January 28, 2020

2889 words 14 mins read

Paper Group ANR 1022

An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extraction. A Maximum Entropy approach to Massive Graph Spectra. Continuous Speech Recognition using EEG and Video. Combining Deep Learning and Model-Based Methods for Robust Real-Time Semantic Landmark Detection. Coercing Machine Learning to Output Physically …

An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extraction


Title	An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extraction
Authors	Wang Chen, Hou Pong Chan, Piji Li, Lidong Bing, Irwin King
Abstract	In this paper, we present a novel integrated approach for keyphrase generation (KG). Unlike previous works which are purely extractive or generative, we first propose a new multi-task learning framework that jointly learns an extractive model and a generative model. Besides extracting keyphrases, the output of the extractive model is also employed to rectify the copy probability distribution of the generative model, such that the generative model can better identify important contents from the given document. Moreover, we retrieve similar documents with the given document from training data and use their associated keyphrases as external knowledge for the generative model to produce more accurate keyphrases. For further exploiting the power of extraction and retrieval, we propose a neural-based merging module to combine and re-rank the predicted keyphrases from the enhanced generative model, the extractive model, and the retrieved keyphrases. Experiments on the five KG benchmarks demonstrate that our integrated approach outperforms the state-of-the-art methods.
Tasks	Multi-Task Learning
Published	2019-04-06
URL	http://arxiv.org/abs/1904.03454v1
PDF	http://arxiv.org/pdf/1904.03454v1.pdf
PWC	https://paperswithcode.com/paper/an-integrated-approach-for-keyphrase
Repo
Framework

A Maximum Entropy approach to Massive Graph Spectra


Title	A Maximum Entropy approach to Massive Graph Spectra
Authors	Diego Granziol, Robin Ru, Stefan Zohren, Xiaowen Dong, Michael Osborne, Stephen Roberts
Abstract	Graph spectral techniques for measuring graph similarity, or for learning the cluster number, require kernel smoothing. The choice of kernel function and bandwidth are typically chosen in an ad-hoc manner and heavily affect the resulting output. We prove that kernel smoothing biases the moments of the spectral density. We propose an information theoretically optimal approach to learn a smooth graph spectral density, which fully respects the moment information. Our method’s computational cost is linear in the number of edges, and hence can be applied to large networks, with millions of nodes. We apply our method to the problems to graph similarity and cluster number learning, where we outperform comparable iterative spectral approaches on synthetic and real graphs.
Tasks	Graph Similarity
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09068v1
PDF	https://arxiv.org/pdf/1912.09068v1.pdf
PWC	https://paperswithcode.com/paper/a-maximum-entropy-approach-to-massive-graph
Repo
Framework

Continuous Speech Recognition using EEG and Video


Title	Continuous Speech Recognition using EEG and Video
Authors	Gautam Krishna, Mason Carnahan, Co Tran, Ahmed H Tewfik
Abstract	In this paper we investigate whether electroencephalography (EEG) features can be used to improve the performance of continuous visual speech recognition systems. We implemented a connectionist temporal classification (CTC) based end-to-end automatic speech recognition (ASR) model for performing recognition. Our results demonstrate that EEG features are helpful in enhancing the performance of continuous visual speech recognition systems.
Tasks	EEG, Speech Recognition, Visual Speech Recognition
Published	2019-12-16
URL	https://arxiv.org/abs/1912.07730v5
PDF	https://arxiv.org/pdf/1912.07730v5.pdf
PWC	https://paperswithcode.com/paper/continuous-speech-recognition-using-eeg-and
Repo
Framework

Combining Deep Learning and Model-Based Methods for Robust Real-Time Semantic Landmark Detection


Title	Combining Deep Learning and Model-Based Methods for Robust Real-Time Semantic Landmark Detection
Authors	Benjamin Naujoks, Patrick Burger, Hans-Joachim Wuensche
Abstract	Compared to abstract features, significant objects, so-called landmarks, are a more natural means for vehicle localization and navigation, especially in challenging unstructured environments. The major challenge is to recognize landmarks in various lighting conditions and changing environment (growing vegetation) while only having few training samples available. We propose a new method which leverages Deep Learning as well as model-based methods to overcome the need of a large data set. Using RGB images and light detection and ranging (LiDAR) point clouds, our approach combines state-of-the-art classification results of Convolutional Neural Networks (CNN), with robust model-based methods by taking prior knowledge of previous time steps into account. Evaluations on a challenging real-wold scenario, with trees and bushes as landmarks, show promising results over pure learning-based state-of-the-art 3D detectors, while being significant faster.
Tasks
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00733v1
PDF	https://arxiv.org/pdf/1909.00733v1.pdf
PWC	https://paperswithcode.com/paper/combining-deep-learning-and-model-based
Repo
Framework

