Cross-Lingual spoken language understanding from unaligned data using discriminative classification models and machine translation

This paper investigates several approaches to bootstrapping a new spoken language understanding (SLU) component in a target language given a large dataset of semantically-annotated utterances in some other source language. The aim is to reduce the cost associated with porting a spoken dialogue system from one language to another by minimising the amount of data required in the target language. Since word-level semantic annotations are costly, Semantic Tuple Classifiers (STCs) are used in conjunction with statistical machine translation models both of which are trained from unaligned data to further reduce development time. The paper presents experiments in which a French SLU component in the tourist information domain is bootstrapped from English data. Results show that training STCs on automatically translated data produced the best performance for predicting the utterance's dialogue act type, however individual slot/value pairs are best predicted by training STCs on the source language and using them to decode translated utterances. © 2010 ISCA.

Derivative Kernels for Noise Robust ASR

Recently there has been interest in combined gen- erative/discriminative classifiers. In these classifiers features for the discriminative models are derived from generative kernels. One advantage of using generative kernels is that systematic approaches exist how to introduce complex dependencies beyond conditional independence assumptions. Furthermore, by using generative kernels model-based compensation/adaptation tech- niques can be applied to make discriminative models robust to noise/speaker conditions. This paper extends previous work with combined generative/discriminative classifiers in several directions. First, it introduces derivative kernels based on context- dependent generative models. Second, it describes how derivative kernels can be incorporated in continuous discriminative models. Third, it addresses the issues associated with large number of classes and parameters when context-dependent models and high- dimensional features of derivative kernels are used. The approach is evaluated on two noise-corrupted tasks: small vocabulary AURORA 2 and medium-to-large vocabulary AURORA 4 task.

Derivative kernels for noise robust ASR

Recently there has been interest in combining generative and discriminative classifiers. In these classifiers features for the discriminative models are derived from the generative kernels. One advantage of using generative kernels is that systematic approaches exist to introduce complex dependencies into the feature-space. Furthermore, as the features are based on generative models standard model-based compensation and adaptation techniques can be applied to make discriminative models robust to noise and speaker conditions. This paper extends previous work in this framework in several directions. First, it introduces derivative kernels based on context-dependent generative models. Second, it describes how derivative kernels can be incorporated in structured discriminative models. Third, it addresses the issues associated with large number of classes and parameters when context-dependent models and high-dimensional feature-spaces of derivative kernels are used. The approach is evaluated on two noise-corrupted tasks: small vocabulary AURORA 2 and medium-to-large vocabulary AURORA 4 task. © 2011 IEEE.

MCBoost: Multiple classifier boosting for perceptual co-clustering of images and visual features

We present a new co-clustering problem of images and visual features. The problem involves a set of non-object images in addition to a set of object images and features to be co-clustered. Co-clustering is performed in a way that maximises discrimination of object images from non-object images, thus emphasizing discriminative features. This provides a way of obtaining perceptual joint-clusters of object images and features. We tackle the problem by simultaneously boosting multiple strong classifiers which compete for images by their expertise. Each boosting classifier is an aggregation of weak-learners, i.e. simple visual features. The obtained classifiers are useful for object detection tasks which exhibit multimodalities, e.g. multi-category and multi-view object detection tasks. Experiments on a set of pedestrian images and a face data set demonstrate that the method yields intuitive image clusters with associated features and is much superior to conventional boosting classifiers in object detection tasks.

Making a shallow network deep: Conversion of a boosting classifier into a decision tree by boolean optimisation

This paper presents a novel way to speed up the evaluation time of a boosting classifier. We make a shallow (flat) network deep (hierarchical) by growing a tree from decision regions of a given boosting classifier. The tree provides many short paths for speeding up while preserving the reasonably smooth decision regions of the boosting classifier for good generalisation. For converting a boosting classifier into a decision tree, we formulate a Boolean optimization problem, which has been previously studied for circuit design but limited to a small number of binary variables. In this work, a novel optimisation method is proposed for, firstly, several tens of variables i.e. weak-learners of a boosting classifier, and then any larger number of weak-learners by using a two-stage cascade. Experiments on the synthetic and face image data sets show that the obtained tree achieves a significant speed up both over a standard boosting classifier and the Fast-exit-a previously described method for speeding-up boosting classification, at the same accuracy. The proposed method as a general meta-algorithm is also useful for a boosting cascade, where it speeds up individual stage classifiers by different gains. The proposed method is further demonstrated for fast-moving object tracking and segmentation problems. © 2011 Springer Science+Business Media, LLC.

