January 26, 2020

3227 words 16 mins read

Paper Group ANR 1354

Generating Diverse and Informative Natural Language Fashion Feedback. Convolutional Feature Extraction and Neural Arithmetic Logic Units for Stock Prediction. The Collective Advantage for Advancing Communications and Intelligence. On Universal Approximation by Neural Networks with Uniform Guarantees on Approximation of Infinite Dimensional Maps. A …

Generating Diverse and Informative Natural Language Fashion Feedback


Title	Generating Diverse and Informative Natural Language Fashion Feedback
Authors	Gil Sadeh, Lior Fritz, Gabi Shalev, Eduard Oks
Abstract	Recent advances in multi-modal vision and language tasks enable a new set of applications. In this paper, we consider the task of generating natural language fashion feedback on outfit images. We collect a unique dataset, which contains outfit images and corresponding positive and constructive fashion feedback. We treat each feedback type separately, and train deep generative encoder-decoder models with visual attention, similar to the standard image captioning pipeline. Following this approach, the generated sentences tend to be too general and non-informative. We propose an alternative decoding technique based on the Maximum Mutual Information objective function, which leads to more diverse and detailed responses. We evaluate our model with common language metrics, and also show human evaluation results. This technology is applied within the ``Alexa, how do I look?’’ feature, publicly available in Echo Look devices. \|
Tasks	Image Captioning
Published	2019-06-15
URL	https://arxiv.org/abs/1906.06619v1
PDF	https://arxiv.org/pdf/1906.06619v1.pdf
PWC	https://paperswithcode.com/paper/generating-diverse-and-informative-natural
Repo
Framework

Convolutional Feature Extraction and Neural Arithmetic Logic Units for Stock Prediction


Title	Convolutional Feature Extraction and Neural Arithmetic Logic Units for Stock Prediction
Authors	Shangeth Rajaa, Jajati Keshari Sahoo
Abstract	Stock prediction is a topic undergoing intense study for many years. Finance experts and mathematicians have been working on a way to predict the future stock price so as to decide to buy the stock or sell it to make profit. Stock experts or economists, usually analyze on the previous stock values using technical indicators, sentiment analysis etc to predict the future stock price. In recent years, many researches have extensively used machine learning for predicting the stock behaviour. In this paper we propose data driven deep learning approach to predict the future stock value with the previous price with the feature extraction property of convolutional neural network and to use Neural Arithmetic Logic Units with it.
Tasks	Sentiment Analysis, Stock Prediction
Published	2019-05-18
URL	https://arxiv.org/abs/1905.07581v1
PDF	https://arxiv.org/pdf/1905.07581v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-feature-extraction-and-neural
Repo
Framework

The Collective Advantage for Advancing Communications and Intelligence


Title	The Collective Advantage for Advancing Communications and Intelligence
Authors	Rongpeng Li, Zhifeng Zhao, Xing Xu, Fei Ni, Honggang Zhang
Abstract	The fifth-generation cellular networks (5G) has boosted the unprecedented convergence between the information world and physical world. On the other hand, empowered with the enormous amount of data and information, artificial intelligence (AI) has been universally applied and pervasive AI is believed to be an integral part of the future cellular networks (e.g., beyond 5G, B5G). Consequently, benefiting from the advancement in communication technology and AI, we boldly argue that the conditions for collective intelligence (CI) will be mature in the B5G era and CI will emerge among the widely connected beings and things. Afterwards, we highlight the potential huge impact of CI on both communications and intelligence. In particular, we introduce a regular language (i.e., the information economy metalanguage) supporting the future collective communications to augment human intelligence and explain its potential applications in naming Internet information and pushing information centric networks forward. Meanwhile, we propose a stigmergy-based federated collective intelligence and demonstrate its achievement in a simulated scenario where the agents collectively work together to form a pattern through simple indirect communications. In a word, CI could advance both communications and intelligence. discuss an anytime universal intelligence test model to evaluate the intelligence level of collective agents.
Tasks
Published	2019-04-26
URL	https://arxiv.org/abs/1905.00719v5
PDF	https://arxiv.org/pdf/1905.00719v5.pdf
PWC	https://paperswithcode.com/paper/190500719
Repo
Framework

