Exploiting coherence for the simultaneous discovery of latent facets and associated sentiments

Facet-based sentiment analysis involves discovering the latent facets, sentiments and their associations. Traditional facet-based sentiment analysis algorithms typically perform the various tasks in sequence, and fail to take advantage of the mutual reinforcement of the tasks. Additionally,inferring sentiment levels typically requires domain knowledge or human intervention. In this paper, we propose aseries of probabilistic models that jointly discover latent facets and sentiment topics, and also order the sentiment topics with respect to a multi-point scale, in a language and domain independent manner. This is achieved by simultaneously capturing both short-range syntactic structure and long range semantic dependencies between the sentiment and facet words. The models further incorporate coherence in reviews, where reviewers dwell on one facet or sentiment level before moving on, for more accurate facet and sentiment discovery. For reviews which are supplemented with ratings, our models automatically order the latent sentiment topics, without requiring seed-words or domain-knowledge. To the best of our knowledge, our work is the first attempt to combine the notions of syntactic and semantic dependencies in the domain of review mining. Further, the concept of facet and sentiment coherence has not been explored earlier either. Extensive experimental results on real world review data show that the proposed models outperform various state of the art baselines for facet-based sentiment analysis.

Stochastic optimization for adaptive labor staffing in service systems

Service systems are labor intensive. Further, the workload tends to vary greatly with time. Adapting the staffing levels to the workloads in such systems is nontrivial due to a large number of parameters and operational variations, but crucial for business objectives such as minimal labor inventory. One of the central challenges is to optimize the staffing while maintaining system steady-state and compliance to aggregate SLA constraints. We formulate this problem as a parametrized constrained Markov process and propose a novel stochastic optimization algorithm for solving it. Our algorithm is a multi-timescale stochastic approximation scheme that incorporates a SPSA based algorithm for ‘primal descent' and couples it with a ‘dual ascent' scheme for the Lagrange multipliers. We validate this optimization scheme on five real-life service systems and compare it with a state-of-the-art optimization tool-kit OptQuest. Being two orders of magnitude faster than OptQuest, our scheme is particularly suitable for adaptive labor staffing. Also, we observe that it guarantees convergence and finds better solutions than OptQuest in many cases.

Loop transformations: convexity, pruning, and optimization

High-level loop transformations are a key instrument in mapping computational kernels to effectively exploit the resources in modern processor architectures. Nevertheless, selecting required compositions of loop transformations to achieve this remains a significantly challenging task; current compilers may be off by orders of magnitude in performance compared to hand-optimized programs. To address this fundamental challenge, we first present a convex characterization of all distinct, semantics-preserving, multidimensional affine transformations. We then bring together algebraic, algorithmic, and performance analysis results to design a tractable optimization algorithm over this highly expressive space. Our framework has been implemented and validated experimentally on a representative set of benchmarks running on state-of-the-art multi-core platforms.

A sequential dual method for structural SVMs

In many real world prediction problems the output is a structured object like a sequence or a tree or a graph. Such problems range from natural language processing to compu- tational biology or computer vision and have been tackled using algorithms, referred to as structured output learning algorithms. We consider the problem of structured classifi- cation. In the last few years, large margin classifiers like sup-port vector machines (SVMs) have shown much promise for structured output learning. The related optimization prob -lem is a convex quadratic program (QP) with a large num-ber of constraints, which makes the problem intractable for large data sets. This paper proposes a fast sequential dual method (SDM) for structural SVMs. The method makes re-peated passes over the training set and optimizes the dual variables associated with one example at a time. The use of additional heuristics makes the proposed method more efficient. We present an extensive empirical evaluation of the proposed method on several sequence learning problems.Our experiments on large data sets demonstrate that the proposed method is an order of magnitude faster than state of the art methods like cutting-plane method and stochastic gradient descent method (SGD). Further, SDM reaches steady state generalization performance faster than the SGD method. The proposed SDM is thus a useful alternative for large scale structured output learning.

