Multilingual Text Classification (MLTC) is a text classification task in which documents are written each in one among a set L of natural languages, and in which all documents must be classified under the same classification scheme, irrespective of language. There are two main variants of MLTC, namely Cross-Lingual Text Classification (CLTC) and Polylingual Text Classification (PLTC). In PLTC, which is the focus of this paper, we assume (differently from CLTC) that for each language in L there is a representative set of training documents; PLTC consists of improving the accuracy of each of the |L| monolingual classifiers by also leveraging the training documents written in the other (|L| − 1) languages. The obvious solution, consisting of generating a single polylingual classifier from the juxtaposed monolingual vector spaces, is usually infeasible, since the dimensionality of the resulting vector space is roughly |L| times that of a monolingual one, and is thus often unmanageable. As a response, the use of machine translation tools or multilingual dictionaries has been proposed. However, these resources are not always available, or are not always free to use. One machine-translation-free and dictionary-free method that, to the best of our knowledge, has never been applied to PLTC before, is Random Indexing (RI). We analyse RI in terms of space and time efficiency, and propose a particular configuration of it (that we dub Lightweight Random Indexing LRI). By running experiments on two well known public benchmarks, Reuters RCV1/RCV2 (a comparable corpus) and JRC-Acquis (a parallel one), we show LRI to outperform (both in terms of effectiveness and efficiency) a number of previously proposed machine-translation-free and dictionary-free PLTC methods that we use as baselines.

Probabilistic inference algorithms such as Sequential Monte Carlo (SMC) provide powerful tools for constraining procedural models in computer graphics, but they require many samples to produce desirable results. In this paper, we show how to create procedural models which learn how to satisfy constraints. We augment procedural models with neural networks which control how the model makes random choices based on the output it has generated thus far. We call such models neurally-guided procedural models. As a pre-computation, we train these models to maximize the likelihood of example outputs generated via SMC. They are then used as efficient SMC importance samplers, generating high-quality results with very few samples. We evaluate our method on L-system-like models with image-based constraints. Given a desired quality threshold, neurally-guided models can generate satisfactory results up to 10x faster than unguided models.

The study of neurocognitive tasks requiring accurate localisation of activity often rely on functional Magnetic Resonance Imaging, a widely adopted technique that makes use of a pipeline of data processing modules, each involving a variety of parameters. These parameters are frequently set according to the local goal of each specific module, not accounting for the rest of the pipeline. Given recent success of neural network research in many different domains, we propose to convert the whole data pipeline into a deep neural network, where the parameters involved are jointly optimised by the network to best serve a common global goal. As a proof of concept, we develop a module able to adaptively apply the most suitable spatial smoothing to every brain volume for each specific neuroimaging task, and we validate its results in a standard brain decoding experiment.

We propose a flexible framework for spectral conversion (SC) that facilitates training with unaligned corpora. Many SC frameworks require parallel corpora, phonetic alignments, or explicit frame-wise correspondence for learning conversion functions or for synthesizing a target spectrum with the aid of alignments. However, these requirements gravely limit the scope of practical applications of SC due to scarcity or even unavailability of parallel corpora. We propose an SC framework based on variational auto-encoder which enables us to exploit non-parallel corpora. The framework comprises an encoder that learns speaker-independent phonetic representations and a decoder that learns to reconstruct the designated speaker. It removes the requirement of parallel corpora or phonetic alignments to train a spectral conversion system. We report objective and subjective evaluations to validate our proposed method and compare it to SC methods that have access to aligned corpora.

In this paper, we propose a dictionary update method for Nonnegative Matrix Factorization (NMF) with high dimensional data in a spectral conversion (SC) task. Voice conversion has been widely studied due to its potential applications such as personalized speech synthesis and speech enhancement. Exemplar-based NMF (ENMF) emerges as an effective and probably the simplest choice among all techniques for SC, as long as a source-target parallel speech corpus is given. ENMF-based SC systems usually need a large amount of bases (exemplars) to ensure the quality of the converted speech. However, a small and effective dictionary is desirable but hard to obtain via dictionary update, in particular when high-dimensional features such as STRAIGHT spectra are used. Therefore, we propose a dictionary update framework for NMF by means of an encoder-decoder reformulation. Regarding NMF as an encoder-decoder network makes it possible to exploit the whole parallel corpus more effectively and efficiently when applied to SC. Our experiments demonstrate significant gains of the proposed system with small dictionaries over conventional ENMF-based systems with dictionaries of same or much larger size.

