May 5, 2019

2512 words 12 mins read

Paper Group ANR 519

Dependency Language Models for Transition-based Dependency Parsing. Automatic Event Detection for Signal-based Surveillance. Adaptive Skills, Adaptive Partitions (ASAP). Diversity in Object Proposals. Neural Emoji Recommendation in Dialogue Systems. Deep Convolutional Networks as Models of Generalization and Blending Within Visual Creativity. Vista …

Dependency Language Models for Transition-based Dependency Parsing


Title	Dependency Language Models for Transition-based Dependency Parsing
Authors	Juntao Yu, Bernd Bohnet
Abstract	In this paper, we present an approach to improve the accuracy of a strong transition-based dependency parser by exploiting dependency language models that are extracted from a large parsed corpus. We integrated a small number of features based on the dependency language models into the parser. To demonstrate the effectiveness of the proposed approach, we evaluate our parser on standard English and Chinese data where the base parser could achieve competitive accuracy scores. Our enhanced parser achieved state-of-the-art accuracy on Chinese data and competitive results on English data. We gained a large absolute improvement of one point (UAS) on Chinese and 0.5 points for English.
Tasks	Dependency Parsing, Transition-Based Dependency Parsing
Published	2016-07-18
URL	http://arxiv.org/abs/1607.04982v2
PDF	http://arxiv.org/pdf/1607.04982v2.pdf
PWC	https://paperswithcode.com/paper/dependency-language-models-for-transition
Repo
Framework

Automatic Event Detection for Signal-based Surveillance


Title	Automatic Event Detection for Signal-based Surveillance
Authors	Jingxin Xu, Clinton Fookes, Sridha Sridharan
Abstract	Signal-based Surveillance systems such as Closed Circuits Televisions (CCTV) have been widely installed in public places. Those systems are normally used to find the events with security interest, and play a significant role in public safety. Though such systems are still heavily reliant on human labour to monitor the captured information, there have been a number of automatic techniques proposed to analysing the data. This article provides an overview of automatic surveillance event detection techniques . Despite it’s popularity in research, it is still too challenging a problem to be realised in a real world deployment. The challenges come from not only the detection techniques such as signal processing and machine learning, but also the experimental design with factors such as data collection, evaluation protocols, and ground-truth annotation. Finally, this article propose that multi-disciplinary research is the path towards a solution to this problem.
Tasks
Published	2016-12-06
URL	http://arxiv.org/abs/1612.01611v1
PDF	http://arxiv.org/pdf/1612.01611v1.pdf
PWC	https://paperswithcode.com/paper/automatic-event-detection-for-signal-based
Repo
Framework

Adaptive Skills, Adaptive Partitions (ASAP)


Title	Adaptive Skills, Adaptive Partitions (ASAP)
Authors	Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor
Abstract	We introduce the Adaptive Skills, Adaptive Partitions (ASAP) framework that (1) learns skills (i.e., temporally extended actions or options) as well as (2) where to apply them. We believe that both (1) and (2) are necessary for a truly general skill learning framework, which is a key building block needed to scale up to lifelong learning agents. The ASAP framework can also solve related new tasks simply by adapting where it applies its existing learned skills. We prove that ASAP converges to a local optimum under natural conditions. Finally, our experimental results, which include a RoboCup domain, demonstrate the ability of ASAP to learn where to reuse skills as well as solve multiple tasks with considerably less experience than solving each task from scratch.
Tasks
Published	2016-02-10
URL	http://arxiv.org/abs/1602.03351v2
PDF	http://arxiv.org/pdf/1602.03351v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-skills-adaptive-partitions-asap
Repo
Framework

Diversity in Object Proposals


Title	Diversity in Object Proposals
Authors	Anton Winschel, Rainer Lienhart, Christian Eggert
Abstract	Current top performing object recognition systems build on object proposals as a preprocessing step. Object proposal algorithms are designed to generate candidate regions for generic objects, yet current approaches are limited in capturing the vast variety of object characteristics. In this paper we analyze the error modes of the state-of-the-art Selective Search object proposal algorithm and suggest extensions to broaden its feature diversity in order to mitigate its error modes. We devise an edge grouping algorithm for handling objects without clear boundaries. To further enhance diversity, we incorporate the Edge Boxes proposal algorithm, which is based on fundamentally different principles than Selective Search. The combination of segmentations and edges provides rich image information and feature diversity which is essential for obtaining high quality object proposals for generic objects. For a preset amount of object proposals we achieve considerably better results by using our combination of different strategies than using any single strategy alone.
Tasks	Object Recognition
Published	2016-03-14
URL	http://arxiv.org/abs/1603.04308v1
PDF	http://arxiv.org/pdf/1603.04308v1.pdf
PWC	https://paperswithcode.com/paper/diversity-in-object-proposals
Repo
Framework

