July 27, 2019

2831 words 14 mins read

Paper Group ANR 640

Towards Collaborative Conceptual Exploration. Inferring agent objectives at different scales of a complex adaptive system. Multi-view Unsupervised Feature Selection by Cross-diffused Matrix Alignment. Polar Transformer Networks. Decoupled Learning of Environment Characteristics for Safe Exploration. Simplifying the Bible and Wikipedia Using Statist …

Towards Collaborative Conceptual Exploration


Title	Towards Collaborative Conceptual Exploration
Authors	Tom Hanika, Jens Zumbrägel
Abstract	In domains with high knowledge distribution a natural objective is to create principle foundations for collaborative interactive learning environments. We present a first mathematical characterization of a collaborative learning group, a consortium, based on closure systems of attribute sets and the well-known attribute exploration algorithm from formal concept analysis. To this end, we introduce (weak) local experts for subdomains of a given knowledge domain. These entities are able to refute and potentially accept a given (implicational) query for some closure system that is a restriction of the whole domain. On this we build up a consortial expert and show first insights about the ability of such an expert to answer queries. Furthermore, we depict techniques on how to cope with falsely accepted implications and on combining counterexamples. Using notions from combinatorial design theory we further expand those insights as far as providing first results on the decidability problem if a given consortium is able to explore some target domain. Applications in conceptual knowledge acquisition as well as in collaborative interactive ontology learning are at hand.
Tasks
Published	2017-12-23
URL	http://arxiv.org/abs/1712.08858v2
PDF	http://arxiv.org/pdf/1712.08858v2.pdf
PWC	https://paperswithcode.com/paper/towards-collaborative-conceptual-exploration
Repo
Framework

Inferring agent objectives at different scales of a complex adaptive system


Title	Inferring agent objectives at different scales of a complex adaptive system
Authors	Dieter Hendricks, Adam Cobb, Richard Everett, Jonathan Downing, Stephen J. Roberts
Abstract	We introduce a framework to study the effective objectives at different time scales of financial market microstructure. The financial market can be regarded as a complex adaptive system, where purposeful agents collectively and simultaneously create and perceive their environment as they interact with it. It has been suggested that multiple agent classes operate in this system, with a non-trivial hierarchy of top-down and bottom-up causation classes with different effective models governing each level. We conjecture that agent classes may in fact operate at different time scales and thus act differently in response to the same perceived market state. Given scale-specific temporal state trajectories and action sequences estimated from aggregate market behaviour, we use Inverse Reinforcement Learning to compute the effective reward function for the aggregate agent class at each scale, allowing us to assess the relative attractiveness of feature vectors across different scales. Differences in reward functions for feature vectors may indicate different objectives of market participants, which could assist in finding the scale boundary for agent classes. This has implications for learning algorithms operating in this domain.
Tasks
Published	2017-12-04
URL	http://arxiv.org/abs/1712.01137v1
PDF	http://arxiv.org/pdf/1712.01137v1.pdf
PWC	https://paperswithcode.com/paper/inferring-agent-objectives-at-different
Repo
Framework

Multi-view Unsupervised Feature Selection by Cross-diffused Matrix Alignment


Title	Multi-view Unsupervised Feature Selection by Cross-diffused Matrix Alignment
Authors	Xiaokai Wei, Bokai Cao, Philip S. Yu
Abstract	Multi-view high-dimensional data become increasingly popular in the big data era. Feature selection is a useful technique for alleviating the curse of dimensionality in multi-view learning. In this paper, we study unsupervised feature selection for multi-view data, as class labels are usually expensive to obtain. Traditional feature selection methods are mostly designed for single-view data and cannot fully exploit the rich information from multi-view data. Existing multi-view feature selection methods are usually based on noisy cluster labels which might not preserve sufficient information from multi-view data. To better utilize multi-view information, we propose a method, CDMA-FS, to select features for each view by performing alignment on a cross diffused matrix. We formulate it as a constrained optimization problem and solve it using Quasi-Newton based method. Experiments results on four real-world datasets show that the proposed method is more effective than the state-of-the-art methods in multi-view setting.
Tasks	Feature Selection, MULTI-VIEW LEARNING
Published	2017-05-02
URL	http://arxiv.org/abs/1705.00825v1
PDF	http://arxiv.org/pdf/1705.00825v1.pdf
PWC	https://paperswithcode.com/paper/multi-view-unsupervised-feature-selection-by
Repo
Framework

