April 3, 2020

3172 words 15 mins read

Paper Group AWR 67

An Evaluation of Change Point Detection Algorithms. Variable-lag Granger Causality and Transfer Entropy for Time Series Analysis. Source Separation with Deep Generative Priors. Crowdsourced Collective Entity Resolution with Relational Match Propagation. On the interaction between supervision and self-play in emergent communication. DefogGAN: Predic …

An Evaluation of Change Point Detection Algorithms


Title	An Evaluation of Change Point Detection Algorithms
Authors	Gerrit J. J. van den Burg, Christopher K. I. Williams
Abstract	Change point detection is an important part of time series analysis, as the presence of a change point indicates an abrupt and significant change in the data generating process. While many algorithms for change point detection exist, little attention has been paid to evaluating their performance on real-world time series. Algorithms are typically evaluated on simulated data and a small number of commonly-used series with unreliable ground truth. Clearly this does not provide sufficient insight into the comparative performance of these algorithms. Therefore, instead of developing yet another change point detection method, we consider it vastly more important to properly evaluate existing algorithms on real-world data. To achieve this, we present the first data set specifically designed for the evaluation of change point detection algorithms, consisting of 37 time series from various domains. Each time series was annotated by five expert human annotators to provide ground truth on the presence and location of change points. We analyze the consistency of the human annotators, and describe evaluation metrics that can be used to measure algorithm performance in the presence of multiple ground truth annotations. Subsequently, we present a benchmark study where 13 existing algorithms are evaluated on each of the time series in the data set. This study shows that binary segmentation (Scott and Knott, 1974) and Bayesian online change point detection (Adams and MacKay, 2007) are among the best performing methods. Our aim is that this data set will serve as a proving ground in the development of novel change point detection algorithms.
Tasks	Change Point Detection, Time Series, Time Series Analysis
Published	2020-03-13
URL	https://arxiv.org/abs/2003.06222v1
PDF	https://arxiv.org/pdf/2003.06222v1.pdf
PWC	https://paperswithcode.com/paper/an-evaluation-of-change-point-detection
Repo	https://github.com/alan-turing-institute/TCPDBench
Framework	none

Variable-lag Granger Causality and Transfer Entropy for Time Series Analysis


Title	Variable-lag Granger Causality and Transfer Entropy for Time Series Analysis
Authors	Chainarong Amornbunchornvej, Elena Zheleva, Tanya Berger-Wolf
Abstract	Granger causality is a fundamental technique for causal inference in time series data, commonly used in the social and biological sciences. Typical operationalizations of Granger causality make a strong assumption that every time point of the effect time series is influenced by a combination of other time series with a fixed time delay. The assumption of fixed time delay also exists in Transfer Entropy, which is considered to be a non-linear version of Granger causality. However, the assumption of the fixed time delay does not hold in many applications, such as collective behavior, financial markets, and many natural phenomena. To address this issue, we develop Variable-lag Granger causality and Variable-lag Transfer Entropy, generalizations of both Granger causality and Transfer Entropy that relax the assumption of the fixed time delay and allow causes to influence effects with arbitrary time delays. In addition, we propose a method for inferring both variable-lag Granger causality and Transfer Entropy relations. We demonstrate our approaches on an application for studying coordinated collective behavior and other real-world casual-inference datasets and show that our proposed approaches perform better than several existing methods in both simulated and real-world datasets. Our approaches can be applied in any domain of time series analysis. The software of this work is available in the R-CRAN package: VLTimeCausality.
Tasks	Causal Inference, Time Series, Time Series Analysis
Published	2020-02-01
URL	https://arxiv.org/abs/2002.00208v2
PDF	https://arxiv.org/pdf/2002.00208v2.pdf
PWC	https://paperswithcode.com/paper/variable-lag-granger-causality-and-transfer
Repo	https://github.com/DarkEyes/VLTimeSeriesCausality
Framework	none

