Ara es mostren els items 21-40 de 46

    • Joint arc-factored parsing of syntactic and semantic dependencies 

      Lluis Martorell, Xavier; Carreras Pérez, Xavier; Màrquez Villodre, Lluís (2013-05)
      Article
      Accés restringit per política de l'editorial
      In this paper we introduce a joint arc-factored model for syntactic and semantic dependency parsing. The semantic role labeler predicts the full syntactic paths that connect predicates with their arguments. This process ...
    • Lenguajes, gramáticas y autómatas : curso básico 

      Cases Muñoz, Rafel; Màrquez Villodre, Lluís (Edicions UPC, 2001)
      Llibre
      Accés restringit a la comunitat UPC
      El objeto de este libro es servir de soporte a un curso de introducción a la informática teórica, dirigido a estudiantes de primer ciclo de ingeniería. Aborda los temas de lenguajes regulares e incontextuales y expone sus ...
    • Linguistic measures for automatic machine translation evaluation 

      Giménez Linares, Jesús Ángel; Màrquez Villodre, Lluís (2010-12)
      Article
      Accés restringit per política de l'editorial
      Assessing the quality of candidate translations involves diverse linguistic facets. However, most automatic evaluation methods in use today rely on limited quality assumptions, such as lexical similarity. This introduces ...
    • Llenguatges, gramàtiques i autòmats : curs bàsic 

      Cases Muñoz, Rafel; Màrquez Villodre, Lluís (Edicions UPC, 2000)
      Llibre
      Accés restringit a la comunitat UPC
      L'objecte d'aquest llibre és servir de suport a un curs d'introducció a la informàtica teòrica, adreçat a estudiants de primer curs d'enginyeria. Cobreix els temes de llenguatges regulars i incontextuals. N'exposa els ...
    • Llenguatges, gramàtiques i autòmats : curs bàsic 

      Cases Muñoz, Rafel; Màrquez Villodre, Lluís (Edicions UPC, 2003)
      Llibre
      Accés restringit a la comunitat UPC
      L'objecte d'aquest llibre és servir de suport a un curs d'introducció a la informàtica teòrica, adreçat a estudiants de primer curs d'enginyeria. Cobreix els temes de llenguatges regulars i incontextuals. N'exposa els ...
    • Machine learning and natural language processing 

      Màrquez Villodre, Lluís (2000-07)
      Report de recerca
      Accés obert
      In this report, some collaborative work between the fields of Machine Learning (ML) and Natural Language Processing (NLP) is presented. The document is structured in two parts. The first part includes a superficial but ...
    • Margin maximization with feed-forward neural networks: a comparative study with support vector machines and AdaBoost 

      Romero Merino, Enrique; Màrquez Villodre, Lluís; Carreras Pérez, Xavier (2003-06)
      Report de recerca
      Accés obert
      Feed-forward Neural Networks (FNN) and Support Vector Machines (SVM) are two machine learning frameworks developed from very different starting points of view. In this work a new learning model for FNN is proposed such ...
    • Mètode de determinació d'àmbits de quantificació en un entorn de representació semàntica de frases en llenguatge natural 

      Màrquez Villodre, Lluís (1994)
      Report de recerca
      Accés obert
      El present treball descriu un sistema de reescriptura, basat en el proposat per Patrick Saint-Dizier l'any 1985, que permet reordenar el rang dels quantificadors introduïts pels determinants que apareixen en frases de ...
    • MT techniques in a retrieval system of semantically enriched patents 

      González Bermúdez, Meritxell; Mateva, Maria; Enache, Ramona; España Bonet, Cristina; Màrquez Villodre, Lluís; Popov, Borislav; Ranta, Aarne (2013)
      Comunicació de congrés
      Accés obert
      This paper focuses on how automatic translation techniques integrated in a patent retrieval system increase its capabilities and make possible extended features and functionalities. We describe 1) a novel methodology ...
    • Naive Bayes and exemplar-based approaches to word sense disambiguation revisited 

      Escudero Bakx, Gerard; Màrquez Villodre, Lluís; Rigau Claramunt, German (2000-02)
      Report de recerca
      Accés obert
      This paper describes an experimental comparison between two standard supervised learning methods, namely Naive Bayes and Exemplar--based classification, on the Word Sense Disambiguation (WSD) problem. The aim of the ...
    • On the portability and tuning of supervised word sense disambiguation systems 