Polar Transformer Networks


Title	Polar Transformer Networks
Authors	Carlos Esteves, Christine Allen-Blanchette, Xiaowei Zhou, Kostas Daniilidis
Abstract	Convolutional neural networks (CNNs) are inherently equivariant to translation. Efforts to embed other forms of equivariance have concentrated solely on rotation. We expand the notion of equivariance in CNNs through the Polar Transformer Network (PTN). PTN combines ideas from the Spatial Transformer Network (STN) and canonical coordinate representations. The result is a network invariant to translation and equivariant to both rotation and scale. PTN is trained end-to-end and composed of three distinct stages: a polar origin predictor, the newly introduced polar transformer module and a classifier. PTN achieves state-of-the-art on rotated MNIST and the newly introduced SIM2MNIST dataset, an MNIST variation obtained by adding clutter and perturbing digits with translation, rotation and scaling. The ideas of PTN are extensible to 3D which we demonstrate through the Cylindrical Transformer Network.
Tasks
Published	2017-09-06
URL	http://arxiv.org/abs/1709.01889v3
PDF	http://arxiv.org/pdf/1709.01889v3.pdf
PWC	https://paperswithcode.com/paper/polar-transformer-networks
Repo
Framework

Decoupled Learning of Environment Characteristics for Safe Exploration


Title	Decoupled Learning of Environment Characteristics for Safe Exploration
Authors	Pieter Van Molle, Tim Verbelen, Steven Bohez, Sam Leroux, Pieter Simoens, Bart Dhoedt
Abstract	Reinforcement learning is a proven technique for an agent to learn a task. However, when learning a task using reinforcement learning, the agent cannot distinguish the characteristics of the environment from those of the task. This makes it harder to transfer skills between tasks in the same environment. Furthermore, this does not reduce risk when training for a new task. In this paper, we introduce an approach to decouple the environment characteristics from the task-specific ones, allowing an agent to develop a sense of survival. We evaluate our approach in an environment where an agent must learn a sequence of collection tasks, and show that decoupled learning allows for a safer utilization of prior knowledge.
Tasks	Safe Exploration
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02838v1
PDF	http://arxiv.org/pdf/1708.02838v1.pdf
PWC	https://paperswithcode.com/paper/decoupled-learning-of-environment
Repo
Framework

Simplifying the Bible and Wikipedia Using Statistical Machine Translation


Title	Simplifying the Bible and Wikipedia Using Statistical Machine Translation
Authors	Yohan Jo
Abstract	I started this work with the hope of generating a text synthesizer (like a musical synthesizer) that can imitate certain linguistic styles. Most of the report focuses on text simplification using statistical machine translation (SMT) techniques. I applied MOSES to a parallel corpus of the Bible (King James Version and Easy-to-Read Version) and that of Wikipedia articles (normal and simplified). I report the importance of the three main components of SMT—phrase translation, language model, and recording—by changing their weights and comparing the resulting quality of simplified text in terms of METEOR and BLEU. Toward the end of the report will be presented some examples of text “synthesized” into the King James style.
Tasks	Language Modelling, Machine Translation, Text Simplification
Published	2017-03-25
URL	http://arxiv.org/abs/1703.08646v1
PDF	http://arxiv.org/pdf/1703.08646v1.pdf
PWC	https://paperswithcode.com/paper/simplifying-the-bible-and-wikipedia-using
Repo
Framework

Linguistic Reflexes of Well-Being and Happiness in Echo


Title	Linguistic Reflexes of Well-Being and Happiness in Echo
Authors	Jiaqi Wu, Marilyn Walker, Pranav Anand, Steve Whittaker
Abstract	Different theories posit different sources for feelings of well-being and happiness. Appraisal theory grounds our emotional responses in our goals and desires and their fulfillment, or lack of fulfillment. Self Determination theory posits that the basis for well-being rests on our assessment of our competence, autonomy, and social connection. And surveys that measure happiness empirically note that people require their basic needs to be met for food and shelter, but beyond that tend to be happiest when socializing, eating or having sex. We analyze a corpus of private microblogs from a well-being application called ECHO, where users label each written post about daily events with a happiness score between 1 and 9. Our goal is to ground the linguistic descriptions of events that users experience in theories of well-being and happiness, and then examine the extent to which different theoretical accounts can explain the variance in the happiness scores. We show that recurrent event types, such as OBLIGATION and INCOMPETENCE, which affect people’s feelings of well-being are not captured in current lexical or semantic resources.
Tasks
Published	2017-08-31
URL	http://arxiv.org/abs/1709.00094v1
PDF	http://arxiv.org/pdf/1709.00094v1.pdf
PWC	https://paperswithcode.com/paper/linguistic-reflexes-of-well-being-and
Repo
Framework

Protein Folding Optimization using Differential Evolution Extended with Local Search and Component Reinitialization


