Papers.

Dutch Blockchain Research Agenda

Digital Cookbook: How to ensure successful Digital Transformation

Data Cleaning Pocket Primer

Data Cleaning

BlazeIt: Fast Exploratory Video Queries using Neural Networks.

Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming

Training of deep learning models depends on gradient descent and end-to-end differentiation. Under the slogan of differentiable programming, there is an increasing demand for efficient automatic gradient computation for emerging network architectures that incorporate dynamic control flow, especially in NLP. In this paper we propose an implementation of backpropagation using functions with callbacks, where the forward pass is executed as a sequence of function calls, and the backward pass as a corresponding sequence of function returns. A key realization is that this technique of chaining callbacks is well known in the programming languages community as continuation-passing style (CPS). Any program can be converted to this form using standard techniques, and hence, any program can be mechanically converted to compute gradients. Our approach achieves the same flexibility as other reverse-mode automatic differentiation (AD) techniques, but it can be implemented without any auxiliary data structures besides the function call stack, and it can easily be combined with graph construction and native code generation techniques through forms of multi-stage programming, leading to a highly efficient implementation that combines the performance benefits of define-then-run software frameworks such as TensorFlow with the expressiveness of define-by-run frameworks such as PyTorch.

Are Blockchain and the Internet of Things Made for Each Other?

Approximability of Discriminators Implies Diversity in GANs.

Android pocket primer

Alluxio: A Virtual Distributed File System

Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations.

Algorithmic Framework for Model-based Reinforcement Learning with Theoretical Guarantees.

Accelerating the Machine Learning Lifecycle with MLflow

A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors.

360{\deg} Stance Detection

Remembering Our Future: The Frontier of Search Technologies

Remembering Our Future: The Frontier of Search Technologies

T2 Trainspotting’s obsession with the past says a lot about today

Session details: TempWeb'17: The 7th Temporal Web Analytics Workshop

Hi-WAY: Execution of Scientific Workflows on Hadoop YARN

Automatic Stylistic Composition of Bach Chorales with Deep LSTM

BachBot: a deep LSTM generative model for composing and completing chorales in the style of J.S. Bach, trained on the Riemenschneider chorale corpus, evaluated with a large-scale online musical Turing test in which participants distinguished BachBot completions from Bach originals only marginally better than chance.

Business Resiliency Framework for Enterprise Workloads in the Cloud

Businesses with enterprise-level workloads such as Systems Applications and Products (SAP) workloads require business level resiliency including high availability, clustering, or physical server appliances. To enable businesses to use enterprise workloads in a cloud, the IBM Cloud Managed Services (CMS) cloud offers many SAP enterprise-level workloads for both virtualized and non-virtualized cloud environments. Based on our experience with enabling resiliency for enterprise-level workloads like SAP and Oracle, we realize that as the end-to-end process is quite cumbersome, complex and expensive. Therefore, it would be highly beneficial for the customers and the cloud providers to have a systematic business resiliency framework in place, which would very well fit the cloud model with appropriate level of abstraction, automation, while allowing the desired cost benefits. In this paper, we introduce an end-to-end business resiliency framework and resiliency life cycle. We further introduce an algorithm to determine the optimal resiliency pattern for enterprise applications using a diverse set of platforms in the IBM CMS cloud

Unification of Compile-Time and Runtime Metaprogramming in Scala

Overcoming information asymmetry in patent pledge records

Transition to Agile Software Development in a Large-Scale Project : A Systems Analysis and Design Perspective

skimr: Compact and Flexible Summaries of Data

R package providing compact, flexible summary statistics for data frames; an rOpenSci unconf project co-authored by Arino de la Rubia.

Cold Fusion: Training Seq2Seq Models Together with Language Models

Sequence-to-sequence (Seq2Seq) models with attention have excelled at tasks which involve generating natural language sentences such as machine translation, image captioning and speech recognition. Performance has further been improved by leveraging unlabeled data, often in the form of a language model. In this work, we present the Cold Fusion method, which leverages a pre-trained language model during training, and show its effectiveness on the speech recognition task. We show that Seq2Seq models with Cold Fusion are able to better utilize language information enjoying i) faster convergence and better generalization, and ii) almost complete transfer to a new domain while using less than 10% of the labeled training data.

