Now showing items 1-14 of 14

  • A latent variable ranking model for content-based retrieval 

    Quattoni, Ariadna Julieta; Carreras Pérez, Xavier; Torralba, Antonio (Springer, 2012)
    Conference report
    Restricted access - publisher's policy
    Since their introduction, ranking SVM models have become a powerful tool for training content-based retrieval systems. All we need for training a model are retrieval examples in the form of triplet constraints, i.e. examples ...
  • An empirical study of semi-supervised structured conditional models for dependency parsing 

    Suzuki, Jun; Isozaki, Hideki; Carreras Pérez, Xavier; Collins, Michael (2009)
    Conference report
    Open Access
    This paper describes an empirical study of high-performance dependency parsers based on a semi-supervised learning approach. We describe an extension of semisupervised structured conditional models (SS-SCMs) to the dependency ...
  • Exponentiated gradient algorithms for conditional random fields and max-margin Markov networks 

    Collins, Michael; Globerson, Amir; Koo, Terry; Carreras Pérez, Xavier; Bartlett, Peter (2008-08)
    Article
    Open Access
    Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of parameters in these models is therefore ...
  • Joint arc-factored parsing of syntactic and semantic dependencies 

    Lluis Martorell, Xavier; Carreras Pérez, Xavier; Màrquez Villodre, Lluís (2013-05)
    Article
    Restricted access - publisher's policy
    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 ...
  • Non-projective parsing for statistical machine translation 

    Carreras Pérez, Xavier; Collins, Michael (2009)
    Conference report
    Open Access
    We describe a novel approach for syntaxbased statistical MT, which builds on a variant of tree adjoining grammar (TAG). Inspired by work in discriminative dependency parsing, the key idea in our approach is to allow highly ...
  • Projective dependency parsing with perceptron 

    Carreras Pérez, Xavier; Surdeanu, Mihai; Màrquez Villodre, Lluís (2010)
    Conference report
    Open Access
    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 ...
  • Simple semi-supervised dependency parsing 

    Koo, Terry; Carreras Pérez, Xavier; Collins, Michael (2008)
    Conference report
    Open Access
    We present a simple and effective semisupervised method for training dependency parsers. We focus on the problem of lexical representation, introducing features that incorporate word clusters derived from a large unannotated ...
  • Spectral learning in non-deterministic dependency parsing 

    Luque, Franco M.; Quattoni, Ariadna Julieta; Balle Pigem, Borja de; Carreras Pérez, Xavier (2012)
    Conference report
    Restricted access - publisher's policy
    In this paper we study spectral learning methods for non-deterministic split head-automata grammars, a powerful hidden-state formalism for dependency parsing. We present a learning algorithm that, like other spectral ...
  • Spectral learning of weighted automata: a forward-backward perspective 

    Balle Pigem, Borja de; Carreras Pérez, Xavier; Luque, Franco M.; Quattoni, Ariadna Julieta (2013-10-07)
    Article
    Restricted access - publisher's policy
    In recent years we have seen the development of efficient provably correct algorithms for learning Weighted Finite Automata (WFA). Most of these algorithms avoid the known hardness results by defining parameters beyond the ...
  • Structured prediction models via the matrix-tree theorem 

    Koo, Terry; Globerson, Amir; Carreras Pérez, Xavier; Collins, Michael (2007)
    Conference report
    Open Access
    This paper provides an algorithmic framework for learning statistical models involving directed spanning trees, or equivalently non-projective dependency structures. We show how partition functions and marginals for directed ...
  • TAG, dynamic programming, and the perceptron for efficient, feature-rich parsing 

    Carreras Pérez, Xavier; Collins, Michael; Koo, Terry (Coling 2008 Organizing Committee, 2008)
    Conference report
    Open Access
    We describe a parsing approach that makes use of the perceptron algorithm, in conjunction with dynamic programming methods, to recover full constituent-based parse trees. The formalism allows a rich set of parse-tree ...
  • Unsupervised spectral learning of finite-state transducers 

    Bailly, Raphaël; Carreras Pérez, Xavier; Quattoni, Ariadna Julieta (2012)
    Conference report
    Open Access
    Finite-State Transducers (FST) are a standard tool for modeling paired inputoutput sequences and are used in numerous applications, ranging from computational biology to natural language processing. Recently Balle et al. ...
  • Unsupervised spectral learning of FSTs 

    Bailly, Raphaël; Carreras Pérez, Xavier; Quattoni, Ariadna Julieta (2013)
    Conference report
    Open Access
    Finite-State Transducers (FST) are a standard tool for modeling paired input output sequences and are used in numerous applications, ranging from computational biology to natural language processing. Recently Balle et al. ...
  • Unsupervised spectral learning of WCFG as low-rank matrix completion 

    Bailly, Raphaël; Carreras Pérez, Xavier; Luque, Franco M.; Quattoni, Ariadna Julieta (Association for Computational Linguistics, 2013)
    Conference lecture
    Open Access
    We derive a spectral method for unsupervised learning ofWeighted Context Free Grammars. We frame WCFG induction as finding a Hankel matrix that has low rank and is linearly constrained to represent a function computed by ...