April 1, 2020

3203 words 16 mins read

Paper Group ANR 520

XPersona: Evaluating Multilingual Personalized Chatbot. Efficient Scene Text Detection with Textual Attention Tower. Vision based body gesture meta features for Affective Computing. Few-Shot Few-Shot Learning and the role of Spatial Attention. A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning. STRIPS Action Discovery. Stocha …

XPersona: Evaluating Multilingual Personalized Chatbot


Title	XPersona: Evaluating Multilingual Personalized Chatbot
Authors	Zhaojiang Lin, Zihan Liu, Genta Indra Winata, Samuel Cahyawijaya, Andrea Madotto, Yejin Bang, Etsuko Ishii, Pascale Fung
Abstract	Personalized dialogue systems are an essential step toward better human-machine interaction. Existing personalized dialogue agents rely on properly designed conversational datasets, which are mostly monolingual (e.g., English), which greatly limits the usage of conversational agents in other languages. In this paper, we propose a multi-lingual extension of Persona-Chat, namely XPersona. Our dataset includes persona conversations in six different languages other than English for building and evaluating multilingual personalized agents. We experiment with both multilingual and cross-lingual trained baselines, and evaluate them against monolingual and translation-pipeline models using both automatic and human evaluation. Experimental results show that the multilingual trained models outperform the translation-pipeline and that they are on par with the monolingual models, with the advantage of having a single model across multiple languages. On the other hand, the state-of-the-art cross-lingual trained models achieve inferior performance to the other models, showing that cross-lingual conversation modeling is a challenging task. We hope that our dataset and baselines~\footnote{Datasets and all the baselines will be released} will accelerate research in multilingual dialogue systems.
Tasks	Chatbot
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07568v1
PDF	https://arxiv.org/pdf/2003.07568v1.pdf
PWC	https://paperswithcode.com/paper/xpersona-evaluating-multilingual-personalized
Repo
Framework

Efficient Scene Text Detection with Textual Attention Tower


Title	Efficient Scene Text Detection with Textual Attention Tower
Authors	Liang Zhang, Yufei Liu, Hang Xiao, Lu Yang, Guangming Zhu, Syed Afaq Shah, Mohammed Bennamoun, Peiyi Shen
Abstract	Scene text detection has received attention for years and achieved an impressive performance across various benchmarks. In this work, we propose an efficient and accurate approach to detect multioriented text in scene images. The proposed feature fusion mechanism allows us to use a shallower network to reduce the computational complexity. A self-attention mechanism is adopted to suppress false positive detections. Experiments on public benchmarks including ICDAR 2013, ICDAR 2015 and MSRA-TD500 show that our proposed approach can achieve better or comparable performances with fewer parameters and less computational cost.
Tasks	Scene Text Detection
Published	2020-01-30
URL	https://arxiv.org/abs/2002.03741v1
PDF	https://arxiv.org/pdf/2002.03741v1.pdf
PWC	https://paperswithcode.com/paper/efficient-scene-text-detection-with-textual
Repo
Framework

Vision based body gesture meta features for Affective Computing


Title	Vision based body gesture meta features for Affective Computing
Authors	Indigo J. D. Orton
Abstract	Early detection of psychological distress is key to effective treatment. Automatic detection of distress, such as depression, is an active area of research. Current approaches utilise vocal, facial, and bodily modalities. Of these, the bodily modality is the least investigated, partially due to the difficulty in extracting bodily representations from videos, and partially due to the lack of viable datasets. Existing body modality approaches use automatic categorization of expressions to represent body language as a series of specific expressions, much like words within natural language. In this dissertation I present a new type of feature, within the body modality, that represents meta information of gestures, such as speed, and use it to predict a non-clinical depression label. This differs to existing work by representing overall behaviour as a small set of aggregated meta features derived from a person’s movement. In my method I extract pose estimation from videos, detect gestures within body parts, extract meta information from individual gestures, and finally aggregate these features to generate a small feature vector for use in prediction tasks. I introduce a new dataset of 65 video recordings of interviews with self-evaluated distress, personality, and demographic labels. This dataset enables the development of features utilising the whole body in distress detection tasks. I evaluate my newly introduced meta-features for predicting depression, anxiety, perceived stress, somatic stress, five standard personality measures, and gender. A linear regression based classifier using these features achieves a 82.70% F1 score for predicting depression within my novel dataset.
Tasks	Pose Estimation
Published	2020-02-10
URL	https://arxiv.org/abs/2003.00809v1
PDF	https://arxiv.org/pdf/2003.00809v1.pdf
PWC	https://paperswithcode.com/paper/vision-based-body-gesture-meta-features-for
Repo
Framework

