January 30, 2020

2991 words 15 mins read

Paper Group ANR 399

Riposte! A Large Corpus of Counter-Arguments. Modeling Acoustic-Prosodic Cues for Word Importance Prediction in Spoken Dialogues. Perceptual Attention-based Predictive Control. Online Non-Convex Learning: Following the Perturbed Leader is Optimal. An Effective Two-Branch Model-Based Deep Network for Single Image Deraining. Hamiltonian Monte-Carlo f …

Riposte! A Large Corpus of Counter-Arguments


Title	Riposte! A Large Corpus of Counter-Arguments
Authors	Paul Reisert, Benjamin Heinzerling, Naoya Inoue, Shun Kiyono, Kentaro Inui
Abstract	Constructive feedback is an effective method for improving critical thinking skills. Counter-arguments (CAs), one form of constructive feedback, have been proven to be useful for critical thinking skills. However, little work has been done for constructing a large-scale corpus of them which can drive research on automatic generation of CAs for fallacious micro-level arguments (i.e. a single claim and premise pair). In this work, we cast providing constructive feedback as a natural language processing task and create Riposte!, a corpus of CAs, towards this goal. Produced by crowdworkers, Riposte! contains over 18k CAs. We instruct workers to first identify common fallacy types and produce a CA which identifies the fallacy. We analyze how workers create CAs and construct a baseline model based on our analysis.
Tasks
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03246v1
PDF	https://arxiv.org/pdf/1910.03246v1.pdf
PWC	https://paperswithcode.com/paper/riposte-a-large-corpus-of-counter-arguments
Repo
Framework

Modeling Acoustic-Prosodic Cues for Word Importance Prediction in Spoken Dialogues


Title	Modeling Acoustic-Prosodic Cues for Word Importance Prediction in Spoken Dialogues
Authors	Sushant Kafle, Cecilia O. Alm, Matt Huenerfauth
Abstract	Prosodic cues in conversational speech aid listeners in discerning a message. We investigate whether acoustic cues in spoken dialogue can be used to identify the importance of individual words to the meaning of a conversation turn. Individuals who are Deaf and Hard of Hearing often rely on real-time captions in live meetings. Word error rate, a traditional metric for evaluating automatic speech recognition, fails to capture that some words are more important for a system to transcribe correctly than others. We present and evaluate neural architectures that use acoustic features for 3-class word importance prediction. Our model performs competitively against state-of-the-art text-based word-importance prediction models, and it demonstrates particular benefits when operating on imperfect ASR output.
Tasks	Speech Recognition
Published	2019-03-28
URL	https://arxiv.org/abs/1903.12238v2
PDF	https://arxiv.org/pdf/1903.12238v2.pdf
PWC	https://paperswithcode.com/paper/modeling-acoustic-prosodic-cues-for-word
Repo
Framework

Perceptual Attention-based Predictive Control


Title	Perceptual Attention-based Predictive Control
Authors	Keuntaek Lee, Gabriel Nakajima An, Viacheslav Zakharov, Evangelos A. Theodorou
Abstract	In this paper, we present a novel information processing architecture for safe deep learning-based visual navigation of autonomous systems. The proposed information processing architecture is used to support a perceptual attention-based predictive control algorithm that leverages model predictive control (MPC), convolutional neural networks (CNNs), and uncertainty quantification methods. The novelty of our approach lies in using MPC to learn how to place attention on relevant areas of the visual input, which ultimately allows the system to more rapidly detect unsafe conditions. We accomplish this by using MPC to learn to select regions of interest in the input image, which are used to output control actions as well as estimates of epistemic and aleatoric uncertainty in the attention-aware visual input. We use these uncertainty estimates to quantify the safety of our network controller under the current navigation condition. The proposed architecture and algorithm is tested on a 1:5 scale terrestrial vehicle. Experimental results show that the proposed algorithm outperforms previous approaches on early detection of unsafe conditions, such as when novel obstacles are present in the navigation environment. The proposed architecture is the first step towards using deep learning-based perceptual control policies in safety-critical domains.
Tasks	Visual Navigation
Published	2019-04-26
URL	https://arxiv.org/abs/1904.11898v2
PDF	https://arxiv.org/pdf/1904.11898v2.pdf
PWC	https://paperswithcode.com/paper/perceptual-attention-based-predictive-control
Repo
Framework