On Universal Approximation by Neural Networks with Uniform Guarantees on Approximation of Infinite Dimensional Maps


Title	On Universal Approximation by Neural Networks with Uniform Guarantees on Approximation of Infinite Dimensional Maps
Authors	William H. Guss, Ruslan Salakhutdinov
Abstract	The study of universal approximation of arbitrary functions $f: \mathcal{X} \to \mathcal{Y}$ by neural networks has a rich and thorough history dating back to Kolmogorov (1957). In the case of learning finite dimensional maps, many authors have shown various forms of the universality of both fixed depth and fixed width neural networks. However, in many cases, these classical results fail to extend to the recent use of approximations of neural networks with infinitely many units for functional data analysis, dynamical systems identification, and other applications where either $\mathcal{X}$ or $\mathcal{Y}$ become infinite dimensional. Two questions naturally arise: which infinite dimensional analogues of neural networks are sufficient to approximate any map $f: \mathcal{X} \to \mathcal{Y}$, and when do the finite approximations to these analogues used in practice approximate $f$ uniformly over its infinite dimensional domain $\mathcal{X}$? In this paper, we answer the open question of universal approximation of nonlinear operators when $\mathcal{X}$ and $\mathcal{Y}$ are both infinite dimensional. We show that for a large class of different infinite analogues of neural networks, any continuous map can be approximated arbitrarily closely with some mild topological conditions on $\mathcal{X}$. Additionally, we provide the first lower-bound on the minimal number of input and output units required by a finite approximation to an infinite neural network to guarantee that it can uniformly approximate any nonlinear operator using samples from its inputs and outputs.
Tasks
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01545v1
PDF	https://arxiv.org/pdf/1910.01545v1.pdf
PWC	https://paperswithcode.com/paper/on-universal-approximation-by-neural-networks
Repo
Framework

A Comparative Study of High-Recall Real-Time Semantic Segmentation Based on Swift Factorized Network


Title	A Comparative Study of High-Recall Real-Time Semantic Segmentation Based on Swift Factorized Network
Authors	Kaite Xiang, Kaiwei Wang, Kailun Yang
Abstract	Semantic Segmentation (SS) is the task to assign a semantic label to each pixel of the observed images, which is of crucial significance for autonomous vehicles, navigation assistance systems for the visually impaired, and augmented reality devices. However, there is still a long way for SS to be put into practice as there are two essential challenges that need to be addressed: efficiency and evaluation criterions for practical application. For specific application scenarios, different criterions need to be adopted. Recall rate is an important criterion for many tasks like autonomous vehicles. For autonomous vehicles, we need to focus on the detection of the traffic objects like cars, buses, and pedestrians, which should be detected with high recall rates. In other words, it is preferable to detect it wrongly than miss it, because the other traffic objects will be dangerous if the algorithm miss them and segment them as safe roadways. In this paper, our main goal is to explore possible methods to attain high recall rate. Firstly, we propose a real-time SS network named Swift Factorized Network (SFN). The proposed network is adapted from SwiftNet, whose structure is a typical U-shape structure with lateral connections. Inspired by ERFNet and Global convolution Networks (GCNet), we propose two different blocks to enlarge valid receptive field. They do not take up too much calculation resources, but significantly enhance the performance compared with the baseline network. Secondly, we explore three ways to achieve higher recall rate, i.e. loss function, classifier and decision rules. We perform a comprehensive set of experiments on state-of-the-art datasets including CamVid and Cityscapes. We demonstrate that our SS convolutional neural networks reach excellent performance. Furthermore, we make a detailed analysis and comparison of the three proposed methods on the promotion of recall rate.
Tasks	Autonomous Vehicles, Real-Time Semantic Segmentation, Semantic Segmentation
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11394v1
PDF	https://arxiv.org/pdf/1907.11394v1.pdf
PWC	https://paperswithcode.com/paper/a-comparative-study-of-high-recall-real-time
Repo
Framework