Few-Shot Few-Shot Learning and the role of Spatial Attention


Title	Few-Shot Few-Shot Learning and the role of Spatial Attention
Authors	Yann Lifchitz, Yannis Avrithis, Sylvaine Picard
Abstract	Few-shot learning is often motivated by the ability of humans to learn new tasks from few examples. However, standard few-shot classification benchmarks assume that the representation is learned on a limited amount of base class data, ignoring the amount of prior knowledge that a human may have accumulated before learning new tasks. At the same time, even if a powerful representation is available, it may happen in some domain that base class data are limited or non-existent. This motivates us to study a problem where the representation is obtained from a classifier pre-trained on a large-scale dataset of a different domain, assuming no access to its training process, while the base class data are limited to few examples per class and their role is to adapt the representation to the domain at hand rather than learn from scratch. We adapt the representation in two stages, namely on the few base class data if available and on the even fewer data of new tasks. In doing so, we obtain from the pre-trained classifier a spatial attention map that allows focusing on objects and suppressing background clutter. This is important in the new problem, because when base class data are few, the network cannot learn where to focus implicitly. We also show that a pre-trained network may be easily adapted to novel classes, without meta-learning.
Tasks	Few-Shot Learning, Meta-Learning
Published	2020-02-18
URL	https://arxiv.org/abs/2002.07522v1
PDF	https://arxiv.org/pdf/2002.07522v1.pdf
PWC	https://paperswithcode.com/paper/few-shot-few-shot-learning-and-the-role-of-1
Repo
Framework

A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning


Title	A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning
Authors	Soochan Lee, Junsoo Ha, Dongsu Zhang, Gunhee Kim
Abstract	Despite the growing interest in continual learning, most of its contemporary works have been studied in a rather restricted setting where tasks are clearly distinguishable, and task boundaries are known during training. However, if our goal is to develop an algorithm that learns as humans do, this setting is far from realistic, and it is essential to develop a methodology that works in a task-free manner. Meanwhile, among several branches of continual learning, expansion-based methods have the advantage of eliminating catastrophic forgetting by allocating new resources to learn new data. In this work, we propose an expansion-based approach for task-free continual learning. Our model, named Continual Neural Dirichlet Process Mixture (CN-DPM), consists of a set of neural network experts that are in charge of a subset of the data. CN-DPM expands the number of experts in a principled way under the Bayesian nonparametric framework. With extensive experiments, we show that our model successfully performs task-free continual learning for both discriminative and generative tasks such as image classification and image generation.
Tasks	Continual Learning, Image Classification, Image Generation
Published	2020-01-03
URL	https://arxiv.org/abs/2001.00689v2
PDF	https://arxiv.org/pdf/2001.00689v2.pdf
PWC	https://paperswithcode.com/paper/a-neural-dirichlet-process-mixture-model-for-1
Repo
Framework

STRIPS Action Discovery


Title	STRIPS Action Discovery
Authors	Alejandro Suárez-Hernández, Javier Segovia-Aguas, Carme Torras, Guillem Alenyà
Abstract	The problem of specifying high-level knowledge bases for planning becomes a hard task in realistic environments. This knowledge is usually handcrafted and is hard to keep updated, even for system experts. Recent approaches have shown the success of classical planning at synthesizing action models even when all intermediate states are missing. These approaches can synthesize action schemas in Planning Domain Definition Language (PDDL) from a set of execution traces each consisting, at least, of an initial and final state. In this paper, we propose a new algorithm to unsupervisedly synthesize STRIPS action models with a classical planner when action signatures are unknown. In addition, we contribute with a compilation to classical planning that mitigates the problem of learning static predicates in the action model preconditions, exploits the capabilities of SAT planners with parallel encodings to compute action schemas and validate all instances. Our system is flexible in that it supports the inclusion of partial input information that may speed up the search. We show through several experiments how learned action models generalize over unseen planning instances.
Tasks
Published	2020-01-30
URL	https://arxiv.org/abs/2001.11457v2
PDF	https://arxiv.org/pdf/2001.11457v2.pdf
PWC	https://paperswithcode.com/paper/strips-action-discovery
Repo
Framework

