Browsing by Author "Quattoni, Ariadna Julieta"
Now showing items 1-14 of 14
-
A joint model for 2D and 3D pose estimation from a single image
(Institute of Electrical and Electronics Engineers (IEEE), 2013)
Conference report
Restricted access - publisher's policyWe introduce a novel approach to automatically recover 3D human pose from a single image. Most previous work follows a pipelined approach: initially, a set of 2D features such as edges, joints or silhouettes are detected ... -
A latent variable ranking model for content-based retrieval
(Springer, 2012)
Conference report
Restricted access - publisher's policySince 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 ... -
Learning task-specific bilexical embeddings
(2014)
Conference report
Open AccessWe 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 ... -
Measuring alignment bias in neural Seq2Seq semantic parsers
(Association for Computational Linguistics, 2022)
Conference report
Open AccessPrior to deep learning the semantic parsing community has been interested in understanding and modeling the range of possible word alignments between natural language sentences and their corresponding meaning representations. ... -
Semantic tuples for evaluation of image sentence generation
(2015)
Conference report
Open AccessThe automatic generation of image captions has received considerable attention. The problem of evaluating caption generation systems, though, has not been that much explored. We propose a novel evaluation approach based ... -
Spectral learning in non-deterministic dependency parsing
(2012)
Conference report
Restricted access - publisher's policyIn 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 sequence taggers over continuous sequences
(Springer-Verlag, 2013)
Conference report
Restricted access - publisher's policyIn this paper we present a spectral algorithm for learning weighted finite-state sequence taggers (WFSTs) over paired input-output sequences, where the input is continuous and the output discrete. WFSTs are an important ... -
Spectral learning of transducers over continuous sequences
(2013-01-01)
Research report
Open AccessIn this paper we present a spectral algorithm for learning weighted nite state transducers (WFSTs) over paired input-output sequences, where the input is continuous and the output discrete. WFSTs are an important tool for ... -
Spectral learning of weighted automata: a forward-backward perspective
(2013-10-07)
Article
Restricted access - publisher's policyIn 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)
Conference report
Open AccessWe 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 with output embeddings for semantic image annotation
(2016)
Conference report
Open AccessWe address the task of annotating images with semantic tuples. Solving this problem requires an algorithm able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key ... -
Unsupervised spectral learning of finite-state transducers
(2012)
Conference report
Open AccessFinite-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
(2013)
Conference report
Open AccessFinite-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
(Association for Computational Linguistics, 2013)
Conference lecture
Open AccessWe 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 ...
