Once pre-trained on large, unlabelled corpora, we can ...

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

      Lluis Martorell, Xavier; Bott, Stefan Markus; Màrquez Villodre, Lluís (2009)
      Conference lecture
      Restricted access - publisher's policy
      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 ...

    • A Speech-based Dialogue System for Household Robots 

      Pons Rueda, Susana (Universitat Politècnica de Catalunya / Technische Universiteit Delft, 2011)
      Master thesis (pre-Bologna period)
      Restricted access - author's decision
      This thesis studies mechanisms to improve human-robot-interaction through a spoken dialogue for household robots. Therefore, a full dialogue system, in which the semantics of the words play an important role, is ...

    • A study on universal language-agnostic sentence embeddings and applications 

      Ribalta Albado, Maria (Universitat Politècnica de Catalunya, 2021-06-28)
      Bachelor thesis
      Open Access
      In this project we make a study on universal language agnostic sentence embeddings: internal neural networks sentence representations that are independent with relation to the task and the language. To be more precise, we ...

    • ADN-classifier: automatically assigning denotation types to nominalizations 

      Peris, Aina; Taulé, Mariona; Boleda Torrent, Gemma; Rodríguez Hontoria, Horacio (2010)
      Conference report
      Open Access
      This paper presents the ADN-Classifier, an Automatic classification system of Spanish Deverbal Nominalizations aimed at identifying its semantic denotation (i.e. event, result, underspecified, or lexicalized). The classifier ...

    • AI on software engineering processes 

      Miralles Pena, Carles (Universitat Politècnica de Catalunya, 2018-01)
      Master thesis
      Open Access
      Covenantee:   Universitat de Barcelona / Universitat Rovira i Virgili
      Due to the large quantity of available information as well as the huge computational power achieved today, the application of Artificial Intelligence (AI) in computer programs has become, now more than ever, much popular. ...

    • AI-Vocie: intel·ligència artificial aplicada al reconeixement de la veu 

      Gil Aguilar, Aleix (Universitat Politècnica de Catalunya, 2019-10)
      Bachelor thesis
      Open Access
      L’objectiu d’aquest treball de final de grau és dissenyar i implementar un Altaveu Intel·ligent, Lima, senzill, però pràctic, i que respongui a ordres, simulant la manera de pensar de l’ésser humà. La finalitat és que ...

    • Un algoritme per detectar la relació temporal de dues paraules. 

      Núñez Ruiz, Gerard (Universitat Politècnica de Catalunya, 2017-06-21)
      Bachelor thesis
      Open Access
      La informació sobre la relació temporal entre dues paraules és una informació que nosaltres deduïm del text però és un camp actualment en investigació al nivell d'intel·ligència artificial. Aquest projecte està basat en ...

    • Alias assignment in information extraction 

      Sapena Masip, Emilio; Padró, Lluís; Turmo Borras, Jorge (-, 2007-01-31)
      Conference report
      Restricted access - publisher's policy
      This paper presents a general method for alias assignment task in information extraction. We compared two approaches to face the problem and learn a classifier. The first one quantifies a global similarity between the alias ...

    • Aligning textual and graphical descriptions of processes through ILP techniques 

      Sànchez-Ferreres, Josep; Carmona Vargas, Josep; Padró, Lluís (Springer, 2017)
      Conference lecture
      Open Access
      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 ...

    • An adaptive gradient-search based algorithm for discriminative training of hmm's 

      Nogueiras Rodríguez, Albino; Mariño Acebal, José Bernardo; Monte Moreno, Enrique (Robert H. Mannel and Jordi Robert-Ribes, 1998)
      Conference lecture
      Restricted access - publisher's policy
      Although having revealed to be a very powerful tool in acoustic modelling, discriminative training presents a major drawback: the lack of a formulation guaranteeing convergence in no matter which initial conditions, such ...

    • An analysis of gender bias studies in natural language processing 

      Ruiz Costa-Jussà, Marta (Springer Science and Business Media LLC, 2019-10-14)
      Article
      Open Access
      Artificial intelligence systems copy and amplify existing societal biases, a problem that by now is widely acknowledged and studied. But is current research of gender bias in natural language processing actually moving ...

    • Analyzing Twitter data to discover gender biases in Spanish politics 

      Beltrán Jorba, Javier (Universitat Politècnica de Catalunya, 2018-06-27)
      Master thesis
      Open Access
      Covenantee:   Universitat de Barcelona. Facultat de Matemàtiques i Informàtica / Universitat Rovira i Virgili. Escola Tècnica Superior d'Enginyeria
      This work uses Twitter data from Spanish politicians to discover differences in how men and women speak in politics, as well as differences in how men and women politicians are addressed by others. A tool for automatic ...

    • Anàlisi del comerç en línia a partir de l'estudi del client i les seves valoracions 

      Villalobos Guiral, Albert (Universitat Politècnica de Catalunya, 2017-06)
      Bachelor thesis
      Restricted access - confidentiality agreement

    • Anàlisi i similitud d'articles acadèmics utilitzant tècniques de llenguatge natural i xarxes neuronals 

      Botet Colomer, Marc (Universitat Politècnica de Catalunya, 2019-01)
      Bachelor thesis
      Open Access
      This project has reviewed the state of the art in natural language processing in order to extract the similarity between academic papers. In addition, analysis tools have been added in order to study the evolution of the ...