Title	“Conservatives Overfit, Liberals Underfit”: The Social-Psychological Control of Affect and Uncertainty
Authors	Jesse Hoey, Neil J. MacKinnon
Abstract	The presence of artificial agents in human social networks is growing. From chatbots to robots, human experience in the developed world is moving towards a socio-technical system in which agents can be technological or biological, with increasingly blurred distinctions between. Given that emotion is a key element of human interaction, enabling artificial agents with the ability to reason about affect is a key stepping stone towards a future in which technological agents and humans can work together. This paper presents work on building intelligent computational agents that integrate both emotion and cognition. These agents are grounded in the well-established social-psychological Bayesian Affect Control Theory (BayesAct). The core idea of BayesAct is that humans are motivated in their social interactions by affective alignment: they strive for their social experiences to be coherent at a deep, emotional level with their sense of identity and general world views as constructed through culturally shared symbols. This affective alignment creates cohesive bonds between group members, and is instrumental for collaborations to solidify as relational group commitments. BayesAct agents are motivated in their social interactions by a combination of affective alignment and decision theoretic reasoning, trading the two off as a function of the uncertainty or unpredictability of the situation. This paper provides a high-level view of dual process theories and advances BayesAct as a plausible, computationally tractable model based in social-psychological theory. We introduce a revised BayesAct model that more deeply integrates social-psychological theorising, and we demonstrate a component of the model as being sufficient to account for cognitive biases about fairness, dissonance and conformity. We show how the model can unify different exploration strategies in reinforcement learning.
Tasks
Published	2019-08-08
URL	https://arxiv.org/abs/1908.03106v3
PDF	https://arxiv.org/pdf/1908.03106v3.pdf
PWC	https://paperswithcode.com/paper/conservatives-overfit-liberals-underfit-the
Repo
Framework

Revised JNLPBA Corpus: A Revised Version of Biomedical NER Corpus for Relation Extraction Task


Title	Revised JNLPBA Corpus: A Revised Version of Biomedical NER Corpus for Relation Extraction Task
Authors	Ming-Siang Huang, Po-Ting Lai, Richard Tzong-Han Tsai, Wen-Lian Hsu
Abstract	The advancement of biomedical named entity recognition (BNER) and biomedical relation extraction (BRE) researches promotes the development of text mining in biological domains. As a cornerstone of BRE, robust BNER system is required to identify the mentioned NEs in plain texts for further relation extraction stage. However, the current BNER corpora, which play important roles in these tasks, paid less attention to achieve the criteria for BRE task. In this study, we present Revised JNLPBA corpus, the revision of JNLPBA corpus, to broaden the applicability of a NER corpus from BNER to BRE task. We preserve the original entity types including protein, DNA, RNA, cell line and cell type while all the abstracts in JNLPBA corpus are manually curated by domain experts again basis on the new annotation guideline focusing on the specific NEs instead of general terms. Simultaneously, several imperfection issues in JNLPBA are pointed out and made up in the new corpus. To compare the adaptability of different NER systems in Revised JNLPBA and JNLPBA corpora, the F1-measure was measured in three open sources NER systems including BANNER, Gimli and NERSuite. In the same circumstance, all the systems perform average 10% better in Revised JNLPBA than in JNLPBA. Moreover, the cross-validation test is carried out which we train the NER systems on JNLPBA/Revised JNLPBA corpora and access the performance in both protein-protein interaction extraction (PPIE) and biomedical event extraction (BEE) corpora to confirm that the newly refined Revised JNLPBA is a competent NER corpus in biomedical relation application. The revised JNLPBA corpus is freely available at iasl-btm.iis.sinica.edu.tw/BNER/Content/Revised_JNLPBA.zip.
Tasks	Named Entity Recognition, Relation Extraction
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10219v1
PDF	http://arxiv.org/pdf/1901.10219v1.pdf
PWC	https://paperswithcode.com/paper/revised-jnlpba-corpus-a-revised-version-of
Repo
Framework

Executing Instructions in Situated Collaborative Interactions


Title	Executing Instructions in Situated Collaborative Interactions
Authors	Alane Suhr, Claudia Yan, Jacob Schluger, Stanley Yu, Hadi Khader, Marwa Mouallem, Iris Zhang, Yoav Artzi
Abstract	We study a collaborative scenario where a user not only instructs a system to complete tasks, but also acts alongside it. This allows the user to adapt to the system abilities by changing their language or deciding to simply accomplish some tasks themselves, and requires the system to effectively recover from errors as the user strategically assigns it new goals. We build a game environment to study this scenario, and learn to map user instructions to system actions. We introduce a learning approach focused on recovery from cascading errors between instructions, and modeling methods to explicitly reason about instructions with multiple goals. We evaluate with a new evaluation protocol using recorded interactions and online games with human users, and observe how users adapt to the system abilities.
Tasks
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03655v3
PDF	https://arxiv.org/pdf/1910.03655v3.pdf
PWC	https://paperswithcode.com/paper/executing-instructions-in-situated
Repo
Framework

