learning pseudo-independent models

... Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Learning Syntactic Verb Frames Using Graphical Models Thomas Lippincott University of Cambridge Computer Laboratory United ... of verbs: VerbNet (Kipper et al., 2008) draws on several hand-built and semi-automatic sources to link the syntax and semantics of 5,726 verbs. FrameNet (Baker et al., 1998) provides se...

Ngày tải lên: 19/02/2014, 19:20

... source and target lan- guage, and alternative translation possibilities are expressed as alternative edges. Edges are further annotated with feature values, and are annotated with the source span ... prun- ing, and cube growing (Huang and Chiang, 2007). 5 Semiring framework Semirings are a useful mathematical abstraction for dealing with translation forests since many usef...

Ngày tải lên: 07/03/2014, 22:20

... Dia- logue Simulation Using Hidden Markov Models. In Proc. of ASRU, pages 290–295. Nina Dethlefs and Heriberto Cuay´ahuitl. 2010. Hi- erarchical Reinforcement Learning for Adaptive Text Generation. ... Association for Computational Linguistics:shortpapers, pages 654–659, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Hierarchical Reinfo...

Ngày tải lên: 07/03/2014, 22:20

... customized for this monolingual task, the ILP approach signif- icantly outperforms the majority sense baseline and performs as well as the state-of-the-art system re- porting results for the same ... frequent translation are shown in Table 1. For the monolingual scenario, we use the sense tagged corpus and sense repositories provided for verbs in Senseval-3. There are 32 verb...

Ngày tải lên: 08/03/2014, 02:21

... Linguistics Phrase-based Statistical Language Generation using Graphical Models and Active Learning Francáois Mairesse, Milica Ga ˇ si ´ c, Filip Jur ˇ c ´ ı ˇ cek, Simon Keizer, Blaise Thomson, Kai Yu and Steve ... E. Schapire, and D. Hakkani-T ă ur. Active learn- ing for spoken language understanding. In Proceedings of ICASSP, 2003. S. Varges and C. Mellish. Instan...

Ngày tải lên: 17/03/2014, 00:20

... approach to discriminative lan- guage models. First, we introduced the idea of us- ing factored features in the discriminative language modeling framework. Factored features allow the language model ... correlated factored features, and extend a robust learning algorithm to handle them and cope with a high rate of label noise. For discriminatively learning language mod...

Ngày tải lên: 17/03/2014, 00:20

... we take the PCFG encoding of the LDA topic model described above, but modify it so that the Topic i nodes generate sequences of words rather than sin- gle words. Then we adapt each of the Topic i non- terminals, ... further details. 1153 The set of trees generated by the CFG is T S , where S is the start symbol, and the set of strings generated by the CFG...

Ngày tải lên: 23/03/2014, 16:20

... method is also general to other lexicalized reordering models. We plan to apply our method to the complex lexicalized reordering models, for example, the hierarchical reordering model (Galley and ... give a brief introduction to the traditional lexicalized reordering model. Then we introduce our method to estimate the reordering probabilities from reordering graphs. The...

Ngày tải lên: 23/03/2014, 16:20

... Proceedings of the 43rd Annual Meeting of the ACL, pages 371–378, Ann Arbor, June 2005. c 2005 Association for Computational Linguistics Unsupervised Learning of Field Segmentation Models for Information ... consists of de- scriptions of attributes of an item or offer, and a set of ads for similar items share the same attributes. In these cases, the fields presen...

Ngày tải lên: 23/03/2014, 19:20

... pairs from the clickthrough data. These pairs, impli- citly judged by millions of users, are used to train a set of spelling error models. Among these models, the most effective one is a phrase-based ... the error models learned from clickthrough data lead to significant improvements on the task of query spelling correction. In particular, the speller sys- tem incorpor...

Ngày tải lên: 30/03/2014, 21:20

... part of the First name/ Last name graph: Edges indicate co-occurrence or a shared name. Character Ngram graph The ethnicity of personal names are often indi- cated by morphophonemic features of ... Linguistics Typed Graph Models for Semi-Supervised Learning of Name Ethnicity Delip Rao Dept. of Computer Science Johns Hopkins University delip@cs.jhu.edu David Yaro...

Ngày tải lên: 30/03/2014, 21:20

... maximization of submodular functions. In Proceedings of NAACL-HLT, 2010. H. Lin and J. Bilmes. 2011. A Class of Submodu- lar Functions for Document Summarization. In Pro- ceedings of ACL-HLT, ... Linguistics Large-Margin Learning of Submodular Summarization Models Ruben Sipos Dept. of Computer Science Cornell University Ithaca, NY 14853 USA rs@cs.cornell.edu Pannaga Shiva...

Ngày tải lên: 31/03/2014, 20:20

... dimensionality reduction Bayesian learning can infer a posterior over the number of clusters and their intrinsic dimensionalities. Probabilistic Models for Unsupervised Learning Zoubin Ghahramani Sam ... model complexity penalty (i.e. coding cost for all the parameters of the model) so it can be compared across models Optimal form of falls out of free-form variational optimis...

Ngày tải lên: 24/04/2014, 13:20

... UNIVERSITY OF CALIFORNIA, SAN DIEGO Facing Uncertainty: 3D Face Tracking and Learning with Generative Models A dissertation submitted in partial satisfaction of the requirements ... Computation, pp. 55–63, 2000. xi ABSTRACT OF THE DISSERTATION Facing Uncertainty: 3D Face Tracking and Learning with Generative Models by Tim Kalman Marks Doctor of Philosophy...

Ngày tải lên: 13/11/2014, 10:17

Ngày tải lên: 13/11/2014, 15:44