Papers.

Chinese TIMIT: A TIMIT-like corpus of standard Chinese

Analyzing Users’ Sentiment Towards Popular Consumer Industries and Brands on Twitter

Social media serves as a unified platform for users to express their thoughts on subjects ranging from their daily lives to their opinion on consumer brands and products. These users wield an enormous influence in shaping the opinions of other consumers and influence brand perception, brand loyalty and brand advocacy. In this paper, we analyze the opinion of 19M Twitter users towards 62 popular industries, encompassing 12,898 enterprise and consumer brands, as well as associated subject matter topics, via sentiment analysis of 330M tweets over a period spanning a month. We find that users tend to be most positive towards manufacturing and most negative towards service industries. In addition, they tend to be more positive or negative when interacting with brands than generally on Twitter. We also find that sentiment towards brands within an industry varies greatly and we demonstrate this using two industries as use cases. In addition, we discover that there is no strong correlation between topic sentiments of different industries, demonstrating that topic sentiments are highly dependent on the context of the industry that they are mentioned in. We demonstrate the value of such an analysis in order to assess the impact of brands on social media. We hope that this initial study will prove valuable for both researchers and companies in understanding users' perception of industries, brands and associated topics and encourage more research in this field.

Twitter Heron: Towards Extensible Streaming Engines

KeystoneML: Optimizing Pipelines for Large-Scale Advanced Analytics

Hopsworks: Improving User Experience and Development on Hadoop with Scalable, Strongly Consistent Metadata

Dela - Sharing Large Datasets between Hadoop Clusters

Fast and Flexible Networking for Message-Oriented Middleware

Robust Speech Recognition Using Generative Adversarial Networks

This paper describes a general, scalable, end-to-end framework that uses the generative adversarial network (GAN) objective to enable robust speech recognition. Encoders trained with the proposed approach enjoy improved invariance by learning to map noisy audio to the same embedding space as that of clean audio. Unlike previous methods, the new framework does not rely on domain expertise or simplifying assumptions as are often needed in signal processing, and directly encourages robustness in a data-driven way. We show the new approach improves simulated far-field speech recognition of vanilla sequence-to-sequence models without specialized front-ends or preprocessing.

Tensor Contraction Layers for Parsimonious Deep Nets

Tensors offer a natural representation for many kinds of data frequently encountered in machine learning. Images, for example, are naturally represented as third order tensors, where the modes correspond to height, width, and channels. In particular, tensor decompositions are noted for their ability to discover multi-dimensional dependencies and produce compact low-rank approximations of data. In this paper, we explore the use of tensor contractions as neural network layers and investigate several ways to apply them to activation tensors. Specifically, we propose the Tensor Contraction Layer (TCL), the first attempt to incorporate tensor contractions as end-to-end trainable neural network layers. Applied to existing networks, TCLs reduce the dimensionality of the activation tensors and thus the number of model parameters. We evaluate the TCL on the task of image recognition, augmenting popular networks (AlexNet, VGG). The resulting models are trainable end-to-end. We evaluate TCL's performance on the task of image recognition, using the CIFAR100 and ImageNet datasets, studying the effect of parameter reduction via tensor contraction on performance. We demonstrate significant model compression without significant impact on the accuracy and, in some cases, improved performance.

GAGAN: Geometry-Aware Generative Adversarial Networks

Deep generative models learned through adversarial training have become increasingly popular for their ability to generate naturalistic image textures. However, aside from their texture, the visual appearance of objects is significantly influenced by their shape geometry; information which is not taken into account by existing generative models. This paper introduces the Geometry-Aware Generative Adversarial Networks (GAGAN) for incorporating geometric information into the image generation process. Specifically, in GAGAN the generator samples latent variables from the probability space of a statistical shape model. By mapping the output of the generator to a canonical coordinate frame through a differentiable geometric transformation, we enforce the geometry of the objects and add an implicit connection from the prior to the generated object. Experimental results on face generation indicate that the GAGAN can generate realistic images of faces with arbitrary facial attributes such as facial expression, pose, and morphology, that are of better quality than current GAN-based methods. Our method can be used to augment any existing GAN architecture and improve the quality of the images generated.

Xception: Deep Learning with Depthwise Separable Convolutions

We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution). In this light, a depthwise separable convolution can be understood as an Inception module with a maximally large number of towers. This observation leads us to propose a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with depthwise separable convolutions. We show that this architecture, dubbed Xception, slightly outperforms Inception V3 on the ImageNet dataset (which Inception V3 was designed for), and significantly outperforms Inception V3 on a larger image classification dataset comprising 350 million images and 17,000 classes. Since the Xception architecture has the same number of parameters as Inception V3, the performance gains are not due to increased capacity but rather to a more efficient use of model parameters.

Scaling HDFS to more than 1 million operations per second with HopsFS

Continuous integration platform for Arduino embedded software.

Unifying the open big data world: The possibilities of Apache BEAM

Semantic search (invited talk)

Quality-efficiency trade-offs in machine learning for text processing

Exploring Neural Transducers for End-to-End Speech Recognition

In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition. We show that, without any language model, Seq2Seq and RNN-Transducer models both outperform the best reported CTC models with a language model, on the popular Hub5'00 benchmark. On our internal diverse dataset, these trends continue - RNNTransducer models rescored with a language model after beam search outperform our best CTC models. These results simplify the speech recognition pipeline so that decoding can now be expressed purely as neural network operations. We also study how the choice of encoder architecture affects the performance of the three models - when all encoder layers are forward only, and when encoders downsample the input representation aggressively.