We propose a novel kernel based post selection inference (PSI) algorithm, which can not only handle non-linearity in data but also structured output such as multi-dimensional and multi-label outputs. Specifically, we develop a PSI algorithm for independence measures, and propose the Hilbert-Schmidt Independence Criterion (HSIC) based PSI algorithm (hsicInf). The novelty of the proposed algorithm is that it can handle non-linearity and/or structured data through kernels. Namely, the proposed algorithm can be used for wider range of applications including nonlinear multi-class classification and multi-variate regressions, while existing PSI algorithms cannot handle them. Through synthetic experiments, we show that the proposed approach can find a set of statistically significant features for both regression and classification problems. Moreover, we apply the hsicInf algorithm to a real-world data, and show that hsicInf can successfully identify important features.

We introduce the localized Lasso, which is suited for learning models that are both interpretable and have a high predictive power in problems with high dimensionality $d$ and small sample size $n$. More specifically, we consider a function defined by local sparse models, one at each data point. We introduce sample-wise network regularization to borrow strength across the models, and sample-wise exclusive group sparsity (a.k.a., $\ell_{1,2}$ norm) to introduce diversity into the choice of feature sets in the local models. The local models are interpretable in terms of similarity of their sparsity patterns. The cost function is convex, and thus has a globally optimal solution. Moreover, we propose a simple yet efficient iterative least-squares based optimization procedure for the localized Lasso, which does not need a tuning parameter, and is guaranteed to converge to a globally optimal solution. The solution is empirically shown to outperform alternatives for both simulated and genomic personalized medicine data.

Speech Translation has always been about giving source text or audio input and waiting for system to give translated output in desired form. In this paper, we present the Acoustic Dialect Decoder (ADD) - a voice to voice ear-piece translation device. We introduce and survey the recent advances made in the field of Speech Engineering, to employ in the ADD, particularly focusing on the three major processing steps of Recognition, Translation and Synthesis. We tackle the problem of machine understanding of natural language by designing a recognition unit for source audio to text, a translation unit for source language text to target language text, and a synthesis unit for target language text to target language speech. Speech from the surroundings will be recorded by the recognition unit present on the ear-piece and translation will start as soon as one sentence is successfully read. This way, we hope to give translated output as and when input is being read. The recognition unit will use Hidden Markov Models (HMMs) Based Tool-Kit (HTK), hybrid RNN systems with gated memory cells, and the synthesis unit, HMM based speech synthesis system HTS. This system will initially be built as an English to Tamil translation device.

Beijing National Lab for Condensed Matter Physics and Institute of Physics, Chinese Academy of Sciences, Beijing 100190, China Despite their exceptional flexibility and popularity, the Monte Carlo methods often suffer from slow mixing times for challenging statistical physics problems. We present a general strategy to overcome this difficulty by adopting ideas and techniques from the machine learning community. We fit the unnormalized probability of the physical model to a feedforward neural network and reinterpret the architecture as a restricted Boltzmann machine. Then, exploiting its feature detection ability, we utilize the restricted Boltzmann machine for efficient Monte Carlo updates and to speed up the simulation of the original physical system. We implement these ideas for the Falicov-Kimball model and demonstrate improved acceptance ratio and autocorrelation time near the phase transition point. Monte Carlo method is one of the most flexible and powerful methods for studying many-body systems [1, 2]. Monte Carlo methods randomly sample configurations and obtain the answer as a statistical average.

Ever since the Affordable Care Act came to be, there has been a concerted effort to computerize health care, and this goal has come with wanted and unwanted effects on patient outcomes. For example, computerization is great when it comes to having accurate medical records or evaluating statistical outcomes, especially if the data entry is accurate. But there is also an underlying way of reliance on the use of computer technology to triage patient care, as well as directly help with the differential diagnoses and the recommendation of possible therapies for patients. When considering the relationship between human and digital MDs and the quality of patient care, I find a recent study by Harvard University research quite interesting. For one of the first times I've seen, we have some objective data that suggests humans in health care have a better understanding of the multitude of factors that need to be considered to make a diagnosis, and I hope that people in high places who are making decisions for our country get a chance to talk and evaluate this data.