July 29, 2019

2981 words 14 mins read

Paper Group ANR 130

Do Reichenbachian Common Cause Systems of Arbitrary Finite Size Exist?. Improving coreference resolution with automatically predicted prosodic information. An Interactive Tool for Natural Language Processing on Clinical Text. Fast Modeling Methods for Complex System with Separable Features. End-to-End Multi-View Lipreading. Experience-based Optimiz …

Do Reichenbachian Common Cause Systems of Arbitrary Finite Size Exist?


Title	Do Reichenbachian Common Cause Systems of Arbitrary Finite Size Exist?
Authors	Claudio Mazzola, Peter Evans
Abstract	The principle of common cause asserts that positive correlations between causally unrelated events ought to be explained through the action of some shared causal factors. Reichenbachian common cause systems are probabilistic structures aimed at accounting for cases where correlations of the aforesaid sort cannot be explained through the action of a single common cause. The existence of Reichenbachian common cause systems of arbitrary finite size for each pair of non-causally correlated events was allegedly demonstrated by Hofer-Szab'o and R'edei in 2006. This paper shows that their proof is logically deficient, and we propose an improved proof.
Tasks
Published	2017-02-28
URL	http://arxiv.org/abs/1703.00352v1
PDF	http://arxiv.org/pdf/1703.00352v1.pdf
PWC	https://paperswithcode.com/paper/do-reichenbachian-common-cause-systems-of
Repo
Framework

Improving coreference resolution with automatically predicted prosodic information


Title	Improving coreference resolution with automatically predicted prosodic information
Authors	Ina Rösiger, Sabrina Stehwien, Arndt Riester, Ngoc Thang Vu
Abstract	Adding manually annotated prosodic information, specifically pitch accents and phrasing, to the typical text-based feature set for coreference resolution has previously been shown to have a positive effect on German data. Practical applications on spoken language, however, would rely on automatically predicted prosodic information. In this paper we predict pitch accents (and phrase boundaries) using a convolutional neural network (CNN) model from acoustic features extracted from the speech signal. After an assessment of the quality of these automatic prosodic annotations, we show that they also significantly improve coreference resolution.
Tasks	Coreference Resolution
Published	2017-07-28
URL	http://arxiv.org/abs/1707.09231v1
PDF	http://arxiv.org/pdf/1707.09231v1.pdf
PWC	https://paperswithcode.com/paper/improving-coreference-resolution-with
Repo
Framework

An Interactive Tool for Natural Language Processing on Clinical Text


Title	An Interactive Tool for Natural Language Processing on Clinical Text
Authors	Gaurav Trivedi, Phuong Pham, Wendy Chapman, Rebecca Hwa, Janyce Wiebe, Harry Hochheiser
Abstract	Natural Language Processing (NLP) systems often make use of machine learning techniques that are unfamiliar to end-users who are interested in analyzing clinical records. Although NLP has been widely used in extracting information from clinical text, current systems generally do not support model revision based on feedback from domain experts. We present a prototype tool that allows end users to visualize and review the outputs of an NLP system that extracts binary variables from clinical text. Our tool combines multiple visualizations to help the users understand these results and make any necessary corrections, thus forming a feedback loop and helping improve the accuracy of the NLP models. We have tested our prototype in a formative think-aloud user study with clinicians and researchers involved in colonoscopy research. Results from semi-structured interviews and a System Usability Scale (SUS) analysis show that the users are able to quickly start refining NLP models, despite having very little or no experience with machine learning. Observations from these sessions suggest revisions to the interface to better support review workflow and interpretation of results.
Tasks
Published	2017-07-06
URL	http://arxiv.org/abs/1707.01890v2
PDF	http://arxiv.org/pdf/1707.01890v2.pdf
PWC	https://paperswithcode.com/paper/an-interactive-tool-for-natural-language
Repo
Framework