Coercing Machine Learning to Output Physically Accurate Results


Title	Coercing Machine Learning to Output Physically Accurate Results
Authors	Zhenglin Geng, Dan Johnson, Ronald Fedkiw
Abstract	Many machine/deep learning artificial neural networks are trained to simply be interpolation functions that map input variables to output values interpolated from the training data in a linear/nonlinear fashion. Even when the input/output pairs of the training data are physically accurate (e.g. the results of an experiment or numerical simulation), interpolated quantities can deviate quite far from being physically accurate. Although one could project the output of a network into a physically feasible region, such a postprocess is not captured by the energy function minimized when training the network; thus, the final projected result could incorrectly deviate quite far from the training data. We propose folding any such projection or postprocess directly into the network so that the final result is correctly compared to the training data by the energy function. Although we propose a general approach, we illustrate its efficacy on a specific convolutional neural network that takes in human pose parameters (joint rotations) and outputs a prediction of vertex positions representing a triangulated cloth mesh. While the original network outputs vertex positions with erroneously high stretching and compression energies, the new network trained with our physics prior remedies these issues producing highly improved results.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09671v2
PDF	https://arxiv.org/pdf/1910.09671v2.pdf
PWC	https://paperswithcode.com/paper/coercing-machine-learning-to-output
Repo
Framework

Assessing Fashion Recommendations: A Multifaceted Offline Evaluation Approach


Title	Assessing Fashion Recommendations: A Multifaceted Offline Evaluation Approach
Authors	Jake Sherman, Chinmay Shukla, Rhonda Textor, Su Zhang, Amy A. Winecoff
Abstract	Fashion is a unique domain for developing recommender systems (RS). Personalization is critical to fashion users. As a result, highly accurate recommendations are not sufficient unless they are also specific to users. Moreover, fashion data is characterized by a large majority of new users, so a recommendation strategy that performs well only for users with prior interaction history is a poor fit to the fashion problem. Critical to addressing these issues in fashion recommendation is an evaluation strategy that: 1) includes multiple metrics that are relevant to fashion, and 2) is performed within segments of users with different interaction histories. Here, we present our multifaceted offline strategy for evaluating fashion RS. Using our proposed evaluation methodology, we compare the performance of three different algorithms, a most popular (MP) items strategy, a collaborative filtering (CF) strategy, and a content-based (CB) strategy. We demonstrate that only by considering the performance of these algorithms across multiple metrics and user segments can we determine the extent to which each algorithm is likely to fulfill fashion users’ needs.
Tasks	Recommendation Systems
Published	2019-09-05
URL	https://arxiv.org/abs/1909.04496v1
PDF	https://arxiv.org/pdf/1909.04496v1.pdf
PWC	https://paperswithcode.com/paper/assessing-fashion-recommendations-a
Repo
Framework

LapNet : Automatic Balanced Loss and Optimal Assignment for Real-Time Dense Object Detection


Title	LapNet : Automatic Balanced Loss and Optimal Assignment for Real-Time Dense Object Detection
Authors	Florian Chabot, Quoc-Cuong Pham, Mohamed Chaouch
Abstract	Real-time single-stage object detectors based on deep learning still remain less accurate than more complex ones. The trade-off between model performance and computational speed is a major challenge. In this paper, we propose a new way to efficiently learn a single-shot detector which offers a very good compromise between these two objectives. To this end, we introduce LapNet, an anchor based detector, trained end-to-end without any sampling strategy. Our approach aims to overcome two important problems encountered in training an anchor based detector: (1) ambiguity in the assignment of anchor to ground truth and (2) class and object size imbalance. To address the first limitation, we propose a soft positive/negative anchor assignment procedure based on a new overlapping function called “Per-Object Normalized Overlap” (PONO). This soft assignment can be self-corrected by the network itself to avoid ambiguity between close objects. To cope with the second limitation, we propose to learn additional weights, that are not used at inference, to efficiently manage sample imbalance. These two contributions make the detector learning more generic whatever the training dataset. Various experiments show the effectiveness of the proposed approach.
Tasks	Dense Object Detection, Object Detection, Semantic Segmentation
Published	2019-11-04
URL	https://arxiv.org/abs/1911.01149v2
PDF	https://arxiv.org/pdf/1911.01149v2.pdf
PWC	https://paperswithcode.com/paper/lapnet-automatic-balanced-loss-and-optimal
Repo
Framework

