Documents and Dependencies: an Exploration of Vector Space Models for Semantic Composition

In most previous research on distributional semantics, Vector Space Models (VSMs) of words are built either from topical information (e.g., documents in which a word is present), or from syntactic/semantic types of words (e.g., dependency parse links of a word in sentences), but not both. In this paper, we explore the utility of combining these two representations to build VSM for the task of semantic composition of adjective-noun phrases. Through extensive experiments on benchmark datasets, we find that even though a type-based VSM is effective for semantic composition, it is often outperformed by a VSM built using a combination of topic- and type-based statistics. We also introduce a new evaluation task wherein we predict the composed vector representation of a phrase from the brain activity of a human subject reading that phrase. We exploit a large syntactically parsed corpus of 16 billion tokens to build our VSMs, with vectors for both phrases and words, and make them publicly available.

Determinants of WTP for Prosecco wine: A latent class regression with attitudinal responses

Purpose – Under investigation is Prosecco wine, a sparkling white wine from North-East Italy.
Information collection on consumer perceptions is particularly relevant when developing market
strategies for wine, especially so when local production and certification of origin play an important
role in the wine market of a given district, as in the case at hand. Investigating and characterizing the
structure of preference heterogeneity become crucial steps in every successful marketing strategy. The
purpose of this paper is to investigate the sources of systematic differences in consumer preferences.
Design/methodology/approach – The paper explores the effect of inclusion of answers to
attitudinal questions in a latent class regression model of stated willingness to pay (WTP) for this
specialty wine. These additional variables were included in the membership equations to investigate
whether they could be of help in the identification of latent classes. The individual specific WTPs from
the sampled respondents were then derived from the best fitting model and examined for consistency.
Findings – The use of answers to attitudinal question in the latent class regression model is found to
improve model fit, thereby helping in the identification of latent classes. The best performing model
obtained makes use of both attitudinal scores and socio-economic covariates identifying five latent
classes. A reasonable pattern of differences in WTP for Prosecco between CDO and TGI types were
derived from this model.
Originality/value – The approach appears informative and promising: attitudes emerge as
important ancillary indicators of taste differences for specialty wines. This might be of interest per se
and of practical use in market segmentation. If future research shows that these variables can be of use
in other contexts, it is quite possible that more attitudinal questions will be routinely incorporated in
structural latent class hedonic models.

Analysis of IL6 Signal Transduction Model using Reduced Rank Regression

This work presents the application of reduced rank regression to the field of systems biology. A computational approach is used to investigate the mechanisms of the janus-associated kinases/signal transducers and transcription factors (JAK/STAT) and mitogen activated protein kinases (MAPK) signal transduction pathways in hepatic cells stimulated by interleukin-6. The results obtained identify the contribution of individual reactions to the dynamics of the model. These findings are compared to previously available results from sensitivity analysis of the model which focused on the parameters involved and their effect. This application of reduced rank regression allows for an understanding of the individual reaction terms involved in the modelled signal transduction pathways and has the benefit of being computationally inexpensive. The obtained results complement existing findings and also confirm the importance of several protein complexes in the MAPK pathway which hints at benefits that can be achieved by further refining the model.

A Vector Approach for the Analysis and Synthesis of Directional Modulation Transmitters

In order to formalize and extend on previous ad-hoc analysis and synthesis methods a theoretical treatment using vector representations of directional modulation (DM) systems is introduced and used to achieve DM transmitter characteristics. An orthogonal vector approach is proposed which allows the artificial orthogonal noise concept derived from information theory to be brought to bear on DM analysis and synthesis. The orthogonal vector method is validated and discussed via bit error rate (BER) simulations.

Vector representation of directional modulation transmitters

Directional Modulation (DM) is a recently proposed technique for securing wireless communication. In this paper we point out that modulation-directionality is a consequence of varying the beamforming network, either in baseband or in the RF stage, at the information rate In order to formalize and extend on previous analysis and synthesis methods a new theoretical treatment using vector representations of directional modulation (DM) systems is introduced and used to obtain the necessary and sufficient con

Vector bundles on the projective line and finite domination of chain complexes

We present an algebro-geometric approach to a theorem on finite domination of chain complexes over a Laurent polynomial ring. The approach uses extension of chain complexes to sheaves on the projective line, which is governed by a K-theoretical obstruction.