Neural Emoji Recommendation in Dialogue Systems


Title	Neural Emoji Recommendation in Dialogue Systems
Authors	Ruobing Xie, Zhiyuan Liu, Rui Yan, Maosong Sun
Abstract	Emoji is an essential component in dialogues which has been broadly utilized on almost all social platforms. It could express more delicate feelings beyond plain texts and thus smooth the communications between users, making dialogue systems more anthropomorphic and vivid. In this paper, we focus on automatically recommending appropriate emojis given the contextual information in multi-turn dialogue systems, where the challenges locate in understanding the whole conversations. More specifically, we propose the hierarchical long short-term memory model (H-LSTM) to construct dialogue representations, followed by a softmax classifier for emoji classification. We evaluate our models on the task of emoji classification in a real-world dataset, with some further explorations on parameter sensitivity and case study. Experimental results demonstrate that our method achieves the best performances on all evaluation metrics. It indicates that our method could well capture the contextual information and emotion flow in dialogues, which is significant for emoji recommendation.
Tasks
Published	2016-12-14
URL	http://arxiv.org/abs/1612.04609v1
PDF	http://arxiv.org/pdf/1612.04609v1.pdf
PWC	https://paperswithcode.com/paper/neural-emoji-recommendation-in-dialogue
Repo
Framework

Deep Convolutional Networks as Models of Generalization and Blending Within Visual Creativity


Title	Deep Convolutional Networks as Models of Generalization and Blending Within Visual Creativity
Authors	Graeme McCaig, Steve DiPaola, Liane Gabora
Abstract	We examine two recent artificial intelligence (AI) based deep learning algorithms for visual blending in convolutional neural networks (Mordvintsev et al. 2015, Gatys et al. 2015). To investigate the potential value of these algorithms as tools for computational creativity research, we explain and schematize the essential aspects of the algorithms’ operation and give visual examples of their output. We discuss the relationship of the two algorithms to human cognitive science theories of creativity such as conceptual blending theory and honing theory, and characterize the algorithms with respect to generation of novelty and aesthetic quality.
Tasks
Published	2016-10-08
URL	https://arxiv.org/abs/1610.02478v2
PDF	https://arxiv.org/pdf/1610.02478v2.pdf
PWC	https://paperswithcode.com/paper/deep-convolutional-networks-as-models-of
Repo
Framework

Vista: A Visually, Socially, and Temporally-aware Model for Artistic Recommendation


Title	Vista: A Visually, Socially, and Temporally-aware Model for Artistic Recommendation
Authors	Ruining He, Chen Fang, Zhaowen Wang, Julian McAuley
Abstract	Understanding users’ interactions with highly subjective content—like artistic images—is challenging due to the complex semantics that guide our preferences. On the one hand one has to overcome standard' recommender systems challenges, such as dealing with large, sparse, and long-tailed datasets. On the other, several new challenges present themselves, such as the need to model content in terms of its visual appearance, or even social dynamics, such as a preference toward a particular artist that is independent of the art they create. In this paper we build large-scale recommender systems to model the dynamics of a vibrant digital art community, Behance, consisting of tens of millions of interactions (clicks and appreciates’) of users toward digital art. Methodologically, our main contributions are to model (a) rich content, especially in terms of its visual appearance; (b) temporal dynamics, in terms of how users prefer `visually consistent’ content within and across sessions; and (c) social dynamics, in terms of how users exhibit preferences both towards certain art styles, as well as the artists themselves. \|
Tasks	Recommendation Systems
Published	2016-07-15
URL	http://arxiv.org/abs/1607.04373v1
PDF	http://arxiv.org/pdf/1607.04373v1.pdf
PWC	https://paperswithcode.com/paper/vista-a-visually-socially-and-temporally
Repo
Framework

Survey on the Use of Typological Information in Natural Language Processing


Title	Survey on the Use of Typological Information in Natural Language Processing
Authors	Helen O’Horan, Yevgeni Berzak, Ivan Vulić, Roi Reichart, Anna Korhonen
Abstract	In recent years linguistic typology, which classifies the world’s languages according to their functional and structural properties, has been widely used to support multilingual NLP. While the growing importance of typological information in supporting multilingual tasks has been recognised, no systematic survey of existing typological resources and their use in NLP has been published. This paper provides such a survey as well as discussion which we hope will both inform and inspire future work in the area.
Tasks
Published	2016-10-11
URL	http://arxiv.org/abs/1610.03349v1
PDF	http://arxiv.org/pdf/1610.03349v1.pdf
PWC	https://paperswithcode.com/paper/survey-on-the-use-of-typological-information
Repo
Framework