Controversy in Context


Title	Controversy in Context
Authors	Benjamin Sznajder, Ariel Gera, Yonatan Bilu, Dafna Sheinwald, Ella Rabinovich, Ranit Aharonov, David Konopnicki, Noam Slonim
Abstract	With the growing interest in social applications of Natural Language Processing and Computational Argumentation, a natural question is how controversial a given concept is. Prior works relied on Wikipedia’s metadata and on content analysis of the articles pertaining to a concept in question. Here we show that the immediate textual context of a concept is strongly indicative of this property, and, using simple and language-independent machine-learning tools, we leverage this observation to achieve state-of-the-art results in controversiality prediction. In addition, we analyze and make available a new dataset of concepts labeled for controversiality. It is significantly larger than existing datasets, and grades concepts on a 0-10 scale, rather than treating controversiality as a binary label.
Tasks
Published	2019-08-20
URL	https://arxiv.org/abs/1908.07491v1
PDF	https://arxiv.org/pdf/1908.07491v1.pdf
PWC	https://paperswithcode.com/paper/controversy-in-context
Repo
Framework

Recurrent Graph Syntax Encoder for Neural Machine Translation


Title	Recurrent Graph Syntax Encoder for Neural Machine Translation
Authors	Liang Ding, Dacheng Tao
Abstract	Syntax-incorporated machine translation models have been proven successful in improving the model’s reasoning and meaning preservation ability. In this paper, we propose a simple yet effective graph-structured encoder, the Recurrent Graph Syntax Encoder, dubbed \textbf{RGSE}, which enhances the ability to capture useful syntactic information. The RGSE is done over a standard encoder (recurrent or self-attention encoder), regarding recurrent network units as graph nodes and injects syntactic dependencies as edges, such that RGSE models syntactic dependencies and sequential information (\textit{i.e.}, word order) simultaneously. Our approach achieves considerable improvements over several syntax-aware NMT models in English$\Rightarrow$German and English$\Rightarrow$Czech translation tasks. And RGSE-equipped big model obtains competitive result compared with the state-of-the-art model in WMT14 En-De task. Extensive analysis further verifies that RGSE could benefit long sentence modeling, and produces better translations.
Tasks	Machine Translation
Published	2019-08-19
URL	https://arxiv.org/abs/1908.06559v1
PDF	https://arxiv.org/pdf/1908.06559v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-graph-syntax-encoder-for-neural
Repo
Framework

A Visual Technique to Analyze Flow of Information in a Machine Learning System


Title	A Visual Technique to Analyze Flow of Information in a Machine Learning System
Authors	Abon Chaudhuri
Abstract	Machine learning (ML) algorithms and machine learning based software systems implicitly or explicitly involve complex flow of information between various entities such as training data, feature space, validation set and results. Understanding the statistical distribution of such information and how they flow from one entity to another influence the operation and correctness of such systems, especially in large-scale applications that perform classification or prediction in real time. In this paper, we propose a visual approach to understand and analyze flow of information during model training and serving phases. We build the visualizations using a technique called Sankey Diagram - conventionally used to understand data flow among sets - to address various use cases of in a machine learning system. We demonstrate how the proposed technique, tweaked and twisted to suit a classification problem, can play a critical role in better understanding of the training data, the features, and the classifier performance. We also discuss how this technique enables diagnostic analysis of model predictions and comparative analysis of predictions from multiple classifiers. The proposed concept is illustrated with the example of categorization of millions of products in the e-commerce domain - a multi-class hierarchical classification problem.
Tasks
Published	2019-08-02
URL	https://arxiv.org/abs/1908.00754v1
PDF	https://arxiv.org/pdf/1908.00754v1.pdf
PWC	https://paperswithcode.com/paper/a-visual-technique-to-analyze-flow-of
Repo
Framework

From Low-Level Events to Activities – A Session-Based Approach (Extended Version)


Title	From Low-Level Events to Activities – A Session-Based Approach (Extended Version)
Authors	Massimiliano de Leoni, Safa Dundar
Abstract	Process-Mining techniques aim to use event data about past executions to gain insight into how processes are executed. While these techniques are proven to be very valuable, they are less successful to reach their goal if the process is flexible and, hence, events can potentially occur in any order. Furthermore, information systems can record events at very low level, which do not match the high-level concepts known at business level. Without abstracting sequences of events to high-level concepts, the results of applying process mining (e.g., discovered models) easily become very complex and difficult to interpret, which ultimately means that they are of little use. A large body of research exists on event abstraction but typically a large amount of domain knowledge is required to be fed in, which is often not readily available. Other abstraction techniques are unsupervised, which give lower accuracy. This paper puts forward a technique that requires limited domain knowledge that can be easily provided. Traces are divided in sessions, and each session is abstracted as one single high-level activity execution. The abstraction is based on a combination of automatic clustering and visualization methods. The technique was assessed on two case studies that evidently exhibits a large amount of behavior. The results clearly illustrate the benefits of the abstraction to convey knowledge to stakeholders.
Tasks
Published	2019-03-10
URL	https://arxiv.org/abs/1903.03993v3
PDF	https://arxiv.org/pdf/1903.03993v3.pdf
PWC	https://paperswithcode.com/paper/from-low-level-events-to-activities-a-session
Repo
Framework