Title	Protein Folding Optimization using Differential Evolution Extended with Local Search and Component Reinitialization
Authors	Borko Bošković, Janez Brest
Abstract	This paper presents a novel Differential Evolution algorithm for protein folding optimization that is applied to a three-dimensional AB off-lattice model. The proposed algorithm includes two new mechanisms. A local search is used to improve convergence speed and to reduce the runtime complexity of the energy calculation. For this purpose, a local movement is introduced within the local search. The designed evolutionary algorithm has fast convergence speed and, therefore, when it is trapped into the local optimum or a relatively good solution is located, it is hard to locate a better similar solution. The similar solution is different from the good solution in only a few components. A component reinitialization method is designed to mitigate this problem. Both the new mechanisms and the proposed algorithm were analyzed on well-known amino acid sequences that are used frequently in the literature. Experimental results show that the employed new mechanisms improve the efficiency of our algorithm and that the proposed algorithm is superior to other state-of-the-art algorithms. It obtained a hit ratio of 100% for sequences up to 18 monomers, within a budget of $10^{11}$ solution evaluations. New best-known solutions were obtained for most of the sequences. The existence of the symmetric best-known solutions is also demonstrated in the paper.
Tasks
Published	2017-10-19
URL	http://arxiv.org/abs/1710.07031v2
PDF	http://arxiv.org/pdf/1710.07031v2.pdf
PWC	https://paperswithcode.com/paper/protein-folding-optimization-using
Repo
Framework

SyGuS-Comp 2017: Results and Analysis


Title	SyGuS-Comp 2017: Results and Analysis
Authors	Rajeev Alur, Dana Fisman, Rishabh Singh, Armando Solar-Lezama
Abstract	Syntax-Guided Synthesis (SyGuS) is the computational problem of finding an implementation f that meets both a semantic constraint given by a logical formula phi in a background theory T, and a syntactic constraint given by a grammar G, which specifies the allowed set of candidate implementations. Such a synthesis problem can be formally defined in SyGuS-IF, a language that is built on top of SMT-LIB. The Syntax-Guided Synthesis Competition (SyGuS-Comp) is an effort to facilitate, bring together and accelerate research and development of efficient solvers for SyGuS by providing a platform for evaluating different synthesis techniques on a comprehensive set of benchmarks. In this year’s competition six new solvers competed on over 1500 benchmarks. This paper presents and analyses the results of SyGuS-Comp’17.
Tasks
Published	2017-11-29
URL	http://arxiv.org/abs/1711.11438v1
PDF	http://arxiv.org/pdf/1711.11438v1.pdf
PWC	https://paperswithcode.com/paper/sygus-comp-2017-results-and-analysis
Repo
Framework

A Syllable-based Technique for Word Embeddings of Korean Words


Title	A Syllable-based Technique for Word Embeddings of Korean Words
Authors	Sanghyuk Choi, Taeuk Kim, Jinseok Seol, Sang-goo Lee
Abstract	Word embedding has become a fundamental component to many NLP tasks such as named entity recognition and machine translation. However, popular models that learn such embeddings are unaware of the morphology of words, so it is not directly applicable to highly agglutinative languages such as Korean. We propose a syllable-based learning model for Korean using a convolutional neural network, in which word representation is composed of trained syllable vectors. Our model successfully produces morphologically meaningful representation of Korean words compared to the original Skip-gram embeddings. The results also show that it is quite robust to the Out-of-Vocabulary problem.
Tasks	Machine Translation, Named Entity Recognition, Word Embeddings
Published	2017-08-05
URL	http://arxiv.org/abs/1708.01766v1
PDF	http://arxiv.org/pdf/1708.01766v1.pdf
PWC	https://paperswithcode.com/paper/a-syllable-based-technique-for-word
Repo
Framework

Semi-Supervised Instance Population of an Ontology using Word Vector Embeddings


Title	Semi-Supervised Instance Population of an Ontology using Word Vector Embeddings
Authors	Vindula Jayawardana, Dimuthu Lakmal, Nisansa de Silva, Amal Shehan Perera, Keet Sugathadasa, Buddhi Ayesha, Madhavi Perera
Abstract	In many modern day systems such as information extraction and knowledge management agents, ontologies play a vital role in maintaining the concept hierarchies of the selected domain. However, ontology population has become a problematic process due to its nature of heavy coupling with manual human intervention. With the use of word embeddings in the field of natural language processing, it became a popular topic due to its ability to cope up with semantic sensitivity. Hence, in this study, we propose a novel way of semi-supervised ontology population through word embeddings as the basis. We built several models including traditional benchmark models and new types of models which are based on word embeddings. Finally, we ensemble them together to come up with a synergistic model with better accuracy. We demonstrate that our ensemble model can outperform the individual models.
Tasks	Word Embeddings
Published	2017-09-09
URL	http://arxiv.org/abs/1709.02911v1
PDF	http://arxiv.org/pdf/1709.02911v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-instance-population-of-an
Repo
Framework