Fast Modeling Methods for Complex System with Separable Features


Title	Fast Modeling Methods for Complex System with Separable Features
Authors	Chen Chen, Changtong Luo, Zonglin Jiang
Abstract	Data-driven modeling plays an increasingly important role in different areas of engineering. For most of existing methods, such as genetic programming (GP), the convergence speed might be too slow for large scale problems with a large number of variables. Fortunately, in many applications, the target models are separable in some sense. In this paper, we analyze different types of separability of some real-world engineering equations and establish a mathematical model of generalized separable system (GS system). In order to get the structure of the GS system, two concepts, namely block and factor are introduced, and a special method, block and factor detection is also proposed, in which the target model is decomposed into a number of blocks, further into minimal blocks and factors. Compare to the conventional GP, the new method can make large reductions to the search space. The minimal blocks and factors are optimized and assembled with a global optimization search engine, low dimensional simplex evolution (LDSE). An extensive study between the proposed method and a state-of-the-art data-driven fitting tool, Eureqa, has been presented with several man-made problems. Test results indicate that the proposed method is more effective and efficient under all the investigated cases.
Tasks
Published	2017-08-05
URL	http://arxiv.org/abs/1708.04583v1
PDF	http://arxiv.org/pdf/1708.04583v1.pdf
PWC	https://paperswithcode.com/paper/fast-modeling-methods-for-complex-system-with
Repo
Framework

End-to-End Multi-View Lipreading


Title	End-to-End Multi-View Lipreading
Authors	Stavros Petridis, Yujiang Wang, Zuwei Li, Maja Pantic
Abstract	Non-frontal lip views contain useful information which can be used to enhance the performance of frontal view lipreading. However, the vast majority of recent lipreading works, including the deep learning approaches which significantly outperform traditional approaches, have focused on frontal mouth images. As a consequence, research on joint learning of visual features and speech classification from multiple views is limited. In this work, we present an end-to-end multi-view lipreading system based on Bidirectional Long-Short Memory (BLSTM) networks. To the best of our knowledge, this is the first model which simultaneously learns to extract features directly from the pixels and performs visual speech classification from multiple views and also achieves state-of-the-art performance. The model consists of multiple identical streams, one for each view, which extract features directly from different poses of mouth images. The temporal dynamics in each stream/view are modelled by a BLSTM and the fusion of multiple streams/views takes place via another BLSTM. An absolute average improvement of 3% and 3.8% over the frontal view performance is reported on the OuluVS2 database when the best two (frontal and profile) and three views (frontal, profile, 45) are combined, respectively. The best three-view model results in a 10.5% absolute improvement over the current multi-view state-of-the-art performance on OuluVS2, without using external databases for training, achieving a maximum classification accuracy of 96.9%.
Tasks	Lipreading
Published	2017-09-01
URL	http://arxiv.org/abs/1709.00443v1
PDF	http://arxiv.org/pdf/1709.00443v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-multi-view-lipreading
Repo
Framework

Experience-based Optimization: A Coevolutionary Approach


Title	Experience-based Optimization: A Coevolutionary Approach
Authors	Shengcai Liu, Ke Tang, Xin Yao
Abstract	This paper studies improving solvers based on their past solving experiences, and focuses on improving solvers by offline training. Specifically, the key issues of offline training methods are discussed, and research belonging to this category but from different areas are reviewed in a unified framework. Existing training methods generally adopt a two-stage strategy in which selecting the training instances and training instances are treated in two independent phases. This paper proposes a new training method, dubbed LiangYi, which addresses these two issues simultaneously. LiangYi includes a training module for a population-based solver and an instance sampling module for updating the training instances. The idea behind LiangYi is to promote the population-based solver by training it (with the training module) to improve its performance on those instances (discovered by the sampling module) on which it performs badly, while keeping the good performances obtained by it on previous instances. An instantiation of LiangYi on the Travelling Salesman Problem is also proposed. Empirical results on a huge testing set containing 10000 instances showed LiangYi could train solvers that perform significantly better than the solvers trained by other state-of-the-art training method. Moreover, empirical investigation of the behaviours of LiangYi confirmed it was able to continuously improve the solver through training.
Tasks
Published	2017-03-29
URL	http://arxiv.org/abs/1703.09865v2
PDF	http://arxiv.org/pdf/1703.09865v2.pdf
PWC	https://paperswithcode.com/paper/experience-based-optimization-a
Repo
Framework