Online Non-Convex Learning: Following the Perturbed Leader is Optimal


Title	Online Non-Convex Learning: Following the Perturbed Leader is Optimal
Authors	Arun Sai Suggala, Praneeth Netrapalli
Abstract	We study the problem of online learning with non-convex losses, where the learner has access to an offline optimization oracle. We show that the classical Follow the Perturbed Leader (FTPL) algorithm achieves optimal regret rate of $O(T^{-1/2})$ in this setting. This improves upon the previous best-known regret rate of $O(T^{-1/3})$ for FTPL. We further show that an optimistic variant of FTPL achieves better regret bounds when the sequence of losses encountered by the learner is `predictable’. \|
Tasks
Published	2019-03-19
URL	https://arxiv.org/abs/1903.08110v2
PDF	https://arxiv.org/pdf/1903.08110v2.pdf
PWC	https://paperswithcode.com/paper/online-non-convex-learning-following-the
Repo
Framework

An Effective Two-Branch Model-Based Deep Network for Single Image Deraining


Title	An Effective Two-Branch Model-Based Deep Network for Single Image Deraining
Authors	Yinglong Wang, Dong Gong, Jie Yang, Qinfeng Shi, Anton van den Hengel, Dehua Xie, Bing Zeng
Abstract	Removing rain effects from an image is of importance for various applications such as autonomous driving, drone piloting, and photo editing. Conventional methods rely on some heuristics to handcraft various priors to remove or separate the rain effects from an image. Recent deep learning models are proposed to learn end-to-end methods to complete this task. However, they often fail to obtain satisfactory results in many realistic scenarios, especially when the observed images suffer from heavy rain. Heavy rain brings not only rain streaks but also haze-like effect caused by the accumulation of tiny raindrops. Different from the existing deep learning deraining methods that mainly focus on handling the rain streaks, we design a deep neural network by incorporating a physical raining image model. Specifically, in the proposed model, two branches are designed to handle both the rain streaks and haze-like effects. An additional submodule is jointly trained to finally refine the results, which give the model flexibility to control the strength of removing the mist. Extensive experiments on several datasets show that our method outperforms the state-of-the-art in both objective assessments and visual quality.
Tasks	Autonomous Driving, Rain Removal, Single Image Deraining
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05404v2
PDF	https://arxiv.org/pdf/1905.05404v2.pdf
PWC	https://paperswithcode.com/paper/an-effective-two-branch-model-based-deep
Repo
Framework

Hamiltonian Monte-Carlo for Orthogonal Matrices


Title	Hamiltonian Monte-Carlo for Orthogonal Matrices
Authors	Viktor Yanush, Dmitry Kropotov
Abstract	We consider the problem of sampling from posterior distributions for Bayesian models where some parameters are restricted to be orthogonal matrices. Such matrices are sometimes used in neural networks models for reasons of regularization and stabilization of training procedures, and also can parameterize matrices of bounded rank, positive-definite matrices and others. In \citet{byrne2013geodesic} authors have already considered sampling from distributions over manifolds using exact geodesic flows in a scheme similar to Hamiltonian Monte Carlo (HMC). We propose new sampling scheme for a set of orthogonal matrices that is based on the same approach, uses ideas of Riemannian optimization and does not require exact computation of geodesic flows. The method is theoretically justified by proof of symplecticity for the proposed iteration. In experiments we show that the new scheme is comparable or faster in time per iteration and more sample-efficient comparing to conventional HMC with explicit orthogonal parameterization and Geodesic Monte-Carlo. We also provide promising results of Bayesian ensembling for orthogonal neural networks and low-rank matrix factorization.
Tasks
Published	2019-01-23
URL	http://arxiv.org/abs/1901.08045v1
PDF	http://arxiv.org/pdf/1901.08045v1.pdf
PWC	https://paperswithcode.com/paper/hamiltonian-monte-carlo-for-orthogonal
Repo
Framework