      Escudero Bakx, Gerard; Màrquez Villodre, Lluís; Rigau Claramunt, German (2000-05)
      Report de recerca
      Accés obert
      This report describes a set of experiments carried out to explore the portability of alternative supervised Word Sense Disambiguation algorithms. The aim of the work is threefold: firstly, studying the performance of these ...
    • Patent translation within the MOLTO project 

      España Bonet, Cristina; Enache, Ramona; Slaski, Adam; Ranta, Aarne; Màrquez Villodre, Lluís; González Bermúdez, Meritxell (2011)
      Comunicació de congrés
      Accés obert
      MOLTO is an FP7 European project whose goal is to translate texts between multiple languages in real time with high quality. Patents translation is a case of study where research is focused on simultaneously obtaining a ...
    • Projective dependency parsing with perceptron 

      Carreras Pérez, Xavier; Surdeanu, Mihai; Màrquez Villodre, Lluís (2010)
      Text en actes de congrés
      Accés obert
      We describe an online learning dependency parser for the CoNLL-X Shared Task, based on the bottom-up projective algorithm of Eisner (2000). We experiment with a large feature set that models: the tokens involved in ...
    • Real-life translation quality estimation for MT system selection 

      Formiga Fanals, Lluís; Màrquez Villodre, Lluís; Pujantell Traserra, Jaume (2013)
      Comunicació de congrés
      Accés obert
      Research on translation quality annotation and estimation usually makes use of standard language, sometimes related to a specific language genre or domain. However, real-life machine translation (MT), performed for instance ...
    • Robust Estimation of Feature Weights in Statistical Machine Translation 

      España Bonet, Cristina; Màrquez Villodre, Lluís (2010)
      Comunicació de congrés
      Accés obert
      Weights of the various components in a standard Statistical Machine Translation model are usually estimated via Minimum Error Rate Training. With this, one finds their optimum value on a development set with the ...
    • SemEval-2010 Task 1: coreference resolution in multiple languages 

      Recasens Potau, Marta; Martí, Toni; Taulé, Mariona; Màrquez Villodre, Lluís; Sapena Masip, Emilio (2009)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      This paper presents the task "Coreference Resolution in Multiple Languages" to be run in SemEval-2010 (5th International Workshop on Semantic Evaluations). This task aims to evaluate and compare automatic coreference ...
    • Sibyl, a factoid question answering system for spoken documents 

      Comas Umbert, Pere Ramon; Turmo Borras, Jorge; Màrquez Villodre, Lluís (2012)
      Article
      Accés restringit per política de l'editorial
      In this article, we present a factoid question-answering system, Sibyl, specifically tailored for question answering (QA) on spoken-word documents. This work explores, for the first time, which techniques can be robustly ...
    • SVMTool: a general POS tagger generator based on support vector machines 

      Giménez Linares, Jesús Ángel; Màrquez Villodre, Lluís (2004-05-19)
      Report de recerca
      Accés obert
      This paper presents the SVMTool , a simple, flexible, effective and efficient part-of-speech tagger based on Support Vector Machines. The SVMTool offers a fairly good balance among these properties which make it really ...
    • The patents retrieval prototype in the MOLTO project 

      Chechev, Milen; González Bermúdez, Meritxell; Màrquez Villodre, Lluís; España Bonet, Cristina (ACM Press. Association for Computing Machinery, 2012)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      This paper describes the patents retrieval prototype developed within the MOLTO project. The prototype aims to provide a multilingual natural language interface for querying the content of patent documents. The developed ...
    • The TALP-UPC approach to system selection: ASIYA features and pairwise classification using random forests 

      Formiga Fanals, Lluís; González Bermúdez, Meritxell; Barrón-Cedeño, Alberto; Rodríguez Fonollosa, José Adrián; Màrquez Villodre, Lluís (2013)
      Text en actes de congrés
      Accés restringit per política de l'editorial
      This paper describes the TALP-UPC participation in the WMT’13 Shared Task on Quality Estimation (QE). Our participation is reduced to task 1.2 on System Selection. We used a broad set of features (86 for German-to-English ...