Key-Value Retrieval Networks for Task-Oriented Dialogue

Lithium NLP: A System for Rich Information Extraction from Noisy User Generated Text on Social Media

In this paper, we describe the Lithium Natural Language Processing (NLP) system - a resource-constrained, high-throughput and language-agnostic system for information extraction from noisy user generated text on social media. Lithium NLP extracts a rich set of information including entities, topics, hashtags and sentiment from text. We discuss several real world applications of the system currently incorporated in Lithium products. We also compare our system with existing commercial and academic NLP systems in terms of performance, information extracted and languages supported. We show that Lithium NLP is at par with and in some cases, outperforms state-of-the-art commercial NLP systems.

Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings

Learning a Neural Semantic Parser from User Feedback

Beyond Binary Labels: Political Ideology Prediction of Twitter Users

Automatic political preference prediction from social media posts has to date proven successful only in distinguishing between publicly declared liberals and conservatives in the US. This study examines users' political ideology using a sevenpoint scale which enables us to identify politically moderate and neutral usersgroups which are of particular interest to political scientists and pollsters. Using a novel data set with political ideology labels self-reported through surveys, our goal is two-fold: a) to characterize the political groups of users through language use on Twitter; b) to build a fine-grained model that predicts political ideology of unseen users. Our results identify differences in both political leaning and engagement and the extent to which each group tweets using political keywords. Finally, we demonstrate how to improve ideology prediction accuracy by exploiting the relationships between the user groups.

EmoNet: Fine-Grained Emotion Detection with Gated Recurrent Neural Networks

Accurate detection of emotion from natural language has applications ranging from building emotional chatbots to better understanding individuals and their lives. However, progress on emotion detection has been hampered by the absence of large labeled datasets. In this work, we build a very large dataset for fine-grained emotions and develop deep learning models on it. We achieve a new state-of-the-art on 24 fine-grained types of emotions (with an average accuracy of 87.58%). We also extend the task beyond emotion types to model Robert Plutchik's 8 primary emotion dimensions, acquiring a superior accuracy of 95.68%.

Discriminative Information Retrieval for Question Answering Sentence Selection

We propose a framework for discriminative IR atop linguistic features, trained to improve the recall of answer candidate passage retrieval, the initial step in text-based question answering. We formalize this as an instance of linear feature-based IR, demonstrating a 34%-43% improvement in recall for candidate triage for QA.

A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue

Entity Linking via Joint Encoding of Types, Descriptions, and Context

For accurate entity linking, we need to capture various information aspects of an entity, such as its description in a KB, contexts in which it is mentioned, and structured knowledge. Additionally, a linking system should work on texts from different domains without requiring domain-specific training data or hand-engineered features. In this work we present a neural, modular entity linking system that learns a unified dense representation for each entity using multiple sources of information, such as its description, contexts around its mentions, and its fine-grained types. We show that the resulting entity linking system is effective at combining these sources, and performs competitively, sometimes out-performing current state-of-the-art systems across datasets, without requiring any domain-specific training data or hand-engineered features. We also show that our model can effectively “embed” entities that are new to the KB, and is able to link its mentions accurately.

Adversarial Training for Relation Extraction

Adversarial training is a mean of regularizing classification algorithms by generating adversarial noise to the training data. We apply adversarial training in relation extraction within the multi-instance multi-label learning framework. We evaluate various neural network architectures on two different datasets. Experimental results demonstrate that adversarial training is generally effective for both CNN and RNN models and significantly improves the precision of predicted relations.

Neural Semantic Parsing with Type Constraints for Semi-Structured Tables

Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge

Laws for Creating Trust in the Blockchain Age

Dhalion: Self-Regulating Stream Processing in Heron

NoScope

Burden of neurological diseases in the US revealed by web searches

Quantification of transplant-derived circulating cell-free DNA in absence of a donor genotype

Intonation as a disease marker in behavioral variant Frontotemporal Degeneration (P4.186)

Automatic measurement of prosody in behavioral variant FTD

Linguistic camouflage in girls with autism spectrum disorder

Classifying Twitter Topic-Networks Using Social Network Analysis

Smartphone-based “Geofencing” to Ascertain Hospitalizations

Etching Methods for STT-MRAM