SlugBot: Developing a Computational Model andFramework of a Novel Dialogue Genre


Title	SlugBot: Developing a Computational Model andFramework of a Novel Dialogue Genre
Authors	Kevin K. Bowden, Jiaqi Wu, Wen Cui, Juraj Juraska, Vrindavan Harrison, Brian Schwarzmann, Nick Santer, Marilyn Walker
Abstract	One of the most interesting aspects of the Amazon Alexa Prize competition is that the framing of the competition requires the development of new computational models of dialogue and its structure. Traditional computational models of dialogue are of two types: (1) task-oriented dialogue, supported by AI planning models,or simplified planning models consisting of frames with slots to be filled; or (2)search-oriented dialogue where every user turn is treated as a search query that may elaborate and extend current search results. Alexa Prize dialogue systems such as SlugBot must support conversational capabilities that go beyond what these traditional models can do. Moreover, while traditional dialogue systems rely on theoretical computational models, there are no existing computational theories that circumscribe the expected system and user behaviors in the intended conversational genre of the Alexa Prize Bots. This paper describes how UCSC’s SlugBot team has combined the development of a novel computational theoretical model, Discourse Relation Dialogue Model, with its implementation in a modular system in order to test and refine it. We highlight how our novel dialogue model has led us to create a novel ontological resource, UniSlug, and how the structure of UniSlug determine show we curate and structure content so that our dialogue manager implements and tests our novel computational dialogue model.
Tasks
Published	2019-07-22
URL	https://arxiv.org/abs/1907.10658v1
PDF	https://arxiv.org/pdf/1907.10658v1.pdf
PWC	https://paperswithcode.com/paper/slugbot-developing-a-computational-model
Repo
Framework

Dueling Posterior Sampling for Preference-Based Reinforcement Learning


Title	Dueling Posterior Sampling for Preference-Based Reinforcement Learning
Authors	Ellen R. Novoseller, Yibing Wei, Yanan Sui, Yisong Yue, Joel W. Burdick
Abstract	In preference-based reinforcement learning (RL), an agent interacts with the environment while receiving preferences instead of absolute feedback. While there is increasing research activity in preference-based RL, the design of formal frameworks that admit tractable theoretical analysis remains an open challenge. Building upon ideas from preference-based bandit learning and posterior sampling in RL, we present DUELING POSTERIOR SAMPLING (DPS), which employs preference-based posterior sampling to learn both the system dynamics and the underlying utility function that governs the preference feedback. As preference feedback is provided on trajectories rather than individual state/action pairs, we develop a Bayesian approach for the credit assignment problem, translating preferences to a posterior distribution over state/action reward models. We prove an asymptotic Bayesian no-regret rate for DPS with a Bayesian linear regression credit assignment model. This is the first regret guarantee for preference-based RL to our knowledge. We also discuss possible avenues for extending the proof methodology to other credit assignment models. Finally, we evaluate the approach empirically, showing competitive performance against existing baselines.
Tasks
Published	2019-08-04
URL	https://arxiv.org/abs/1908.01289v2
PDF	https://arxiv.org/pdf/1908.01289v2.pdf
PWC	https://paperswithcode.com/paper/dueling-posterior-sampling-for-preference
Repo
Framework

Knowledge-based Conversational Search


Title	Knowledge-based Conversational Search
Authors	Svitlana Vakulenko
Abstract	Conversational interfaces that allow for intuitive and comprehensive access to digitally stored information remain an ambitious goal. In this thesis, we lay foundations for designing conversational search systems by analyzing the requirements and proposing concrete solutions for automating some of the basic components and tasks that such systems should support. We describe several interdependent studies that were conducted to analyse the design requirements for more advanced conversational search systems able to support complex human-like dialogue interactions and provide access to vast knowledge repositories. In the first two research chapters, we focus on analyzing the structures common to information-seeking dialogues by capturing recurrent patterns in terms of both domain-independent functional relations between utterances as well as domain-specific implicit semantic relations from shared background knowledge. Our results show that question answering is one of the key components required for efficient information access but it is not the only type of dialogue interactions that a conversational search system should support. In the third research chapter, we propose a novel approach for complex question answering from a knowledge graph that surpasses the current state-of-the-art results in terms of both efficacy and efficiency. In the last research chapter, we turn our attention towards an alternative interaction mode, which we termed conversational browsing, in which, unlike question answering, the conversational system plays a more pro-active role in the course of a dialogue interaction. We show that this approach helps users to discover relevant items that are difficult to retrieve using only question answering due to the vocabulary mismatch problem.
Tasks	Question Answering
Published	2019-12-14
URL	https://arxiv.org/abs/1912.06859v1
PDF	https://arxiv.org/pdf/1912.06859v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-based-conversational-search
Repo
Framework