Source Separation with Deep Generative Priors


Title	Source Separation with Deep Generative Priors
Authors	Vivek Jayaram, John Thickstun
Abstract	Despite substantial progress in signal source separation, results for richly structured data continue to contain perceptible artifacts. In contrast, recent deep generative models can produce authentic samples in a variety of domains that are indistinguishable from samples of the data distribution. This paper introduces a Bayesian approach to source separation that uses generative models as priors over the components of a mixture of sources, and Langevin dynamics to sample from the posterior distribution of sources given a mixture. This decouples the source separation problem from generative modeling, enabling us to directly use cutting-edge generative models as priors. The method achieves state-of-the-art performance for MNIST digit separation. We introduce new methodology for evaluating separation quality on richer datasets, providing quantitative evaluation of separation results on CIFAR-10. We also provide qualitative results on LSUN.
Tasks
Published	2020-02-19
URL	https://arxiv.org/abs/2002.07942v1
PDF	https://arxiv.org/pdf/2002.07942v1.pdf
PWC	https://paperswithcode.com/paper/source-separation-with-deep-generative-priors
Repo	https://github.com/jthickstun/basis-separation
Framework	pytorch

Crowdsourced Collective Entity Resolution with Relational Match Propagation


Title	Crowdsourced Collective Entity Resolution with Relational Match Propagation
Authors	Jiacheng Huang, Wei Hu, Zhifeng Bao, Yuzhong Qu
Abstract	Knowledge bases (KBs) store rich yet heterogeneous entities and facts. Entity resolution (ER) aims to identify entities in KBs which refer to the same real-world object. Recent studies have shown significant benefits of involving humans in the loop of ER. They often resolve entities with pairwise similarity measures over attribute values and resort to the crowds to label uncertain ones. However, existing methods still suffer from high labor costs and insufficient labeling to some extent. In this paper, we propose a novel approach called crowdsourced collective ER, which leverages the relationships between entities to infer matches jointly rather than independently. Specifically, it iteratively asks human workers to label picked entity pairs and propagates the labeling information to their neighbors in distance. During this process, we address the problems of candidate entity pruning, probabilistic propagation, optimal question selection and error-tolerant truth inference. Our experiments on real-world datasets demonstrate that, compared with state-of-the-art methods, our approach achieves superior accuracy with much less labeling.
Tasks	Entity Resolution
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09361v1
PDF	https://arxiv.org/pdf/2002.09361v1.pdf
PWC	https://paperswithcode.com/paper/crowdsourced-collective-entity-resolution
Repo	https://github.com/nju-websoft/Remp
Framework	none

On the interaction between supervision and self-play in emergent communication


Title	On the interaction between supervision and self-play in emergent communication
Authors	Ryan Lowe, Abhinav Gupta, Jakob Foerster, Douwe Kiela, Joelle Pineau
Abstract	A promising approach for teaching artificial agents to use natural language involves using human-in-the-loop training. However, recent work suggests that current machine learning methods are too data inefficient to be trained in this way from scratch. In this paper, we investigate the relationship between two categories of learning signals with the ultimate goal of improving sample efficiency: imitating human language data via supervised learning, and maximizing reward in a simulated multi-agent environment via self-play (as done in emergent communication), and introduce the term supervised self-play (S2P) for algorithms using both of these signals. We find that first training agents via supervised learning on human data followed by self-play outperforms the converse, suggesting that it is not beneficial to emerge languages from scratch. We then empirically investigate various S2P schedules that begin with supervised learning in two environments: a Lewis signaling game with symbolic inputs, and an image-based referential game with natural language descriptions. Lastly, we introduce population based approaches to S2P, which further improves the performance over single-agent methods.
Tasks
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01093v1
PDF	https://arxiv.org/pdf/2002.01093v1.pdf
PWC	https://paperswithcode.com/paper/on-the-interaction-between-supervision-and-1
Repo	https://github.com/backpropper/s2p
Framework	pytorch

DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets


Title	DefogGAN: Predicting Hidden Information in the StarCraft Fog of War with Generative Adversarial Nets
Authors	Yonghyun Jeong, Hyunjin Choi, Byoungjip Kim, Youngjune Gwon
Abstract	We propose DefogGAN, a generative approach to the problem of inferring state information hidden in the fog of war for real-time strategy (RTS) games. Given a partially observed state, DefogGAN generates defogged images of a game as predictive information. Such information can lead to create a strategic agent for the game. DefogGAN is a conditional GAN variant featuring pyramidal reconstruction loss to optimize on multiple feature resolution scales.We have validated DefogGAN empirically using a large dataset of professional StarCraft replays. Our results indicate that DefogGAN can predict the enemy buildings and combat units as accurately as professional players do and achieves a superior performance among state-of-the-art defoggers.
Tasks	Starcraft
Published	2020-03-04
URL	https://arxiv.org/abs/2003.01927v2
PDF	https://arxiv.org/pdf/2003.01927v2.pdf
PWC	https://paperswithcode.com/paper/defoggan-predicting-hidden-information-in-the
Repo	https://github.com/TeamSAIDA/DefogGAN
Framework	tf

Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation


Title	Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation
Authors	Hengyi Cai, Hongshen Chen, Cheng Zhang, Yonghao Song, Xiaofang Zhao, Yangxi Li, Dongsheng Duan, Dawei Yin
Abstract	Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses. However, due to the subjectivity and open-ended nature of human conversations, the complexity of training dialogues varies greatly. The noise and uneven complexity of query-response pairs impede the learning efficiency and effects of the neural dialogue generation models. What is more, so far, there are no unified dialogue complexity measurements, and the dialogue complexity embodies multiple aspects of attributes—specificity, repetitiveness, relevance, etc. Inspired by human behaviors of learning to converse, where children learn from easy dialogues to complex ones and dynamically adjust their learning progress, in this paper, we first analyze five dialogue attributes to measure the dialogue complexity in multiple perspectives on three publicly available corpora. Then, we propose an adaptive multi-curricula learning framework to schedule a committee of the organized curricula. The framework is established upon the reinforcement learning paradigm, which automatically chooses different curricula at the evolving learning process according to the learning status of the neural dialogue generation model. Extensive experiments conducted on five state-of-the-art models demonstrate its learning efficiency and effectiveness with respect to 13 automatic evaluation metrics and human judgments.
Tasks	Dialogue Generation
Published	2020-03-02
URL	https://arxiv.org/abs/2003.00639v2
PDF	https://arxiv.org/pdf/2003.00639v2.pdf
PWC	https://paperswithcode.com/paper/learning-from-easy-to-complex-adaptive-multi
Repo	https://github.com/hengyicai/Adaptive_Multi-curricula_Learning_for_Dialog
Framework	pytorch

Deep Residual Flow for Out of Distribution Detection


Title	Deep Residual Flow for Out of Distribution Detection
Authors	Ev Zisselman, Aviv Tamar
Abstract	The effective application of neural networks in the real-world relies on proficiently detecting out-of-distribution examples. Contemporary methods seek to model the distribution of feature activations in the training data for adequately distinguishing abnormalities, and the state-of-the-art method uses Gaussian distribution models. In this work, we present a novel approach that improves upon the state-of-the-art by leveraging an expressive density model based on normalizing flows. We introduce the residual flow, a novel flow architecture that learns the residual distribution from a base Gaussian distribution. Our model is general, and can be applied to any data that is approximately Gaussian. For out of distribution detection in image datasets, our approach provides a principled improvement over the state-of-the-art. Specifically, we demonstrate the effectiveness of our method in ResNet and DenseNet architectures trained on various image datasets. For example, on a ResNet trained on CIFAR-100 and evaluated on detection of out-of-distribution samples from the ImageNet dataset, holding the true positive rate (TPR) at $95%$, we improve the true negative rate (TNR) from $56.7%$ (current state-of-the-art) to $77.5%$ (ours).
Tasks	Out-of-Distribution Detection
Published	2020-01-15
URL	https://arxiv.org/abs/2001.05419v2
PDF	https://arxiv.org/pdf/2001.05419v2.pdf
PWC	https://paperswithcode.com/paper/deep-residual-flow-for-novelty-detection
Repo	https://github.com/EvZissel/Residual-Flow
Framework	pytorch

Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation


Title	Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Authors	Xingang Pan, Xiaohang Zhan, Bo Dai, Dahua Lin, Chen Change Loy, Ping Luo
Abstract	Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there are still gaps toward an image prior that captures rich image semantics including color, spatial coherence, textures, and high-level concepts. This work presents an effective way to exploit the image prior captured by a generative adversarial network (GAN) trained on large-scale natural images. As shown in Fig.1, the deep generative prior (DGP) provides compelling results to restore missing semantics, e.g., color, patch, resolution, of various degraded images. It also enables diverse image manipulation including random jittering, image morphing, and category transfer. Such highly flexible restoration and manipulation are made possible through relaxing the assumption of existing GAN-inversion methods, which tend to fix the generator. Notably, we allow the generator to be fine-tuned on-the-fly in a progressive manner regularized by feature distance obtained by the discriminator in GAN. We show that these easy-to-implement and practical changes help preserve the reconstruction to remain in the manifold of nature image, and thus lead to more precise and faithful reconstruction for real images. Code is available at https://github.com/XingangPan/deepgenerative-prior.
Tasks	Image Morphing, Image Restoration
Published	2020-03-30
URL	https://arxiv.org/abs/2003.13659v2
PDF	https://arxiv.org/pdf/2003.13659v2.pdf
PWC	https://paperswithcode.com/paper/exploiting-deep-generative-prior-for
Repo	https://github.com/XingangPan/deep-generative-prior
Framework	pytorch