Stochastic Normalizing Flows


Title	Stochastic Normalizing Flows
Authors	Liam Hodgkinson, Chris van der Heide, Fred Roosta, Michael W. Mahoney
Abstract	We introduce stochastic normalizing flows, an extension of continuous normalizing flows for maximum likelihood estimation and variational inference (VI) using stochastic differential equations (SDEs). Using the theory of rough paths, the underlying Brownian motion is treated as a latent variable and approximated, enabling efficient training of neural SDEs as random neural ordinary differential equations. These SDEs can be used for constructing efficient Markov chains to sample from the underlying distribution of a given dataset. Furthermore, by considering families of targeted SDEs with prescribed stationary distribution, we can apply VI to the optimization of hyperparameters in stochastic MCMC.
Tasks
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09547v2
PDF	https://arxiv.org/pdf/2002.09547v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-normalizing-flows-1
Repo
Framework

Semantics of negative sequential patterns


Title	Semantics of negative sequential patterns
Authors	Thomas Guyet, Philippe Besnard
Abstract	In the field of pattern mining, a negative sequential pattern is specified by means of a sequence consisting of events to occur and of other events, called negative events, to be absent. For instance, containment of the pattern $\langle a\ \neg b\ c\rangle$ arises with an occurrence of a and a subsequent occurrence of c but no occurrence of b in between. This article is to shed light on the ambiguity of such a seemingly intuitive notation and we identify eight possible semantics for the containment relation between a pattern and a sequence. These semantics are illustrated and formally studied, in particular we propose dominance and equivalence relations between them. Also we prove that support is anti-monotonic for some of these semantics. Some of the results are discussed with the aim of developing algorithms to extract efficiently frequent negative patterns.
Tasks
Published	2020-02-17
URL	https://arxiv.org/abs/2002.06920v2
PDF	https://arxiv.org/pdf/2002.06920v2.pdf
PWC	https://paperswithcode.com/paper/semantics-of-negative-sequential-patterns
Repo
Framework

A Survey of Deep Learning for Scientific Discovery


Title	A Survey of Deep Learning for Scientific Discovery
Authors	Maithra Raghu, Eric Schmidt
Abstract	Over the past few years, we have seen fundamental breakthroughs in core problems in machine learning, largely driven by advances in deep neural networks. At the same time, the amount of data collected in a wide array of scientific domains is dramatically increasing in both size and complexity. Taken together, this suggests many exciting opportunities for deep learning applications in scientific settings. But a significant challenge to this is simply knowing where to start. The sheer breadth and diversity of different deep learning techniques makes it difficult to determine what scientific problems might be most amenable to these methods, or which specific combination of methods might offer the most promising first approach. In this survey, we focus on addressing this central issue, providing an overview of many widely used deep learning models, spanning visual, sequential and graph structured data, associated tasks and different training methods, along with techniques to use deep learning with less data and better interpret these complex models — two central considerations for many scientific use cases. We also include overviews of the full design process, implementation tips, and links to a plethora of tutorials, research summaries and open-sourced deep learning pipelines and pretrained models, developed by the community. We hope that this survey will help accelerate the use of deep learning across different scientific domains.
Tasks
Published	2020-03-26
URL	https://arxiv.org/abs/2003.11755v1
PDF	https://arxiv.org/pdf/2003.11755v1.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-deep-learning-for-scientific
Repo
Framework