Improving query focused summarization using look-ahead strategy

Query focused summarization is the task of producing a compressed text of original set of documents based on a query. Documents can be viewed as graph with sentences as nodes and edges can be added based on sentence similarity. Graph based ranking algorithms which use 'Biased random surfer model' like topic-sensitive LexRank have been successfully applied to query focused summarization. In these algorithms, random walk will be biased towards the sentences which contain query relevant words. Specifically, it is assumed that random surfer knows the query relevance score of the sentence to where he jumps. However, neighbourhood information of the sentence to where he jumps is completely ignored. In this paper, we propose look-ahead version of topic-sensitive LexRank. We assume that random surfer not only knows the query relevance of the sentence to where he jumps but he can also look N-step ahead from that sentence to find query relevance scores of future set of sentences. Using this look ahead information, we figure out the sentences which are indirectly related to the query by looking at number of hops to reach a sentence which has query relevant words. Then we make the random walk biased towards even to the indirect query relevant sentences along with the sentences which have query relevant words. Experimental results show 20.2% increase in ROUGE-2 score compared to topic-sensitive LexRank on DUC 2007 data set. Further, our system outperforms best systems in DUC 2006 and results are comparable to state of the art systems.

An adaptation framework for head-pose classification in dynamic multi-view scenarios

Multi-view head-pose estimation in low-resolution, dynamic scenes is difficult due to blurred facial appearance and perspective changes as targets move around freely in the environment. Under these conditions, acquiring sufficient training examples to learn the dynamic relationship between position, face appearance and head-pose can be very expensive. Instead, a transfer learning approach is proposed in this work. Upon learning a weighted-distance function from many examples where the target position is fixed, we adapt these weights to the scenario where target positions are varying. The adaptation framework incorporates reliability of the different face regions for pose estimation under positional variation, by transforming the target appearance to a canonical appearance corresponding to a reference scene location. Experimental results confirm effectiveness of the proposed approach, which outperforms state-of-the-art by 9.5% under relevant conditions. To aid further research on this topic, we also make DPOSE- a dynamic, multi-view head-pose dataset with ground-truth publicly available with this paper.

Music and symbolic dynamics: the science behind an art

Music signals comprise of atomic notes drawn from a musical scale. The creation of musical sequences often involves splicing the notes in a constrained way resulting in aesthetically appealing patterns. We develop an approach for music signal representation based on symbolic dynamics by translating the lexicographic rules over a musical scale to constraints on a Markov chain. This source representation is useful for machine based music synthesis, in a way, similar to a musician producing original music. In order to mathematically quantify user listening experience, we study the correlation between the max-entropic rate of a musical scale and the subjective aesthetic component. We present our analysis with examples from the south Indian classical music system.

Probabilistic least squares approach to ordinal regression

This paper proposes a novel approach to solve the ordinal regression problem using Gaussian processes. The proposed approach, probabilistic least squares ordinal regression (PLSOR), obtains the probability distribution over ordinal labels using a particular likelihood function. It performs model selection (hyperparameter optimization) using the leave-one-out cross-validation (LOO-CV) technique. PLSOR has conceptual simplicity and ease of implementation of least squares approach. Unlike the existing Gaussian process ordinal regression (GPOR) approaches, PLSOR does not use any approximation techniques for inference. We compare the proposed approach with the state-of-the-art GPOR approaches on some synthetic and benchmark data sets. Experimental results show the competitiveness of the proposed approach.

Validation based sparse Gaussian processes for ordinal regression

This paper proposes a sparse modeling approach to solve ordinal regression problems using Gaussian processes (GP). Designing a sparse GP model is important from training time and inference time viewpoints. We first propose a variant of the Gaussian process ordinal regression (GPOR) approach, leave-one-out GPOR (LOO-GPOR). It performs model selection using the leave-one-out cross-validation (LOO-CV) technique. We then provide an approach to design a sparse model for GPOR. The sparse GPOR model reduces computational time and storage requirements. Further, it provides faster inference. We compare the proposed approaches with the state-of-the-art GPOR approach on some benchmark data sets. Experimental results show that the proposed approaches are competitive.

