Background | In this section we review the leXicon learning algorithm introduced by Chen and Mooney (2011) as well as the overall task they designed to test semantic understanding of navigation instructions. |
Experiments | We evaluate our new lexicon learning algorithm as well as the other modifications to the navigation system using the same three tasks as Chen and Mooney (2011). |
Experiments | Here SGOLL has a decidedly large advantage over the lexicon learning algorithm from Chen and Mooney, requiring an order of magnitude less time to run. |
Experiments | We have introduced a novel, online lexicon learning algorithm that is much faster than the one proposed by Chen and Mooney and also performs better on the navigation tasks they devised. |
Introduction | Their lexicon learning algorithm finds the common connected subgraph that occurs with a word by taking intersections of the graphs that represent the different contexts in which the word appears. |
Introduction | In addition to the new lexicon learning algorithm , we also look at modifying the meaning representation grammar (MRG) for their formal semantic language. |
Online Lexicon Learning Algorithm | In addition to introducing a new lexicon learning algorithm , we also made another modification to the original system proposed by Chen and Mooney (2011). |
Discussion | extension of the model and learning algorithm to word sequences and (2) feature functions that relate acoustic measurements to sub-word units. |
Experiments | We compare the CRF4, Passive-Aggressive (PA), and Pegasos learning algorithms . |
Experiments | 4We use the term “CRF” since the learning algorithm corresponds to CRF learning, although the task is multiclass classification rather than a sequence or structure prediction task. |
Experiments | Models labeled X/Y use learning algorithm X and feature set Y. |
Problem setting | In the next section we present a learning algorithm that aims to minimize the expected zero-one loss. |
Abstract | We introduce a spectral learning algorithm for latent-variable PCFGs (Petrov et al., 2006). |
Deriving Empirical Estimates | We now state a PAC-style theorem for the learning algorithm . |
Introduction | Recent work has introduced polynomial-time learning algorithms (and consistent estimation methods) for two important cases of hidden-variable models: Gaussian mixture models (Dasgupta, 1999; Vempala and Wang, 2004) and hidden Markov models (Hsu et al., 2009). |
Proofs | Figure 4: The spectral learning algorithm . |
Related Work | (2011) consider spectral learning algorithms of tree-structured directed bayes nets. |
System Architecture | ADF learning algorithm : procedure ADF(q, c, a, [3) |
System Architecture | Figure 1: The proposed ADF online learning algorithm . |
System Architecture | Prior work on convergence analysis of existing online learning algorithms (Murata, 1998; Hsu et |
Conclusion | We have proposed new approaches to characterize verb classes in learning algorithms . |
Conclusion | The advantage of kernel methods is that they can be directly used in some learning algorithms , e.g., SVMs, to train verb classifiers. |
Introduction | Note that their coding in learning algorithms is rather complex: we need to take into account syntactic structures, which may require an exponential number of syntactic features (i.e., all their possible substructures). |