An Interactive Control Approach to 3D Shape Reconstruction


Title	An Interactive Control Approach to 3D Shape Reconstruction
Authors	Bipul Islam, Ji Liu, Anthony Yezzi, Romeil Sandhu
Abstract	The ability to accurately reconstruct the 3D facets of a scene is one of the key problems in robotic vision. However, even with recent advances with machine learning, there is no high-fidelity universal 3D reconstruction method for this optimization problem as schemes often cater to specific image modalities and are often biased by scene abnormalities. Simply put, there always remains an information gap due to the dynamic nature of real-world scenarios. To this end, we demonstrate a feedback control framework which invokes operator inputs (also prone to errors) in order to augment existing reconstruction schemes. For proof-of-concept, we choose a classical region-based stereoscopic reconstruction approach and show how an ill-posed model can be augmented with operator input to be much more robust to scene artifacts. We provide necessary conditions for stability via Lyapunov analysis and perhaps more importantly, we show that the stability depends on a notion of absolute curvature. Mathematically, this aligns with previous work that has shown Ricci curvature as proxy for functional robustness of dynamical networked systems. We conclude with results that show how our method can improve standalone reconstruction schemes.
Tasks	3D Reconstruction
Published	2019-10-07
URL	https://arxiv.org/abs/1910.02738v1
PDF	https://arxiv.org/pdf/1910.02738v1.pdf
PWC	https://paperswithcode.com/paper/an-interactive-control-approach-to-3d-shape
Repo
Framework

Fantastic Generalization Measures and Where to Find Them


Title	Fantastic Generalization Measures and Where to Find Them
Authors	Yiding Jiang, Behnam Neyshabur, Hossein Mobahi, Dilip Krishnan, Samy Bengio
Abstract	Generalization of deep networks has been of great interest in recent years, resulting in a number of theoretically and empirically motivated complexity measures. However, most papers proposing such measures study only a small set of models, leaving open the question of whether the conclusion drawn from those experiments would remain valid in other settings. We present the first large scale study of generalization in deep networks. We investigate more then 40 complexity measures taken from both theoretical bounds and empirical studies. We train over 10,000 convolutional networks by systematically varying commonly used hyperparameters. Hoping to uncover potentially causal relationships between each measure and generalization, we analyze carefully controlled experiments and show surprising failures of some measures as well as promising measures for further research.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.02178v1
PDF	https://arxiv.org/pdf/1912.02178v1.pdf
PWC	https://paperswithcode.com/paper/fantastic-generalization-measures-and-where-1
Repo
Framework

Safe Linear Stochastic Bandits


Title	Safe Linear Stochastic Bandits
Authors	Kia Khezeli, Eilyan Bitar
Abstract	We introduce the safe linear stochastic bandit framework—a generalization of linear stochastic bandits—where, in each stage, the learner is required to select an arm with an expected reward that is no less than a predetermined (safe) threshold with high probability. We assume that the learner initially has knowledge of an arm that is known to be safe, but not necessarily optimal. Leveraging on this assumption, we introduce a learning algorithm that systematically combines known safe arms with exploratory arms to safely expand the set of safe arms over time, while facilitating safe greedy exploitation in subsequent stages. In addition to ensuring the satisfaction of the safety constraint at every stage of play, the proposed algorithm is shown to exhibit an expected regret that is no more than $O(\sqrt{T}\log (T))$ after $T$ stages of play.
Tasks
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09501v1
PDF	https://arxiv.org/pdf/1911.09501v1.pdf
PWC	https://paperswithcode.com/paper/safe-linear-stochastic-bandits
Repo
Framework

Adaptive Scheduling for Multi-Task Learning


Title	Adaptive Scheduling for Multi-Task Learning
Authors	Sébastien Jean, Orhan Firat, Melvin Johnson
Abstract	To train neural machine translation models simultaneously on multiple tasks (languages), it is common to sample each task uniformly or in proportion to dataset sizes. As these methods offer little control over performance trade-offs, we explore different task scheduling approaches. We first consider existing non-adaptive techniques, then move on to adaptive schedules that over-sample tasks with poorer results compared to their respective baseline. As explicit schedules can be inefficient, especially if one task is highly over-sampled, we also consider implicit schedules, learning to scale learning rates or gradients of individual tasks instead. These techniques allow training multilingual models that perform better for low-resource language pairs (tasks with small amount of data), while minimizing negative effects on high-resource tasks.
Tasks	Machine Translation, Multi-Task Learning
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06434v1
PDF	https://arxiv.org/pdf/1909.06434v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-scheduling-for-multi-task-learning
Repo
Framework