Discriminative spoken language understanding using word confusion networks

Current commercial dialogue systems typically use hand-crafted grammars for Spoken Language Understanding (SLU) operating on the top one or two hypotheses output by the speech recogniser. These systems are expensive to develop and they suffer from significant degradation in performance when faced with recognition errors. This paper presents a robust method for SLU based on features extracted from the full posterior distribution of recognition hypotheses encoded in the form of word confusion networks. Following [1], the system uses SVM classifiers operating on n-gram features, trained on unaligned input/output pairs. Performance is evaluated on both an off-line corpus and on-line in a live user trial. It is shown that a statistical discriminative approach to SLU operating on the full posterior ASR output distribution can substantially improve performance both in terms of accuracy and overall dialogue reward. Furthermore, additional gains can be obtained by incorporating features from the previous system output. © 2012 IEEE.

Encoding of mixtures in a simple olfactory system.

Natural odors are usually mixtures; yet, humans and animals can experience them as unitary percepts. Olfaction also enables stimulus categorization and generalization. We studied how these computations are performed with the responses of 168 locust antennal lobe projection neurons (PNs) to varying mixtures of two monomolecular odors, and of 174 PNs and 209 mushroom body Kenyon cells (KCs) to mixtures of up to eight monomolecular odors. Single-PN responses showed strong hypoadditivity and population trajectories clustered by odor concentration and mixture similarity. KC responses were much sparser on average than those of PNs and often signaled the presence of single components in mixtures. Linear classifiers could read out the responses of both populations in single time bins to perform odor identification, categorization, and generalization. Our results suggest that odor representations in the mushroom body may result from competing optimization constraints to facilitate memorization (sparseness) while enabling identification, classification, and generalization.

Multilinear function factorisation for time series feature extraction

This work applies a variety of multilinear function factorisation techniques to extract appropriate features or attributes from high dimensional multivariate time series for classification. Recently, a great deal of work has centred around designing time series classifiers using more and more complex feature extraction and machine learning schemes. This paper argues that complex learners and domain specific feature extraction schemes of this type are not necessarily needed for time series classification, as excellent classification results can be obtained by simply applying a number of existing matrix factorisation or linear projection techniques, which are simple and computationally inexpensive. We highlight this using a geometric separability measure and classification accuracies obtained though experiments on four different high dimensional multivariate time series datasets. © 2013 IEEE.

Encoding of mixtures in a simple olfactory system

Natural odors are usually mixtures; yet, humans and animals can experience them as unitary percepts. Olfaction also enables stimulus categorization and generalization. We studied how these computations are performed with the responses of 168 locust antennal lobe projection neurons (PNs) to varying mixtures of two monomolecular odors, and of 174 PNs and 209 mushroom body Kenyon cells (KCs) to mixtures of up to eight monomolecular odors. Single-PN responses showed strong hypoadditivity and population trajectories clustered by odor concentration and mixture similarity. KC responses were much sparser on average than those of PNs and often signaled the presence of single components in mixtures. Linear classifiers could read out the responses of both populations in single time bins to perform odor identification, categorization, and generalization. Our results suggest that odor representations in the mushroom body may result from competing optimization constraints to facilitate memorization (sparseness) while enabling identification, classification, and generalization

Is there a preferred classifier for operational thematic mapping?

The importance of properly exploiting a classifier's inherent geometric characteristics when developing a classification methodology is emphasized as a prerequisite to achieving near optimal performance when carrying out thematic mapping. When used properly, it is argued that the long-standing maximum likelihood approach and the more recent support vector machine can perform comparably. Both contain the flexibility to segment the spectral domain in such a manner as to match inherent class separations in the data, as do most reasonable classifiers. The choice of which classifier to use in practice is determined largely by preference and related considerations, such as ease of training, multiclass capabilities, and classification cost. © 1980-2012 IEEE.