Detecting Potential Topics In News Using BERT, CRF and Wikipedia


Title	Detecting Potential Topics In News Using BERT, CRF and Wikipedia
Authors	Swapnil Ashok Jadhav
Abstract	For a news content distribution platform like Dailyhunt, Named Entity Recognition is a pivotal task for building better user recommendation and notification algorithms. Apart from identifying names, locations, organisations from the news for 13+ Indian languages and use them in algorithms, we also need to identify n-grams which do not necessarily fit in the definition of Named-Entity, yet they are important. For example, “me too movement”, “beef ban”, “alwar mob lynching”. In this exercise, given an English language text, we are trying to detect case-less n-grams which convey important information and can be used as topics and/or hashtags for a news. Model is built using Wikipedia titles data, private English news corpus and BERT-Multilingual pre-trained model, Bi-GRU and CRF architecture. It shows promising results when compared with industry best Flair, Spacy and Stanford-caseless-NER in terms of F1 and especially Recall.
Tasks	Named Entity Recognition
Published	2020-02-26
URL	https://arxiv.org/abs/2002.11402v2
PDF	https://arxiv.org/pdf/2002.11402v2.pdf
PWC	https://paperswithcode.com/paper/detecting-potential-topics-in-news-using-bert
Repo	https://github.com/swapniljadhav1921/bert_crf_topic_detection
Framework	none

Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation


Title	Multi-Channel Attention Selection GANs for Guided Image-to-Image Translation
Authors	Hao Tang, Dan Xu, Yan Yan, Jason J. Corso, Philip H. S. Torr, Nicu Sebe
Abstract	We propose a novel model named Multi-Channel Attention Selection Generative Adversarial Network (SelectionGAN) for guided image-to-image translation, where we translate an input image into another while respecting an external semantic guidance. The proposed SelectionGAN explicitly utilizes the semantic guidance information and consists of two stages. In the first stage, the input image and the conditional semantic guidance are fed into a cycled semantic-guided generation network to produce initial coarse results. In the second stage, we refine the initial results by using the proposed multi-scale spatial pooling & channel selection module and the multi-channel attention selection module. Moreover, uncertainty maps automatically learned from attention maps are used to guide the pixel loss for better network optimization. Exhaustive experiments on four challenging guided image-to-image translation tasks (face, hand, body and street view) demonstrate that our SelectionGAN is able to generate significantly better results than the state-of-the-art methods. Meanwhile, the proposed framework and modules are unified solutions and can be applied to solve other generation tasks, such as semantic image synthesis. The code is available at https://github.com/Ha0Tang/SelectionGAN.
Tasks	Image Generation, Image-to-Image Translation
Published	2020-02-03
URL	https://arxiv.org/abs/2002.01048v1
PDF	https://arxiv.org/pdf/2002.01048v1.pdf
PWC	https://paperswithcode.com/paper/multi-channel-attention-selection-gans-for
Repo	https://github.com/Ha0Tang/SelectionGAN
Framework	pytorch

VoiceCoach: Interactive Evidence-based Training for Voice Modulation Skills in Public Speaking


Title	VoiceCoach: Interactive Evidence-based Training for Voice Modulation Skills in Public Speaking
Authors	Xingbo Wang, Haipeng Zeng, Yong Wang, Aoyu Wu, Zhida Sun, Xiaojuan Ma, Huamin Qu
Abstract	The modulation of voice properties, such as pitch, volume, and speed, is crucial for delivering a successful public speech. However, it is challenging to master different voice modulation skills. Though many guidelines are available, they are often not practical enough to be applied in different public speaking situations, especially for novice speakers. We present VoiceCoach, an interactive evidence-based approach to facilitate the effective training of voice modulation skills. Specifically, we have analyzed the voice modulation skills from 2623 high-quality speeches (i.e., TED Talks) and use them as the benchmark dataset. Given a voice input, VoiceCoach automatically recommends good voice modulation examples from the dataset based on the similarity of both sentence structures and voice modulation skills. Immediate and quantitative visual feedback is provided to guide further improvement. The expert interviews and the user study provide support for the effectiveness and usability of VoiceCoach.
Tasks
Published	2020-01-22
URL	https://arxiv.org/abs/2001.07876v1
PDF	https://arxiv.org/pdf/2001.07876v1.pdf
PWC	https://paperswithcode.com/paper/voicecoach-interactive-evidence-based
Repo	https://github.com/xingbow/TED_dataset
Framework	none

