Exploració per autor "Carreras Pérez, Xavier"
Ara es mostren els items 1-20 de 22
-
A latent variable ranking model for content-based retrieval
(Springer, 2012)
Text en actes de congrés
Accés restringit per política de l'editorialSince 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 ... -
A Proposal for wide-coverage Spanish named entity recognition
(2002-04)
Report de recerca
Accés obertThis paper presents a proposal for wide--coverage Named Entity Recognition for Spanish. First, a linguistic description of the typology of Named Entities is proposed. Following this definition an architecture of sequential ... -
A shortest-path method for arc-factored semantic role labeling
(2014)
Comunicació de congrés
Accés restringit per política de l'editorialWe introduce a Semantic Role Labeling (SRL) parser that finds semantic roles for a predicate together with the syntactic paths linking predicates and arguments. Our main contribution is to formulate SRL in terms of ... -
An empirical study of semi-supervised structured conditional models for dependency parsing
(2009)
Text en actes de congrés
Accés obertThis 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 ... -
Boosting trees for anti-spam email filtering (Extended version)
(2001-10)
Report de recerca
Accés obertIn this work, a set of comparative experiments for the problem of automatically filtering unwanted electronic mail messages are performed on two public corpora: PU1 and LingSpam. Several variants of the AdaBoost algorithm ... -
Exploiting diversity of margin-based classifiers
(2003-12)
Report de recerca
Accés obertAn experimental comparison among Support Vector Machines, AdaBoost and a recently proposed model for maximizing the margin with Feed-forward Neural Networks has been made on a real-world classification problem, namely ... -
Exponentiated gradient algorithms for conditional random fields and max-margin Markov networks
(2008-08)
Article
Accés obertLog-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
(2013-05)
Article
Accés restringit per política de l'editorialIn 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 ... -
Learning task-specific bilexical embeddings
(2014)
Text en actes de congrés
Accés obertWe present a method that learns bilexical operators over distributional representations of words and leverages supervised data for a linguistic relation. The learning algorithm exploits lowrank bilinear forms and induces ... -
Margin maximization with feed-forward neural networks: a comparative study with support vector machines and AdaBoost
(2003-06)
Report de recerca
Accés obertFeed-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 ... -
Non-projective parsing for statistical machine translation
(2009)
Text en actes de congrés
Accés obertWe 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
(2010)
Text en actes de congrés
Accés obertWe 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
(2008)
Text en actes de congrés
Accés obertWe 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
(2012)
Text en actes de congrés
Accés restringit per política de l'editorialIn 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
(2013-10-07)
Article
Accés restringit per política de l'editorialIn 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 ... -
Spectral regularization for max-margin sequence tagging
(2014)
Text en actes de congrés
Accés obertWe frame max-margin learning of latent variable structured prediction models as a convex optimization problem, making use of scoring functions computed by input-output observable operator models. This learning problem can ... -
Structured prediction models via the matrix-tree theorem
(2007)
Text en actes de congrés
Accés obertThis 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
(Coling 2008 Organizing Committee, 2008)
Text en actes de congrés
Accés obertWe 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 ... -
Translate first reorder later: leveraging monotonicity in semantic parsing
(Association for Computational Linguistics, 2023)
Text en actes de congrés
Accés obertPrior work in semantic parsing has shown that conventional seq2seq models fail at compositional generalization tasks. This limitation led to a resurgence of methods that model alignments between sentences and their ... -
Unsupervised spectral learning of finite-state transducers
(2012)
Text en actes de congrés
Accés obertFinite-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. ...