Comparison of Memory Thresholds for Planar Qudit Geometries

Improved genome assembly of American alligator genome reveals conserved architecture of estrogen signaling

Evolution and clinical impact of genetic epistasis within EGFR-mutant lung cancers

Humans are colonized by many uncharacterized and highly divergent microbes

Formalizing drug indications on the road to therapeutic intent

E-Science technologies in a workflow for personalized medicine using cancer screening as a case study

Soliciting and Responding to Patients' Questions about Diabetes Through Online Sources

Numerous uncharacterized and highly divergent microbes which colonize humans are revealed by circulating cell-free DNA

Geometric explanation of the rich-club phenomenon in complex networks

The rich club organization (the presence of highly connected hub core in a network) influences many structural and functional characteristics of networks including topology, the efficiency of paths and distribution of load. Despite its major role, the literature contains only a very limited set of models capable of generating networks with realistic rich club structure. One possible reason is that the rich club organization is a divisive property among complex networks which exhibit great diversity, in contrast to other metrics (e.g. diameter, clustering or degree distribution) which seem to behave very similarly across many networks. Here we propose a simple yet powerful geometry-based growing model which can generate realistic complex networks with high rich club diversity by controlling a single geometric parameter. The growing model is validated against the Internet, protein-protein interaction, airport and power grid networks.

Evolution and clinical impact of co-occurring genetic alterations in advanced-stage EGFR-mutant lung cancers

Toil enables reproducible, open source, big biomedical data analyses

Supporting process execution by interdisciplinary healthcare teams: Middleware design for IBM BPM

Abstract Interdisciplinary healthcare teams (IHTs) are involved in clinical processes composed of tasks requiring specific capabilities from different disciplines, often executed at different times. Although some hospitals use Business Process Management (BPM) suites to support their clinical activities, these tools are often unable to support the dynamic and capability-based allocation of tasks to the most suitable practitioner during the execution of a given process. Extensions, such as our previous work on ontological frameworks, exist that enable reasoning about IHT dynamics and allocate tasks to practitioners on the fly, but they are either unable to interact with commercial BPM suites or they are tightly integrated to one specific BPM suite. This paper contributes an innovative BPM-oriented middleware that enables existing BPM suites to interact with a semantic layer, hence offering more opportunities for deploying such advanced functionality in healthcare organizations. As a proof of concept, the middleware implementation is connected to a specific semantic layer and a specific commercial BPM suite (from IBM). The resulting system is illustrated with an acute stroke management process, hence demonstrating the feasibility of the proposed middleware-based approach. This solution compares advantageously against related work.

A machine learning approach for result caching in web search engines

AFEW-VA database for valence and arousal estimation in-the-wild

TrustChain: A Sybil-resistant scalable blockchain

Detecting depression and mental illness on social media: an integrative review

Foreword

Architecting to Deliver Value From a Big Data and Hybrid Cloud Architecture

Mapping a Twitter scholarly communication network: a case of the association of internet researchers’ conference

Privacy-preserving detection of anomalous phenomena in crowdsourced environmental sensing using fine-grained weighted voting

Model-Based Design and Automated Validation of ARINC653 Architectures Using the AADL

On Chomsky and the Two Cultures of Statistical Learning

Improving Authenticated Dynamic Dictionaries, with Applications to Cryptocurrencies

Revisiting Difficulty Control for Blockchain Systems

Computationally Efficient Cardiac Views Projection Using 3D Convolutional Neural Networks

4D Flow is an MRI sequence which allows acquisition of 3D images of the heart. The data is typically acquired volumetrically, so it must be reformatted to generate cardiac long axis and short axis views for diagnostic interpretation. These views may be generated by placing 6 landmarks: the left and right ventricle apex, and the aortic, mitral, pulmonary, and tricuspid valves. In this paper, we propose an automatic method to localize landmarks in order to compute the cardiac views. Our approach consists of first calculating a bounding box that tightly crops the heart, followed by a landmark localization step within this bounded region. Both steps are based on a 3D extension of the recently introduced ENet. We demonstrate that the long and short axis projections computed with our automated method are of equivalent quality to projections created with landmarks placed by an experienced cardiac radiologist, based on a blinded test administered to a different cardiac radiologist.

What HLT Can Do for You (and Vice Versa)

Applying Human Language Technology in Survey Research

AdBench: A Complete Benchmark for Modern Data Pipelines

EuroVoc-Based Summarization of European Case Law.

Structured Text Retrieval Models

Combining Online Maps with Text Analysis

NodeXL

Topic Compositional Neural Language Model

We propose a Topic Compositional Neural Language Model (TCNLM), a novel method designed to simultaneously capture both the global semantic meaning and the local word ordering structure in a document. The TCNLM learns the global semantic coherence of a document via a neural topic model, and the probability of each learned latent topic is further used to build a Mixture-of-Experts (MoE) language model, where each expert (corresponding to one topic) is a recurrent neural network (RNN) that accounts for learning the local structure of a word sequence. In order to train the MoE model efficiently, a matrix factorization method is applied, by extending each weight matrix of the RNN to be an ensemble of topic-dependent weight matrices. The degree to which each member of the ensemble is used is tied to the document-dependent probability of the corresponding topics. Experimental results on several corpora show that the proposed approach outperforms both a pure RNN-based model and other topic-guided language models. Further, our model yields sensible topics, and also has the capacity to generate meaningful sentences conditioned on given topics.