Understanding the Limitations of Network Online Learning


Title	Understanding the Limitations of Network Online Learning
Authors	Timothy LaRock, Timothy Sakharov, Sahely Bhadra, Tina Eliassi-Rad
Abstract	Studies of networked phenomena, such as interactions in online social media, often rely on incomplete data, either because these phenomena are partially observed, or because the data is too large or expensive to acquire all at once. Analysis of incomplete data leads to skewed or misleading results. In this paper, we investigate limitations of learning to complete partially observed networks via node querying. Concretely, we study the following problem: given (i) a partially observed network, (ii) the ability to query nodes for their connections (e.g., by accessing an API), and (iii) a budget on the number of such queries, sequentially learn which nodes to query in order to maximally increase observability. We call this querying process Network Online Learning and present a family of algorithms called NOL*. These algorithms learn to choose which partially observed node to query next based on a parameterized model that is trained online through a process of exploration and exploitation. Extensive experiments on both synthetic and real world networks show that (i) it is possible to sequentially learn to choose which nodes are best to query in a network and (ii) some macroscopic properties of networks, such as the degree distribution and modular structure, impact the potential for learning and the optimal amount of random exploration.
Tasks
Published	2020-01-09
URL	https://arxiv.org/abs/2001.07607v1
PDF	https://arxiv.org/pdf/2001.07607v1.pdf
PWC	https://paperswithcode.com/paper/understanding-the-limitations-of-network
Repo
Framework

Masking schemes for universal marginalisers


Title	Masking schemes for universal marginalisers
Authors	Divya Gautam, Maria Lomeli, Kostis Gourgoulias, Daniel H. Thompson, Saurabh Johri
Abstract	We consider the effect of structure-agnostic and structure-dependent masking schemes when training a universal marginaliser (arXiv:1711.00695) in order to learn conditional distributions of the form $P(x_i \mathbf x_{\mathbf b})$, where $x_i$ is a given random variable and $\mathbf x_{\mathbf b}$ is some arbitrary subset of all random variables of the generative model of interest. In other words, we mimic the self-supervised training of a denoising autoencoder, where a dataset of unlabelled data is used as partially observed input and the neural approximator is optimised to minimise reconstruction loss. We focus on studying the underlying process of the partially observed data—how good is the neural approximator at learning all conditional distributions when the observation process at prediction time differs from the masking process during training? We compare networks trained with different masking schemes in terms of their predictive performance and generalisation properties.
Tasks	Denoising
Published	2020-01-16
URL	https://arxiv.org/abs/2001.05895v1
PDF	https://arxiv.org/pdf/2001.05895v1.pdf
PWC	https://paperswithcode.com/paper/masking-schemes-for-universal-marginalisers
Repo
Framework

Optimization of Operation Strategy for Primary Torque based hydrostatic Drivetrain using Artificial Intelligence


Title	Optimization of Operation Strategy for Primary Torque based hydrostatic Drivetrain using Artificial Intelligence
Authors	Yusheng Xiang, Marcus Geimer
Abstract	A new primary torque control concept for hydrostatics mobile machines was introduced in 2018. The mentioned concept controls the pressure in a closed circuit by changing the angle of the hydraulic pump to achieve the desired pressure based on a feedback system. Thanks to this concept, a series of advantages are expected. However, while working in a Y cycle, the primary torque-controlled wheel loader has worse performance in efficiency compared to secondary controlled earthmover due to lack of recuperation ability. Alternatively, we use deep learning algorithms to improve machines’ regeneration performance. In this paper, we firstly make a potential analysis to show the benefit by utilizing the regeneration process, followed by proposing a series of CRDNNs, which combine CNN, RNN, and DNN, to precisely detect Y cycles. Compared to existing algorithms, the CRDNN with bi-directional LSTMs has the best accuracy, and the CRDNN with LSTMs has a comparable performance but much fewer training parameters. Based on our dataset including 119 truck loading cycles, our best neural network shows a 98.2% test accuracy. Therefore, even with a simple regeneration process, our algorithm can improve the holistic efficiency of mobile machines up to 9% during Y cycle processes if primary torque concept is used.
Tasks
Published	2020-03-22
URL	https://arxiv.org/abs/2003.10011v2
PDF	https://arxiv.org/pdf/2003.10011v2.pdf
PWC	https://paperswithcode.com/paper/optimization-of-operation-startegy-for
Repo
Framework