AliMe KBQA: Question Answering over Structured Knowledge for E-commerce Customer Service


Title	AliMe KBQA: Question Answering over Structured Knowledge for E-commerce Customer Service
Authors	Feng-Lin Li, Weijia Chen, Qi Huang, Yikun Guo
Abstract	With the rise of knowledge graph (KG), question answering over knowledge base (KBQA) has attracted increasing attention in recent years. Despite much research has been conducted on this topic, it is still challenging to apply KBQA technology in industry because business knowledge and real-world questions can be rather complicated. In this paper, we present AliMe-KBQA, a bold attempt to apply KBQA in the E-commerce customer service field. To handle real knowledge and questions, we extend the classic “subject-predicate-object (SPO)” structure with property hierarchy, key-value structure and compound value type (CVT), and enhance traditional KBQA with constraints recognition and reasoning ability. We launch AliMe-KBQA in the Marketing Promotion scenario for merchants during the “Double 11” period in 2018 and other such promotional events afterwards. Online results suggest that AliMe-KBQA is not only able to gain better resolution and improve customer satisfaction, but also becomes the preferred knowledge management method by business knowledge staffs since it offers a more convenient and efficient management experience.
Tasks	Question Answering
Published	2019-12-12
URL	https://arxiv.org/abs/1912.05728v1
PDF	https://arxiv.org/pdf/1912.05728v1.pdf
PWC	https://paperswithcode.com/paper/alime-kbqa-question-answering-over-structured
Repo
Framework

Recurrent Embedding Aggregation Network for Video Face Recognition


Title	Recurrent Embedding Aggregation Network for Video Face Recognition
Authors	Sixue Gong, Yichun Shi, Anil K. Jain
Abstract	Recurrent networks have been successful in analyzing temporal data and have been widely used for video analysis. However, for video face recognition, where the base CNNs trained on large-scale data already provide discriminative features, using Long Short-Term Memory (LSTM), a popular recurrent network, for feature learning could lead to overfitting and degrade the performance instead. We propose a Recurrent Embedding Aggregation Network (REAN) for set to set face recognition. Compared with LSTM, REAN is robust against overfitting because it only learns how to aggregate the pre-trained embeddings rather than learning representations from scratch. Compared with quality-aware aggregation methods, REAN can take advantage of the context information to circumvent the noise introduced by redundant video frames. Empirical results on three public domain video face recognition datasets, IJB-S, YTF, and PaSC show that the proposed REAN significantly outperforms naive CNN-LSTM structure and quality-aware aggregation methods.
Tasks	Face Recognition
Published	2019-04-26
URL	https://arxiv.org/abs/1904.12019v2
PDF	https://arxiv.org/pdf/1904.12019v2.pdf
PWC	https://paperswithcode.com/paper/recurrent-embedding-aggregation-network-for
Repo
Framework

Online Algorithms for Multiclass Classification using Partial Labels


Title	Online Algorithms for Multiclass Classification using Partial Labels
Authors	Rajarshi Bhattacharjee, Naresh Manwani
Abstract	In this paper, we propose online algorithms for multiclass classification using partial labels. We propose two variants of Perceptron called Avg Perceptron and Max Perceptron to deal with the partial labeled data. We also propose Avg Pegasos and Max Pegasos, which are extensions of Pegasos algorithm. We also provide mistake bounds for Avg Perceptron and regret bound for Avg Pegasos. We show the effectiveness of the proposed approaches by experimenting on various datasets and comparing them with the standard Perceptron and Pegasos.
Tasks
Published	2019-12-24
URL	https://arxiv.org/abs/1912.11367v1
PDF	https://arxiv.org/pdf/1912.11367v1.pdf
PWC	https://paperswithcode.com/paper/online-algorithms-for-multiclass
Repo
Framework