The Lovasz θ function, SVMs and finding large dense subgraphs

The Lovasz θ function of a graph, is a fundamental tool in combinatorial optimization and approximation algorithms. Computing θ involves solving a SDP and is extremely expensive even for moderately sized graphs. In this paper we establish that the Lovasz θ function is equivalent to a kernel learning problem related to one class SVM. This interesting connection opens up many opportunities bridging graph theoretic algorithms and machine learning. We show that there exist graphs, which we call SVM−θ graphs, on which the Lovasz θ function can be approximated well by a one-class SVM. This leads to a novel use of SVM techniques to solve algorithmic problems in large graphs e.g. identifying a planted clique of size Θ(n√) in a random graph G(n,12). A classic approach for this problem involves computing the θ function, however it is not scalable due to SDP computation. We show that the random graph with a planted clique is an example of SVM−θ graph, and as a consequence a SVM based approach easily identifies the clique in large graphs and is competitive with the state-of-the-art. Further, we introduce the notion of a ''common orthogonal labeling'' which extends the notion of a ''orthogonal labelling of a single graph (used in defining the θ function) to multiple graphs. The problem of finding the optimal common orthogonal labelling is cast as a Multiple Kernel Learning problem and is used to identify a large common dense region in multiple graphs. The proposed algorithm achieves an order of magnitude scalability compared to the state of the art.

Dynamic multi-relational Chinese restaurant process for analyzing influences on users in social media

We study the problem of analyzing influence of various factors affecting individual messages posted in social media. The problem is challenging because of various types of influences propagating through the social media network that act simultaneously on any user. Additionally, the topic composition of the influencing factors and the susceptibility of users to these influences evolve over time. This problem has not been studied before, and off-the-shelf models are unsuitable for this purpose. To capture the complex interplay of these various factors, we propose a new non-parametric model called the Dynamic Multi-Relational Chinese Restaurant Process. This accounts for the user network for data generation and also allows the parameters to evolve over time. Designing inference algorithms for this model suited for large scale social-media data is another challenge. To this end, we propose a scalable and multi-threaded inference algorithm based on online Gibbs Sampling. Extensive evaluations on large-scale Twitter and Face book data show that the extracted topics when applied to authorship and commenting prediction outperform state-of-the-art baselines. More importantly, our model produces valuable insights on topic trends and user personality trends beyond the capability of existing approaches.

Behaviour simulation in computer aided product concept sketching

In the product conceptualization phase of design, sketches are often used for exploration of diverse behaviour patterns of the components to achieve the required functionality. This paper presents a method to animate the sketch produced using a tablet interface to aid verification of the desired behaviour. A sketch is a spatial organization of strokes whose perceptual organization helps one to visually interpret its components and their interconnections. A Gestalt based segmentation followed by interactive grouping and articulation, presented in this paper, enables one to use a mechanism simulation framework to animate the sketch in a “pick and drag” mode to visualize different configurations of the product and gain insight into the product’s behaviour.

A MatLAB Based Virtual Phantom for 2D Electrical Impedance Tomography (MatVP2DEIT): Studying the Medical Electrical Impedance Tomography Reconstruction in Computer