Improving drug sensitivity predictions in precision medicine through active expert knowledge elicitation


Title	Improving drug sensitivity predictions in precision medicine through active expert knowledge elicitation
Authors	Iiris Sundin, Tomi Peltola, Muntasir Mamun Majumder, Pedram Daee, Marta Soare, Homayun Afrabandpey, Caroline Heckman, Samuel Kaski, Pekka Marttinen
Abstract	Predicting the efficacy of a drug for a given individual, using high-dimensional genomic measurements, is at the core of precision medicine. However, identifying features on which to base the predictions remains a challenge, especially when the sample size is small. Incorporating expert knowledge offers a promising alternative to improve a prediction model, but collecting such knowledge is laborious to the expert if the number of candidate features is very large. We introduce a probabilistic model that can incorporate expert feedback about the impact of genomic measurements on the sensitivity of a cancer cell for a given drug. We also present two methods to intelligently collect this feedback from the expert, using experimental design and multi-armed bandit models. In a multiple myeloma blood cancer data set (n=51), expert knowledge decreased the prediction error by 8%. Furthermore, the intelligent approaches can be used to reduce the workload of feedback collection to less than 30% on average compared to a naive approach.
Tasks
Published	2017-05-09
URL	http://arxiv.org/abs/1705.03290v1
PDF	http://arxiv.org/pdf/1705.03290v1.pdf
PWC	https://paperswithcode.com/paper/improving-drug-sensitivity-predictions-in
Repo
Framework

Variational Gaussian Dropout is not Bayesian


Title	Variational Gaussian Dropout is not Bayesian
Authors	Jiri Hron, Alexander G. de G. Matthews, Zoubin Ghahramani
Abstract	Gaussian multiplicative noise is commonly used as a stochastic regularisation technique in training of deterministic neural networks. A recent paper reinterpreted the technique as a specific algorithm for approximate inference in Bayesian neural networks; several extensions ensued. We show that the log-uniform prior used in all the above publications does not generally induce a proper posterior, and thus Bayesian inference in such models is ill-posed. Independent of the log-uniform prior, the correlated weight noise approximation has further issues leading to either infinite objective or high risk of overfitting. The above implies that the reported sparsity of obtained solutions cannot be explained by Bayesian or the related minimum description length arguments. We thus study the objective from a non-Bayesian perspective, provide its previously unknown analytical form which allows exact gradient evaluation, and show that the later proposed additive reparametrisation introduces minima not present in the original multiplicative parametrisation. Implications and future research directions are discussed.
Tasks	Bayesian Inference
Published	2017-11-08
URL	http://arxiv.org/abs/1711.02989v1
PDF	http://arxiv.org/pdf/1711.02989v1.pdf
PWC	https://paperswithcode.com/paper/variational-gaussian-dropout-is-not-bayesian
Repo
Framework

An Optimized Union-Find Algorithm for Connected Components Labeling Using GPUs


Title	An Optimized Union-Find Algorithm for Connected Components Labeling Using GPUs
Authors	Jun Chen, Qiang Yao, Houari Sabirin, Keisuke Nonaka, Hiroshi Sankoh, Sei Naito
Abstract	In this paper, we report an optimized union-find (UF) algorithm that can label the connected components on a 2D image efficiently by employing the GPU architecture. The proposed method contains three phases: UF-based local merge, boundary analysis, and link. The coarse labeling in local merge reduces the number atomic operations, while the boundary analysis only manages the pixels on the boundary of each block. Evaluation results showed that the proposed algorithm speed up the average running time by more than 1.3X.
Tasks
Published	2017-08-28
URL	http://arxiv.org/abs/1708.08180v2
PDF	http://arxiv.org/pdf/1708.08180v2.pdf
PWC	https://paperswithcode.com/paper/an-optimized-union-find-algorithm-for
Repo
Framework