SANet: Structure-Aware Network for Visual Tracking


Title	SANet: Structure-Aware Network for Visual Tracking
Authors	Heng Fan, Haibin Ling
Abstract	Convolutional neural network (CNN) has drawn increasing interest in visual tracking owing to its powerfulness in feature extraction. Most existing CNN-based trackers treat tracking as a classification problem. However, these trackers are sensitive to similar distractors because their CNN models mainly focus on inter-class classification. To address this problem, we use self-structure information of object to distinguish it from distractors. Specifically, we utilize recurrent neural network (RNN) to model object structure, and incorporate it into CNN to improve its robustness to similar distractors. Considering that convolutional layers in different levels characterize the object from different perspectives, we use multiple RNNs to model object structure in different levels respectively. Extensive experiments on three benchmarks, OTB100, TC-128 and VOT2015, show that the proposed algorithm outperforms other methods. Code is released at http://www.dabi.temple.edu/~hbling/code/SANet/SANet.html.
Tasks	Visual Tracking
Published	2016-11-21
URL	http://arxiv.org/abs/1611.06878v3
PDF	http://arxiv.org/pdf/1611.06878v3.pdf
PWC	https://paperswithcode.com/paper/sanet-structure-aware-network-for-visual
Repo
Framework

Semantic descriptions of 24 evaluational adjectives, for application in sentiment analysis


Title	Semantic descriptions of 24 evaluational adjectives, for application in sentiment analysis
Authors	Cliff Goddard, Maite Taboada, Radoslava Trnavac
Abstract	We apply the Natural Semantic Metalanguage (NSM) approach (Goddard and Wierzbicka 2014) to the lexical-semantic analysis of English evaluational adjectives and compare the results with the picture developed in the Appraisal Framework (Martin and White 2005). The analysis is corpus-assisted, with examples mainly drawn from film and book reviews, and supported by collocational and statistical information from WordBanks Online. We propose NSM explications for 24 evaluational adjectives, arguing that they fall into five groups, each of which corresponds to a distinct semantic template. The groups can be sketched as follows: “First-person thought-plus-affect”, e.g. wonderful; “Experiential”, e.g. entertaining; “Experiential with bodily reaction”, e.g. gripping; “Lasting impact”, e.g. memorable; “Cognitive evaluation”, e.g. complex, excellent. These groupings and semantic templates are compared with the classifications in the Appraisal Framework’s system of Appreciation. In addition, we are particularly interested in sentiment analysis, the automatic identification of evaluation and subjectivity in text. We discuss the relevance of the two frameworks for sentiment analysis and other language technology applications.
Tasks	Sentiment Analysis
Published	2016-08-24
URL	http://arxiv.org/abs/1608.06697v1
PDF	http://arxiv.org/pdf/1608.06697v1.pdf
PWC	https://paperswithcode.com/paper/semantic-descriptions-of-24-evaluational
Repo
Framework

FaceNet2ExpNet: Regularizing a Deep Face Recognition Net for Expression Recognition


Title	FaceNet2ExpNet: Regularizing a Deep Face Recognition Net for Expression Recognition
Authors	Hui Ding, Shaohua Kevin Zhou, Rama Chellappa
Abstract	Relatively small data sets available for expression recognition research make the training of deep networks for expression recognition very challenging. Although fine-tuning can partially alleviate the issue, the performance is still below acceptable levels as the deep features probably contain redun- dant information from the pre-trained domain. In this paper, we present FaceNet2ExpNet, a novel idea to train an expression recognition network based on static images. We first propose a new distribution function to model the high-level neurons of the expression network. Based on this, a two-stage training algorithm is carefully designed. In the pre-training stage, we train the convolutional layers of the expression net, regularized by the face net; In the refining stage, we append fully- connected layers to the pre-trained convolutional layers and train the whole network jointly. Visualization shows that the model trained with our method captures improved high-level expression semantics. Evaluations on four public expression databases, CK+, Oulu-CASIA, TFD, and SFEW demonstrate that our method achieves better results than state-of-the-art.
Tasks	Face Recognition
Published	2016-09-21
URL	http://arxiv.org/abs/1609.06591v2
PDF	http://arxiv.org/pdf/1609.06591v2.pdf
PWC	https://paperswithcode.com/paper/facenet2expnet-regularizing-a-deep-face
Repo
Framework