Electrical Impedance Tomography (EIT) is a computerized medical imaging technique which reconstructs the electrical impedance images of a domain under test from the boundary voltage-current data measured by an EIT electronic instrumentation using an image reconstruction algorithm. Being a computed tomography technique, EIT injects a constant current to the patient's body through the surface electrodes surrounding the domain to be imaged (Omega) and tries to calculate the spatial distribution of electrical conductivity or resistivity of the closed conducting domain using the potentials developed at the domain boundary (partial derivative Omega). Practical phantoms are essentially required to study, test and calibrate a medical EIT system for certifying the system before applying it on patients for diagnostic imaging. Therefore, the EIT phantoms are essentially required to generate boundary data for studying and assessing the instrumentation and inverse solvers a in EIT. For proper assessment of an inverse solver of a 2D EIT system, a perfect 2D practical phantom is required. As the practical phantoms are the assemblies of the objects with 3D geometries, the developing of a practical 2D-phantom is a great challenge and therefore, the boundary data generated from the practical phantoms with 3D geometry are found inappropriate for assessing a 2D inverse solver. Furthermore, the boundary data errors contributed by the instrumentation are also difficult to separate from the errors developed by the 3D phantoms. Hence, the errorless boundary data are found essential to assess the inverse solver in 2D EIT. In this direction, a MatLAB-based Virtual Phantom for 2D EIT (MatVP2DEIT) is developed to generate accurate boundary data for assessing the 2D-EIT inverse solvers and the image reconstruction accuracy. MatVP2DEIT is a MatLAB-based computer program which simulates a phantom in computer and generates the boundary potential data as the outputs by using the combinations of different phantom parameters as the inputs to the program. Phantom diameter, inhomogeneity geometry (shape, size and position), number of inhomogeneities, applied current magnitude, background resistivity, inhomogeneity resistivity all are set as the phantom variables which are provided as the input parameters to the MatVP2DEIT for simulating different phantom configurations. A constant current injection is simulated at the phantom boundary with different current injection protocols and boundary potential data are calculated. Boundary data sets are generated with different phantom configurations obtained with the different combinations of the phantom variables and the resistivity images are reconstructed using EIDORS. Boundary data of the virtual phantoms, containing inhomogeneities with complex geometries, are also generated for different current injection patterns using MatVP2DEIT and the resistivity imaging is studied. The effect of regularization method on the image reconstruction is also studied with the data generated by MatVP2DEIT. Resistivity images are evaluated by studying the resistivity parameters and contrast parameters estimated from the elemental resistivity profiles of the reconstructed phantom domain. Results show that the MatVP2DEIT generates accurate boundary data for different types of single or multiple objects which are efficient and accurate enough to reconstruct the resistivity images in EIDORS. The spatial resolution studies show that, the resistivity imaging conducted with the boundary data generated by MatVP2DEIT with 2048 elements, can reconstruct two circular inhomogeneities placed with a minimum distance (boundary to boundary) of 2 mm. It is also observed that, in MatVP2DEIT with 2048 elements, the boundary data generated for a phantom with a circular inhomogeneity of a diameter less than 7% of that of the phantom domain can produce resistivity images in EIDORS with a 1968 element mesh. Results also show that the MatVP2DEIT accurately generates the boundary data for neighbouring, opposite reference and trigonometric current patterns which are very suitable for resistivity reconstruction studies. MatVP2DEIT generated data are also found suitable for studying the effect of the different regularization methods on reconstruction process. Comparing the reconstructed image with an original geometry made in MatVP2DEIT, it would be easier to study the resistivity imaging procedures as well as the inverse solver performance. Using the proposed MatVP2DEIT software with modified domains, the cross sectional anatomy of a number of body parts can be simulated in PC and the impedance image reconstruction of human anatomy can be studied.

Lovasz theta function, SVMs and Finding Dense Subgraphs

In this paper we establish that the Lovasz theta function on a graph can be restated as a kernel learning problem. We introduce the notion of SVM-theta graphs, on which Lovasz theta function can be approximated well by a Support vector machine (SVM). We show that Erdos-Renyi random G(n, p) graphs are SVM-theta graphs for log(4)n/n <= p < 1. Even if we embed a large clique of size Theta(root np/1-p) in a G(n, p) graph the resultant graph still remains a SVM-theta graph. This immediately suggests an SVM based algorithm for recovering a large planted clique in random graphs. Associated with the theta function is the notion of orthogonal labellings. We introduce common orthogonal labellings which extends the idea of orthogonal labellings to multiple graphs. This allows us to propose a Multiple Kernel learning (MKL) based solution which is capable of identifying a large common dense subgraph in multiple graphs. Both in the planted clique case and common subgraph detection problem the proposed solutions beat the state of the art by an order of magnitude.

Automatic Tonic Identification in Indian Art Music: Approaches and Evaluation

The tonic is a fundamental concept in Indian art music. It is the base pitch, which an artist chooses in order to construct the melodies during a rg(a) rendition, and all accompanying instruments are tuned using the tonic pitch. Consequently, tonic identification is a fundamental task for most computational analyses of Indian art music, such as intonation analysis, melodic motif analysis and rg recognition. In this paper we review existing approaches for tonic identification in Indian art music and evaluate them on six diverse datasets for a thorough comparison and analysis. We study the performance of each method in different contexts such as the presence/absence of additional metadata, the quality of audio data, the duration of audio data, music tradition (Hindustani/Carnatic) and the gender of the singer (male/female). We show that the approaches that combine multi-pitch analysis with machine learning provide the best performance in most cases (90% identification accuracy on average), and are robust across the aforementioned contexts compared to the approaches based on expert knowledge. In addition, we also show that the performance of the latter can be improved when additional metadata is available to further constrain the problem. Finally, we present a detailed error analysis of each method, providing further insights into the advantages and limitations of the methods.