More cat than cute? Interpretable Prediction of Adjective-Noun Pairs


Title	More cat than cute? Interpretable Prediction of Adjective-Noun Pairs
Authors	Delia Fernandez, Alejandro Woodward, Victor Campos, Xavier Giro-i-Nieto, Brendan Jou, Shih-Fu Chang
Abstract	The increasing availability of affect-rich multimedia resources has bolstered interest in understanding sentiment and emotions in and from visual content. Adjective-noun pairs (ANP) are a popular mid-level semantic construct for capturing affect via visually detectable concepts such as “cute dog” or “beautiful landscape”. Current state-of-the-art methods approach ANP prediction by considering each of these compound concepts as individual tokens, ignoring the underlying relationships in ANPs. This work aims at disentangling the contributions of the `adjectives' and` nouns’ in the visual prediction of ANPs. Two specialised classifiers, one trained for detecting adjectives and another for nouns, are fused to predict 553 different ANPs. The resulting ANP prediction model is more interpretable as it allows us to study contributions of the adjective and noun components. Source code and models are available at https://imatge-upc.github.io/affective-2017-musa2/ .
Tasks
Published	2017-08-21
URL	http://arxiv.org/abs/1708.06039v1
PDF	http://arxiv.org/pdf/1708.06039v1.pdf
PWC	https://paperswithcode.com/paper/more-cat-than-cute-interpretable-prediction
Repo
Framework

On Using Backpropagation for Speech Texture Generation and Voice Conversion


Title	On Using Backpropagation for Speech Texture Generation and Voice Conversion
Authors	Jan Chorowski, Ron J. Weiss, Rif A. Saurous, Samy Bengio
Abstract	Inspired by recent work on neural network image generation which rely on backpropagation towards the network inputs, we present a proof-of-concept system for speech texture synthesis and voice conversion based on two mechanisms: approximate inversion of the representation learned by a speech recognition neural network, and on matching statistics of neuron activations between different source and target utterances. Similar to image texture synthesis and neural style transfer, the system works by optimizing a cost function with respect to the input waveform samples. To this end we use a differentiable mel-filterbank feature extraction pipeline and train a convolutional CTC speech recognition network. Our system is able to extract speaker characteristics from very limited amounts of target speaker data, as little as a few seconds, and can be used to generate realistic speech babble or reconstruct an utterance in a different voice.
Tasks	Image Generation, Speech Recognition, Style Transfer, Texture Synthesis, Voice Conversion
Published	2017-12-22
URL	http://arxiv.org/abs/1712.08363v2
PDF	http://arxiv.org/pdf/1712.08363v2.pdf
PWC	https://paperswithcode.com/paper/on-using-backpropagation-for-speech-texture
Repo
Framework

Modeling Semantic Relatedness using Global Relation Vectors


Title	Modeling Semantic Relatedness using Global Relation Vectors
Authors	Shoaib Jameel, Zied Bouraoui, Steven Schockaert
Abstract	Word embedding models such as GloVe rely on co-occurrence statistics from a large corpus to learn vector representations of word meaning. These vectors have proven to capture surprisingly fine-grained semantic and syntactic information. While we may similarly expect that co-occurrence statistics can be used to capture rich information about the relationships between different words, existing approaches for modeling such relationships have mostly relied on manipulating pre-trained word vectors. In this paper, we introduce a novel method which directly learns relation vectors from co-occurrence statistics. To this end, we first introduce a variant of GloVe, in which there is an explicit connection between word vectors and PMI weighted co-occurrence vectors. We then show how relation vectors can be naturally embedded into the resulting vector space.
Tasks
Published	2017-11-14
URL	http://arxiv.org/abs/1711.05294v1
PDF	http://arxiv.org/pdf/1711.05294v1.pdf
PWC	https://paperswithcode.com/paper/modeling-semantic-relatedness-using-global
Repo
Framework

HitFraud: A Broad Learning Approach for Collective Fraud Detection in Heterogeneous Information Networks


