Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Martins, Andre F.T."'
Autor:
Bicego, Manuele a, ⁎, Ulaş, Aydın a, Castellani, Umberto a, Perina, Alessandro e, Murino, Vittorio a, b, Martins, André F.T. c, Aguiar, Pedro M.Q. d, Figueiredo, Mário A.T. c
Publikováno v:
In Neurocomputing 4 February 2013 101:161-169
Autor:
Martins, Andre F.T., Smith, Noah A., Xing, Eric P., Aguiar, Pedro M.Q., Figeuiredo, Mario A. T.
Training structured predictors often requires a considerable time selecting features or tweaking the kernel. Multiple kernel learning (MKL) sidesteps this issue by embedding the kernel learning into the training procedure. Despite the recent progress
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::377da0411cb9e8de29563d5e396d57fa
Autor:
Martins, Andre F.T., Smith, Noah A., Xing, Eric P., Aguiar, Pedro M.Q., Figueiredo, Mario A. T.
Despite the recent progress towards efficient multiple kernel learning (MKL), the structured output case remains an open research front. Current approaches involve repeatedly solving a batch learning problem, which makes them inadequate for large sca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::10288e39a6aaed60e5b54b59f84eb7e3
Autor:
Martins, Andre F.T., Figeuiredo, Mario A. T., Aguiar, Pedro M.Q., Smith, Noah A., Xing, Eric P
We propose AD3 , a new algorithm for approximate maximum a posteriori (MAP) inference on factor graphs based on the alternating directions method of multipliers. Like dual decomposition algorithms, AD3 uses worker nodes to iteratively solve local sub
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b7f171b0acab81c648f8e0fcc57a8a15
Autor:
Martins, Andre F.T., Figueiredo, Mario A. T., Aguiar, Pedro M.Q., Smith, Noah A., Xing, Eric P
We present AD3, a new algorithm for approximate maximum a posteriori (MAP) inference on factor graphs, based on the alternating directions method of multipliers. Like other dual decomposition algorithms, AD3 has a modular architecture, where local su
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::09af7b50703e3cb34d9141374ff23db6
We present fast, accurate, direct nonprojective dependency parsers with thirdorder features. Our approach uses AD3 , an accelerated dual decomposition algorithm which we extend to handle specialized head automata and sequential head bigram models. Ex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ae75c3b16b3931ac55c49683c631174
We present a novel technique for jointly predicting semantic arguments for lexical predicates. The task is to find the best matching between semantic roles and sentential spans, subject to structural constraints that come from expert linguistic knowl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::65a6abcd807e0e1bb365c7de9886ca82
Autor:
Martins, Andre F.T., Figeuiredo, Mario A. T., Aguiar, Pedro M.Q., Smith, Noah A., Xing, Eric P
We propose a new fast algorithm for approximate MAP inference on factor graphs, which combines augmented Lagrangian optimization with the dual decomposition method. Each slave subproblem is given a quadratic penalty, which pushes toward faster consen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::76e191bbcb60af71719061096f064f63
Dual decomposition has been recently proposed as a way of combining complementary models, with a boost in predictive power. However, in cases where lightweight decompositions are not readily available (e.g., due to the presence of rich features or lo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2b5fc52ce256e863151a4d09125de415
Linear models have enjoyed great success in structured prediction in NLP. While a lot of progress has been made on efficient training with several loss functions, the problem of endowing learners with a mechanism for feature selection is still unsolv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::800a909554a6c1dad5fd4ab2c5ce953d