A Method of Detecting End-To-End Curves of Limited Curvature


Title	A Method of Detecting End-To-End Curves of Limited Curvature
Authors	Ekaterina Panfilova, Mikhail Aliev, Irina Kunina, Vasiliy Postnikov, Dmitry Nikolaev
Abstract	In this paper we consider a method for detecting end-to-end curves of limited curvature like the k-link polylines with bending angle between adjacent segments in a given range. The approximation accuracy is achieved by maximization of the quality function in the image matrix. The method is based on a dynamic programming scheme constructed over Fast Hough Transform calculation results for image bands. The proposed method asymptotic complexity is $O(h \cdot (w+ \frac{h}{k}) \cdot log(\frac{h}{k}))$, where $h$ and $w$ are the image size, and $k$ is the approximating polyline links number, which is an analogue of the complexity of the fast Fourier transform or the fast Hough transform. We also show the results of the proposed method on synthetic and real data.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01884v1
PDF	https://arxiv.org/pdf/1912.01884v1.pdf
PWC	https://paperswithcode.com/paper/a-method-of-detecting-end-to-end-curves-of
Repo
Framework

Game Description Logic with Integers: A GDL Numerical Extension


Title	Game Description Logic with Integers: A GDL Numerical Extension
Authors	Munyque Mittelmann, Laurent Perrussel
Abstract	Many problems can be viewed as games, where one or more agents try to ensure that certain objectives hold no matter the behavior from the environment and other agents. In recent years, a number of logical formalisms have been proposed for specifying games among which the Game Description Language (GDL) was established as the official language for General Game Playing. Although numbers are recurring in games, the description of games with numerical features in GDL requires the enumeration from all possible numeric values and the relation among them. Thereby, in this paper, we introduce the Game Description Logic with Integers (GDLZ) to describe games with numerical variables, numerical parameters, as well as to perform numerical comparisons. We compare our approach with GDL and show that when describing the same game, GDLZ is more compact.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01876v1
PDF	https://arxiv.org/pdf/1912.01876v1.pdf
PWC	https://paperswithcode.com/paper/game-description-logic-with-integers-a-gdl
Repo
Framework

A Generic Acceleration Framework for Stochastic Composite Optimization


Title	A Generic Acceleration Framework for Stochastic Composite Optimization
Authors	Andrei Kulunchakov, Julien Mairal
Abstract	In this paper, we introduce various mechanisms to obtain accelerated first-order stochastic optimization algorithms when the objective function is convex or strongly convex. Specifically, we extend the Catalyst approach originally designed for deterministic objectives to the stochastic setting. Given an optimization method with mild convergence guarantees for strongly convex problems, the challenge is to accelerate convergence to a noise-dominated region, and then achieve convergence with an optimal worst-case complexity depending on the noise variance of the gradients. A side contribution of our work is also a generic analysis that can handle inexact proximal operators, providing new insights about the robustness of stochastic algorithms when the proximal operator cannot be exactly computed.
Tasks	Stochastic Optimization
Published	2019-06-03
URL	https://arxiv.org/abs/1906.01164v3
PDF	https://arxiv.org/pdf/1906.01164v3.pdf
PWC	https://paperswithcode.com/paper/a-generic-acceleration-framework-for
Repo
Framework

DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning


Title	DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning
Authors	Zhuoxuan Jiang, Ziming Huang, Dong Sheng Li, Xian-Ling Mao
Abstract	In end-to-end dialogue modeling and agent learning, it is important to (1) effectively learn knowledge from data, and (2) fully utilize heterogeneous information, e.g., dialogue act flow and utterances. However, the majority of existing methods cannot simultaneously satisfy the two conditions. For example, rule definition and data labeling during system design take too much manual work, and sequence-to-sequence methods only model one-side utterance information. In this paper, we propose a novel joint end-to-end model by multi-task representation learning, which can capture the knowledge from heterogeneous information through automatically learning knowledgeable low-dimensional embeddings from data, named with DialogAct2Vec. The model requires little manual work for intervention in system design and we find that the multi-task learning can greatly improve the effectiveness of representation learning. Extensive experiments on a public dataset for restaurant reservation show that the proposed method leads to significant improvements against the state-of-the-art baselines on both the act prediction task and utterance prediction task.
Tasks	Multi-Task Learning, Representation Learning
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04088v1
PDF	https://arxiv.org/pdf/1911.04088v1.pdf
PWC	https://paperswithcode.com/paper/dialogact2vec-towards-end-to-end-dialogue
Repo
Framework

Fitting 3D Shapes from Partial and Noisy Point Clouds with Evolutionary Computing


Title	Fitting 3D Shapes from Partial and Noisy Point Clouds with Evolutionary Computing
Authors	Jean F. Liénard
Abstract	Point clouds obtained from photogrammetry are noisy and incomplete models of reality. We propose an evolutionary optimization methodology that is able to approximate the underlying object geometry on such point clouds. This approach assumes a priori knowledge on the 3D structure modeled and enables the identification of a collection of primitive shapes approximating the scene. Built-in mechanisms that enforce high shape diversity and adaptive population size make this method suitable to modeling both simple and complex scenes. We focus here on the case of cylinder approximations and we describe, test, and compare a set of mutation operators designed for optimal exploration of their search space. We assess the robustness and limitations of this algorithm through a series of synthetic examples, and we finally demonstrate its general applicability on two real-life cases in vegetation and industrial settings.
Tasks
Published	2019-01-20
URL	http://arxiv.org/abs/1901.06722v1
PDF	http://arxiv.org/pdf/1901.06722v1.pdf
PWC	https://paperswithcode.com/paper/fitting-3d-shapes-from-partial-and-noisy
Repo
Framework

Genetic Random Weight Change Algorithm for the Learning of Multilayer Neural Networks


Title	Genetic Random Weight Change Algorithm for the Learning of Multilayer Neural Networks
Authors	Mohammad Ibraim Sarker, Yali Nie, Hong Yongki, Hyongsuk Kim
Abstract	A new method to improve the performance of Random weight change (RWC) algorithm based on a simple genetic algorithm, namely, Genetic random weight change (GRWC) is proposed. It is to find the optimal values of global minima via learning. In contrast to Random Weight Change (RWC), GRWC contains an effective optimization procedure which are good at exploring a large and complex space in an intellectual strategies influenced by the GA/RWC synergy. By implementing our simple GA in RWC we achieve an astounding accuracy of finding global minima.
Tasks
Published	2019-06-05
URL	https://arxiv.org/abs/1906.01892v1
PDF	https://arxiv.org/pdf/1906.01892v1.pdf
PWC	https://paperswithcode.com/paper/genetic-random-weight-change-algorithm-for
Repo
Framework

Transfer Learning across Languages from Someone Else’s NMT Model


Title	Transfer Learning across Languages from Someone Else’s NMT Model
Authors	Tom Kocmi, Ondřej Bojar
Abstract	Neural machine translation is demanding in terms of training time, hardware resources, size, and quantity of parallel sentences. We propose a simple transfer learning method to recycle already trained models for different language pairs with no need for modifications in model architecture, hyper-parameters, or vocabulary. We achieve better translation quality and shorter convergence times than when training from random initialization. To show the applicability of our method, we recycle a Transformer model trained by different researchers for translating English-to-Czech and used it to seed models for seven language pairs. Our translation models are significantly better even when the re-used model’s language pair is not linguistically related to the child language pair, especially for low-resource languages. Our approach needs only one pretrained model for all transferring to all various languages pairs. Additionally, we improve this approach with a simple vocabulary transformation. We analyze the behavior of transfer learning to understand the gains from unrelated languages.
Tasks	Machine Translation, Transfer Learning
Published	2019-09-24
URL	https://arxiv.org/abs/1909.10955v1
PDF	https://arxiv.org/pdf/1909.10955v1.pdf
PWC	https://paperswithcode.com/paper/transfer-learning-across-languages-from
Repo
Framework