Assisting Drivers During Overtaking Using Car-2-Car Communication and Multi-Agent Systems


Title	Assisting Drivers During Overtaking Using Car-2-Car Communication and Multi-Agent Systems
Authors	Adrian Groza, Calin Cara, Sergiu Zaporojan, Igor Calmicov
Abstract	A warning system for assisting drivers during overtaking maneuvers is proposed. The system relies on Car-2-Car communication technologies and multi-agent systems. A protocol for safety overtaking is proposed based on ACL communicative acts. The mathematical model for safety overtaking used Kalman filter to minimize localization error.
Tasks
Published	2016-07-27
URL	http://arxiv.org/abs/1607.08073v1
PDF	http://arxiv.org/pdf/1607.08073v1.pdf
PWC	https://paperswithcode.com/paper/assisting-drivers-during-overtaking-using-car
Repo
Framework

Visualizing Dynamics: from t-SNE to SEMI-MDPs


Title	Visualizing Dynamics: from t-SNE to SEMI-MDPs
Authors	Nir Ben Zrihem, Tom Zahavy, Shie Mannor
Abstract	Deep Reinforcement Learning (DRL) is a trending field of research, showing great promise in many challenging problems such as playing Atari, solving Go and controlling robots. While DRL agents perform well in practice we are still missing the tools to analayze their performance and visualize the temporal abstractions that they learn. In this paper, we present a novel method that automatically discovers an internal Semi Markov Decision Process (SMDP) model in the Deep Q Network’s (DQN) learned representation. We suggest a novel visualization method that represents the SMDP model by a directed graph and visualize it above a t-SNE map. We show how can we interpret the agent’s policy and give evidence for the hierarchical state aggregation that DQNs are learning automatically. Our algorithm is fully automatic, does not require any domain specific knowledge and is evaluated by a novel likelihood based evaluation criteria.
Tasks
Published	2016-06-22
URL	http://arxiv.org/abs/1606.07112v1
PDF	http://arxiv.org/pdf/1606.07112v1.pdf
PWC	https://paperswithcode.com/paper/visualizing-dynamics-from-t-sne-to-semi-mdps
Repo
Framework

On the Powerball Method for Optimization


Title	On the Powerball Method for Optimization
Authors	Ye Yuan, Mu Li, Jun Liu, Claire J. Tomlin
Abstract	We propose a new method to accelerate the convergence of optimization algorithms. This method simply adds a power coefficient $\gamma\in[0,1)$ to the gradient during optimization. We call this the Powerball method and analyze the convergence rate for the Powerball method for strongly convex functions. While theoretically the Powerball method is guaranteed to have a linear convergence rate in the same order of the gradient method, we show that empirically it significantly outperforms the gradient descent and Newton’s method, especially during the initial iterations. We demonstrate that the Powerball method provides a $10$-fold speedup of the convergence of both gradient descent and L-BFGS on multiple real datasets.
Tasks
Published	2016-03-24
URL	http://arxiv.org/abs/1603.07421v4
PDF	http://arxiv.org/pdf/1603.07421v4.pdf
PWC	https://paperswithcode.com/paper/on-the-powerball-method-for-optimization
Repo
Framework

Low Data Drug Discovery with One-shot Learning


Title	Low Data Drug Discovery with One-shot Learning
Authors	Han Altae-Tran, Bharath Ramsundar, Aneesh S. Pappu, Vijay Pande
Abstract	Recent advances in machine learning have made significant contributions to drug discovery. Deep neural networks in particular have been demonstrated to provide significant boosts in predictive power when inferring the properties and activities of small-molecule compounds. However, the applicability of these techniques has been limited by the requirement for large amounts of training data. In this work, we demonstrate how one-shot learning can be used to significantly lower the amounts of data required to make meaningful predictions in drug discovery applications. We introduce a new architecture, the residual LSTM embedding, that, when combined with graph convolutional neural networks, significantly improves the ability to learn meaningful distance metrics over small-molecules. We open source all models introduced in this work as part of DeepChem, an open-source framework for deep-learning in drug discovery.
Tasks	Drug Discovery, One-Shot Learning
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03199v1
PDF	http://arxiv.org/pdf/1611.03199v1.pdf
PWC	https://paperswithcode.com/paper/low-data-drug-discovery-with-one-shot
Repo
Framework