A predictive maintenance system for integral type faults based on support vector machines:An application to ion implantation

In semiconductor fabrication processes, effective management of maintenance operations is fundamental to decrease costs associated with failures and downtime. Predictive Maintenance (PdM) approaches, based on statistical methods and historical data, are becoming popular for their predictive capabilities and low (potentially zero) added costs. We present here a PdM module based on Support Vector Machines for prediction of integral type faults, that is, the kind of failures that happen due to machine usage and stress of equipment parts. The proposed module may also be employed as a health factor indicator. The module has been applied to a frequent maintenance problem in semiconductor manufacturing industry, namely the breaking of the filament in the ion-source of ion-implantation tools. The PdM has been tested on a real production dataset. © 2013 IEEE.

A dynamic sampling methodology for plasma etch processes using Gaussian process regression

Plasma etch is a key process in modern semiconductor manufacturing facilities as it offers process simplification and yet greater dimensional tolerances compared to wet chemical etch technology. The main challenge of operating plasma etchers is to maintain a consistent etch rate spatially and temporally for a given wafer and for successive wafers processed in the same etch tool. Etch rate measurements require expensive metrology steps and therefore in general only limited sampling is performed. Furthermore, the results of measurements are not accessible in real-time, limiting the options for run-to-run control. This paper investigates a Virtual Metrology (VM) enabled Dynamic Sampling (DS) methodology as an alternative paradigm for balancing the need to reduce costly metrology with the need to measure more frequently and in a timely fashion to enable wafer-to-wafer control. Using a Gaussian Process Regression (GPR) VM model for etch rate estimation of a plasma etch process, the proposed dynamic sampling methodology is demonstrated and evaluated for a number of different predictive dynamic sampling rules. © 2013 IEEE.

MSC-clustering and forward stepwise regression for virtual metrology in highly correlated input spaces

Increasingly semiconductor manufacturers are exploring opportunities for virtual metrology (VM) enabled process monitoring and control as a means of reducing non-value added metrology and achieving ever more demanding wafer fabrication tolerances. However, developing robust, reliable and interpretable VM models can be very challenging due to the highly correlated input space often associated with the underpinning data sets. A particularly pertinent example is etch rate prediction of plasma etch processes from multichannel optical emission spectroscopy data. This paper proposes a novel input-clustering based forward stepwise regression methodology for VM model building in such highly correlated input spaces. Max Separation Clustering (MSC) is employed as a pre-processing step to identify a reduced srt of well-conditioned, representative variables that can then be used as inputs to state-of-the-art model building techniques such as Forward Selection Regression (FSR), Ridge regression, LASSO and Forward Selection Ridge Regression (FCRR). The methodology is validated on a benchmark semiconductor plasma etch dataset and the results obtained are compared with those achieved when the state-of-art approaches are applied directly to the data without the MSC pre-processing step. Significant performance improvements are observed when MSC is combined with FSR (13%) and FSRR (8.5%), but not with Ridge Regression (-1%) or LASSO (-32%). The optimal VM results are obtained using the MSC-FSR and MSC-FSRR generated models. © 2012 IEEE.

Efficient Marginal Likelihood Computation for Gaussian Process Regression

In a Bayesian learning setting, the posterior distribution of a predictive model arises from a trade-off between its prior distribution and the conditional likelihood of observed data. Such distribution functions usually rely on additional hyperparameters which need to be tuned in order to achieve optimum predictive performance; this operation can be efficiently performed in an Empirical Bayes fashion by maximizing the posterior marginal likelihood of the observed data. Since the score function of this optimization problem is in general characterized by the presence of local optima, it is necessary to resort to global optimization strategies, which require a large number of function evaluations. Given that the evaluation is usually computationally intensive and badly scaled with respect to the dataset size, the maximum number of observations that can be treated simultaneously is quite limited. In this paper, we consider the case of hyperparameter tuning in Gaussian process regression. A straightforward implementation of the posterior log-likelihood for this model requires O(N^3) operations for every iteration of the optimization procedure, where N is the number of examples in the input dataset. We derive a novel set of identities that allow, after an initial overhead of O(N^3), the evaluation of the score function, as well as the Jacobian and Hessian matrices, in O(N) operations. We prove how the proposed identities, that follow from the eigendecomposition of the kernel matrix, yield a reduction of several orders of magnitude in the computation time for the hyperparameter optimization problem. Notably, the proposed solution provides computational advantages even with respect to state of the art approximations that rely on sparse kernel matrices.