Title	HitFraud: A Broad Learning Approach for Collective Fraud Detection in Heterogeneous Information Networks
Authors	Bokai Cao, Mia Mao, Siim Viidu, Philip S. Yu
Abstract	On electronic game platforms, different payment transactions have different levels of risk. Risk is generally higher for digital goods in e-commerce. However, it differs based on product and its popularity, the offer type (packaged game, virtual currency to a game or subscription service), storefront and geography. Existing fraud policies and models make decisions independently for each transaction based on transaction attributes, payment velocities, user characteristics, and other relevant information. However, suspicious transactions may still evade detection and hence we propose a broad learning approach leveraging a graph based perspective to uncover relationships among suspicious transactions, i.e., inter-transaction dependency. Our focus is to detect suspicious transactions by capturing common fraudulent behaviors that would not be considered suspicious when being considered in isolation. In this paper, we present HitFraud that leverages heterogeneous information networks for collective fraud detection by exploring correlated and fast evolving fraudulent behaviors. First, a heterogeneous information network is designed to link entities of interest in the transaction database via different semantics. Then, graph based features are efficiently discovered from the network exploiting the concept of meta-paths, and decisions on frauds are made collectively on test instances. Experiments on real-world payment transaction data from Electronic Arts demonstrate that the prediction performance is effectively boosted by HitFraud with fast convergence where the computation of meta-path based features is largely optimized. Notably, recall can be improved up to 7.93% and F-score 4.62% compared to baselines.
Tasks	Fraud Detection
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04129v2
PDF	http://arxiv.org/pdf/1709.04129v2.pdf
PWC	https://paperswithcode.com/paper/hitfraud-a-broad-learning-approach-for
Repo
Framework

Evaluating Discourse Phenomena in Neural Machine Translation


Title	Evaluating Discourse Phenomena in Neural Machine Translation
Authors	Rachel Bawden, Rico Sennrich, Alexandra Birch, Barry Haddow
Abstract	For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally evaluated with standard automatic metrics, poorly adapted to evaluating discourse phenomena. In this article, we present hand-crafted, discourse test sets, designed to test the models’ ability to exploit previous source and target sentences. We investigate the performance of recently proposed multi-encoder NMT models trained on subtitles for English to French. We also explore a novel way of exploiting context from the previous sentence. Despite gains using BLEU, multi-encoder models give limited improvement in the handling of discourse phenomena: 50% accuracy on our coreference test set and 53.5% for coherence/cohesion (compared to a non-contextual baseline of 50%). A simple strategy of decoding the concatenation of the previous and current sentence leads to good performance, and our novel strategy of multi-encoding and decoding of two sentences leads to the best performance (72.5% for coreference and 57% for coherence/cohesion), highlighting the importance of target-side context.
Tasks	Machine Translation
Published	2017-11-01
URL	http://arxiv.org/abs/1711.00513v3
PDF	http://arxiv.org/pdf/1711.00513v3.pdf
PWC	https://paperswithcode.com/paper/evaluating-discourse-phenomena-in-neural
Repo
Framework

Teaching a Machine to Read Maps with Deep Reinforcement Learning


Title	Teaching a Machine to Read Maps with Deep Reinforcement Learning
Authors	Gino Brunner, Oliver Richter, Yuyi Wang, Roger Wattenhofer
Abstract	The ability to use a 2D map to navigate a complex 3D environment is quite remarkable, and even difficult for many humans. Localization and navigation is also an important problem in domains such as robotics, and has recently become a focus of the deep reinforcement learning community. In this paper we teach a reinforcement learning agent to read a map in order to find the shortest way out of a random maze it has never seen before. Our system combines several state-of-the-art methods such as A3C and incorporates novel elements such as a recurrent localization cell. Our agent learns to localize itself based on 3D first person images and an approximate orientation angle. The agent generalizes well to bigger mazes, showing that it learned useful localization and navigation capabilities.
Tasks
Published	2017-11-20
URL	http://arxiv.org/abs/1711.07479v1
PDF	http://arxiv.org/pdf/1711.07479v1.pdf
PWC	https://paperswithcode.com/paper/teaching-a-machine-to-read-maps-with-deep
Repo
Framework