Learn More
(1985). A learning algorithm for boltzmann machines. (2010). Learning the structure of deep sparse graphical models. In AI/Statistics. On tight approximate inference of the logistic-normal topic admixture model. In AI/Statistics.ference using message propoga-tion and topology transformation in vector Gaussian continuous networks. In UAI. Bayesian analysis(More)
Learning general functional dependencies is one of the main goals in machine learning. Recent progress in kernel-based methods has focused on designing flexible and powerful input representations. This paper addresses the complementary issue of problems involving complex outputs such as multiple dependent output variables and structured output spaces. We(More)
This paper presents a novel discriminative learning technique for label sequences based on a combination of the two most successful learning algorithms, Support Vector Machines and Hidden Markov Models which we call Hidden Markov Support Vector Machine. The proposed architecture handles dependencies between neighboring labels using Viterbi decoding. In(More)
This paper presents a novel approach to broad-coverage word sense disambigua-tion and information extraction. The task consists of annotating text with the tagset defined by the 41 Wordnet super-sense classes for nouns and verbs. Since the tagset is directly related to Wordnet synsets, the tagger returns partial word sense disambiguation. Furthermore, since(More)
In this paper we unify divergence minimization and statistical inference by means of convex duality. In the process of doing so, we prove that the dual of approximate maximum entropy estimation is maximum a posteriori estimation. Moreover, our treatment leads to stability and convergence bounds for many statistical learning problems. Finally, we show how an(More)
This paper investigates a boosting approach to discriminative learning of label sequences based on a sequence rank loss function. The proposed method combines many of the advantages of boosting schemes with the efficiency of dynamic programming methods and is attractive both, conceptually and computationally. In addition , we also discuss alternative(More)
The detection of prosodic characteristics is an important aspect of both speech synthesis and speech recognition. Correct placement of pitch accents aids in more natural sounding speech, while automatic detection of accents can contribute to better word-level recognition and better textual understanding. In this paper we investigate probabilistic,(More)
We investigate the adaptation of structured classifiers to new domains. In particular, the problem of using a supervised Named-Entity Recognition (NER) system on data from a different source than the training data. We present a Semi-Markov Model, trained with the perceptron algorithm, coupled with an external dictionary with the goal of improving(More)