Flow-based generative models for Markov chain Monte Carlo in lattice field theory


Title	Flow-based generative models for Markov chain Monte Carlo in lattice field theory
Authors	M. S. Albergo, G. Kanwar, P. E. Shanahan
Abstract	A Markov chain update scheme using a machine-learned flow-based generative model is proposed for Monte Carlo sampling in lattice field theories. The generative model may be optimized (trained) to produce samples from a distribution approximating the desired Boltzmann distribution determined by the lattice action of the theory being studied. Training the model systematically improves autocorrelation times in the Markov chain, even in regions of parameter space where standard Markov chain Monte Carlo algorithms exhibit critical slowing down in producing decorrelated updates. Moreover, the model may be trained without existing samples from the desired distribution. The algorithm is compared with HMC and local Metropolis sampling for $\phi^4$ theory in two dimensions.
Tasks
Published	2019-04-26
URL	https://arxiv.org/abs/1904.12072v3
PDF	https://arxiv.org/pdf/1904.12072v3.pdf
PWC	https://paperswithcode.com/paper/flow-based-generative-models-for-markov-chain
Repo
Framework

A Human-Centered Data-Driven Planner-Actor-Critic Architecture via Logic Programming


Title	A Human-Centered Data-Driven Planner-Actor-Critic Architecture via Logic Programming
Authors	Daoming Lyu, Fangkai Yang, Bo Liu, Steven Gustafson
Abstract	Recent successes of Reinforcement Learning (RL) allow an agent to learn policies that surpass human experts but suffers from being time-hungry and data-hungry. By contrast, human learning is significantly faster because prior and general knowledge and multiple information resources are utilized. In this paper, we propose a Planner-Actor-Critic architecture for huMAN-centered planning and learning (PACMAN), where an agent uses its prior, high-level, deterministic symbolic knowledge to plan for goal-directed actions, and also integrates the Actor-Critic algorithm of RL to fine-tune its behavior towards both environmental rewards and human feedback. This work is the first unified framework where knowledge-based planning, RL, and human teaching jointly contribute to the policy learning of an agent. Our experiments demonstrate that PACMAN leads to a significant jump-start at the early stage of learning, converges rapidly and with small variance, and is robust to inconsistent, infrequent, and misleading feedback.
Tasks
Published	2019-09-18
URL	https://arxiv.org/abs/1909.09209v1
PDF	https://arxiv.org/pdf/1909.09209v1.pdf
PWC	https://paperswithcode.com/paper/a-human-centered-data-driven-planner-actor
Repo
Framework

Synthetic Event Time Series Health Data Generation


Title	Synthetic Event Time Series Health Data Generation
Authors	Saloni Dash, Ritik Dutta, Isabelle Guyon, Adrien Pavao, Andrew Yale, Kristin P. Bennett
Abstract	Synthetic medical data which preserves privacy while maintaining utility can be used as an alternative to real medical data, which has privacy costs and resource constraints associated with it. At present, most models focus on generating cross-sectional health data which is not necessarily representative of real data. In reality, medical data is longitudinal in nature, with a single patient having multiple health events, non-uniformly distributed throughout their lifetime. These events are influenced by patient covariates such as comorbidities, age group, gender etc. as well as external temporal effects (e.g. flu season). While there exist seminal methods to model time series data, it becomes increasingly challenging to extend these methods to medical event time series data. Due to the complexity of the real data, in which each patient visit is an event, we transform the data by using summary statistics to characterize the events for a fixed set of time intervals, to facilitate analysis and interpretability. We then train a generative adversarial network to generate synthetic data. We demonstrate this approach by generating human sleep patterns, from a publicly available dataset. We empirically evaluate the generated data and show close univariate resemblance between synthetic and real data. However, we also demonstrate how stratification by covariates is required to gain a deeper understanding of synthetic data quality.
Tasks	Time Series
Published	2019-11-14
URL	https://arxiv.org/abs/1911.06411v2
PDF	https://arxiv.org/pdf/1911.06411v2.pdf
PWC	https://paperswithcode.com/paper/synthetic-event-time-series-health-data
Repo
Framework