Multi-Label Text Classification using Attention-based Graph Neural Network


Title	Multi-Label Text Classification using Attention-based Graph Neural Network
Authors	Ankit Pal, Muru Selvakumar, Malaikannan Sankarasubbu
Abstract	In Multi-Label Text Classification (MLTC), one sample can belong to more than one class. It is observed that most MLTC tasks, there are dependencies or correlations among labels. Existing methods tend to ignore the relationship among labels. In this paper, a graph attention network-based model is proposed to capture the attentive dependency structure among the labels. The graph attention network uses a feature matrix and a correlation matrix to capture and explore the crucial dependencies between the labels and generate classifiers for the task. The generated classifiers are applied to sentence feature vectors obtained from the text feature extraction network (BiLSTM) to enable end-to-end training. Attention allows the system to assign different weights to neighbor nodes per label, thus allowing it to learn the dependencies among labels implicitly. The results of the proposed model are validated on five real-world MLTC datasets. The proposed model achieves similar or better performance compared to the previous state-of-the-art models.
Tasks	Multi-Label Text Classification, Text Classification
Published	2020-03-22
URL	https://arxiv.org/abs/2003.11644v1
PDF	https://arxiv.org/pdf/2003.11644v1.pdf
PWC	https://paperswithcode.com/paper/multi-label-text-classification-using
Repo
Framework


Title	Blind Source Separation for NMR Spectra with Negative Intensity
Authors	Ryan J. McCarty, Nimish Ronghe, Mandy Woo, Todd M. Alam
Abstract	NMR spectral datasets, especially in systems with limited samples, can be difficult to interpret if they contain multiple chemical components (phases, polymorphs, molecules, crystals, glasses, etc…) and the possibility of overlapping resonances. In this paper, we benchmark several blind source separation techniques for analysis of NMR spectral datasets containing negative intensity. For benchmarking purposes, we generated a large synthetic datasbase of quadrupolar solid-state NMR-like spectra that model spin-lattice T1 relaxation or nutation tip/flip angle experiments. Our benchmarking approach focused exclusively on the ability of blind source separation techniques to reproduce the spectra of the underlying pure components. In general, we find that FastICA (Fast Independent Component Analysis), SIMPLISMA (SIMPLe-to-use-Interactive Self-modeling Mixture Analysis), and NNMF (Non-Negative Matrix Factorization) are top-performing techniques. We demonstrate that dataset normalization approaches prior to blind source separation do not considerably improve outcomes. Within the range of noise levels studied, we did not find drastic changes to the ranking of techniques. The accuracy of FastICA and SIMPLISMA degrades quickly if excess (unreal) pure components are predicted. Our results indicate poor performance of SVD (Singular Value Decomposition) methods, and we propose alternative techniques for matrix initialization. The benchmarked techniques are also applied to real solid state NMR datasets. In general, the recommendations from the synthetic datasets agree with the recommendations and results from the real data analysis. The discussion provides some additional recommendations for spectroscopists applying blind source separation to NMR datasets, and for future benchmark studies.
Tasks
Published	2020-02-07
URL	https://arxiv.org/abs/2002.03009v1
PDF	https://arxiv.org/pdf/2002.03009v1.pdf
PWC	https://paperswithcode.com/paper/blind-source-separation-for-nmr-spectra-with
Repo
Framework

The Information in Emotion Communication


Title	The Information in Emotion Communication
Authors	Alison Duncan Kerr, Kevin Scharp
Abstract	How much information is transmitted when animals use emotions to communicate? It is clear that emotions are used as communication systems in humans and other species. The quantitative theory of emotion information presented here is based on Shannon’s mathematical theory of information in communication systems. The theory explains myriad aspects of emotion communication and offers dozens of new directions for research. It is superior to the “contagion” theory of emotion spreading, which is currently dominant. One important application of the information theory of emotion communication is that it permits the development of emotion security systems for social networks to guard against the widespread emotion manipulation we see online today.
Tasks
Published	2020-02-14
URL	https://arxiv.org/abs/2002.08470v1
PDF	https://arxiv.org/pdf/2002.08470v1.pdf
PWC	https://paperswithcode.com/paper/the-information-in-emotion-communication
Repo
Framework