Using Data Imputation for Signal Separation in High Contrast Imaging


Title	Using Data Imputation for Signal Separation in High Contrast Imaging
Authors	Bin Ren, Laurent Pueyo, Christine Chen, Élodie Choquet, John H. Debes, Gaspard Duchêne, François Ménard, Marshall D. Perrin
Abstract	To characterize circumstellar systems in high contrast imaging, the fundamental step is to construct a best point spread function (PSF) template for the non-circumstellar signals (i.e., star light and speckles) and separate it from the observation. With existing PSF construction methods, the circumstellar signals (e.g., planets, circumstellar disks) are unavoidably altered by over-fitting and/or self-subtraction, making forward modeling a necessity to recover these signals. We present a forward modeling–free solution to these problems with data imputation using sequential non-negative matrix factorization (DI-sNMF). DI-sNMF first converts this signal separation problem to a “missing data” problem in statistics by flagging the regions which host circumstellar signals as missing data, then attributes PSF signals to these regions. We mathematically prove it to have negligible alteration to circumstellar signals when the imputation region is relatively small, which thus enables precise measurement for these circumstellar objects. We apply it to simulated point source and circumstellar disk observations to demonstrate its proper recovery of them. We apply it to Gemini Planet Imager (GPI) K1-band observations of the debris disk surrounding HR 4796A, finding a tentative trend that the dust is more forward scattering as the wavelength increases. We expect DI-sNMF to be applicable to other general scenarios where the separation of signals is needed.
Tasks	Imputation
Published	2020-01-02
URL	https://arxiv.org/abs/2001.00563v3
PDF	https://arxiv.org/pdf/2001.00563v3.pdf
PWC	https://paperswithcode.com/paper/using-data-imputation-for-signal-separation
Repo	https://github.com/seawander/aastex_pwned
Framework	none

Shallow Discourse Annotation for Chinese TED Talks


Title	Shallow Discourse Annotation for Chinese TED Talks
Authors	Wanqiu Long, Xinyi Cai, James E. M. Reid, Bonnie Webber, Deyi Xiong
Abstract	Text corpora annotated with language-related properties are an important resource for the development of Language Technology. The current work contributes a new resource for Chinese Language Technology and for Chinese-English translation, in the form of a set of TED talks (some originally given in English, some in Chinese) that have been annotated with discourse relations in the style of the Penn Discourse TreeBank, adapted to properties of Chinese text that are not present in English. The resource is currently unique in annotating discourse-level properties of planned spoken monologues rather than of written text. An inter-annotator agreement study demonstrates that the annotation scheme is able to achieve highly reliable results.
Tasks
Published	2020-03-09
URL	https://arxiv.org/abs/2003.04032v1
PDF	https://arxiv.org/pdf/2003.04032v1.pdf
PWC	https://paperswithcode.com/paper/shallow-discourse-annotation-for-chinese-ted
Repo	https://github.com/tjunlp-lab/Shallow-Discourse-Annotation-for-Chinese-TED-Talks
Framework	none

Business Negotiation Definition Language


Title	Business Negotiation Definition Language
Authors	Rustam Tagiew
Abstract	The target of this paper is to present an industry-ready prototype software for general game playing. This software can also be used as the central element for experimental economics research, interfacing of game-theoretic libraries, AI-driven software testing, algorithmic trade, human behavior mining and simulation of (strategic) interactions. The software is based on a domain-specific language for electronic business to business negotiations – SIDL3.0. The paper also contains many examples to prove the power of this language.
Tasks
Published	2020-01-04
URL	https://arxiv.org/abs/2001.10799v1
PDF	https://arxiv.org/pdf/2001.10799v1.pdf
PWC	https://paperswithcode.com/paper/business-negotiation-definition-language
Repo	https://github.com/Yepkio/sidl
Framework	none