Bootstrapped Graph Diffusions: Exposing the Power of Nonlinearity


Title	Bootstrapped Graph Diffusions: Exposing the Power of Nonlinearity
Authors	Eliav Buchnik, Edith Cohen
Abstract	Graph-based semi-supervised learning (SSL) algorithms predict labels for all nodes based on provided labels of a small set of seed nodes. Classic methods capture the graph structure through some underlying diffusion process that propagates through the graph edges. Spectral diffusion, which includes personalized page rank and label propagation, propagates through random walks. Social diffusion propagates through shortest paths. A common ground to these diffusions is their {\em linearity}, which does not distinguish between contributions of few “strong” relations and many “weak” relations. Recently, non-linear methods such as node embeddings and graph convolutional networks (GCN) demonstrated a large gain in quality for SSL tasks. These methods introduce multiple components and greatly vary on how the graph structure, seed label information, and other features are used. We aim here to study the contribution of non-linearity, as an isolated ingredient, to the performance gain. To do so, we place classic linear graph diffusions in a self-training framework. Surprisingly, we observe that SSL using the resulting {\em bootstrapped diffusions} not only significantly improves over the respective non-bootstrapped baselines but also outperform state-of-the-art non-linear SSL methods. Moreover, since the self-training wrapper retains the scalability of the base method, we obtain both higher quality and better scalability.
Tasks
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02618v2
PDF	http://arxiv.org/pdf/1703.02618v2.pdf
PWC	https://paperswithcode.com/paper/bootstrapped-graph-diffusions-exposing-the
Repo
Framework

Imitation Learning for Vision-based Lane Keeping Assistance


Title	Imitation Learning for Vision-based Lane Keeping Assistance
Authors	Christopher Innocenti, Henrik Lindén, Ghazaleh Panahandeh, Lennart Svensson, Nasser Mohammadiha
Abstract	This paper aims to investigate direct imitation learning from human drivers for the task of lane keeping assistance in highway and country roads using grayscale images from a single front view camera. The employed method utilizes convolutional neural networks (CNN) to act as a policy that is driving a vehicle. The policy is successfully learned via imitation learning using real-world data collected from human drivers and is evaluated in closed-loop simulated environments, demonstrating good driving behaviour and a robustness for domain changes. Evaluation is based on two proposed performance metrics measuring how well the vehicle is positioned in a lane and the smoothness of the driven trajectory.
Tasks	Imitation Learning
Published	2017-09-12
URL	http://arxiv.org/abs/1709.03853v1
PDF	http://arxiv.org/pdf/1709.03853v1.pdf
PWC	https://paperswithcode.com/paper/imitation-learning-for-vision-based-lane
Repo
Framework

Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models


Title	Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models
Authors	Bing Liu, Ian Lane
Abstract	In this paper, we present a deep reinforcement learning (RL) framework for iterative dialog policy optimization in end-to-end task-oriented dialog systems. Popular approaches in learning dialog policy with RL include letting a dialog agent to learn against a user simulator. Building a reliable user simulator, however, is not trivial, often as difficult as building a good dialog agent. We address this challenge by jointly optimizing the dialog agent and the user simulator with deep RL by simulating dialogs between the two agents. We first bootstrap a basic dialog agent and a basic user simulator by learning directly from dialog corpora with supervised training. We then improve them further by letting the two agents to conduct task-oriented dialogs and iteratively optimizing their policies with deep RL. Both the dialog agent and the user simulator are designed with neural network models that can be trained end-to-end. Our experiment results show that the proposed method leads to promising improvements on task success rate and total task reward comparing to supervised training and single-agent RL training baseline models.
Tasks
Published	2017-09-18
URL	http://arxiv.org/abs/1709.06136v1
PDF	http://arxiv.org/pdf/1709.06136v1.pdf
PWC	https://paperswithcode.com/paper/iterative-policy-learning-in-end-to-end
Repo
Framework

Critical Survey of the Freely Available Arabic Corpora


Title	Critical Survey of the Freely Available Arabic Corpora
Authors	Wajdi Zaghouani
Abstract	The availability of corpora is a major factor in building natural language processing applications. However, the costs of acquiring corpora can prevent some researchers from going further in their endeavours. The ease of access to freely available corpora is urgent needed in the NLP research community especially for language such as Arabic. Currently, there is not easy was to access to a comprehensive and updated list of freely available Arabic corpora. We present in this paper, the results of a recent survey conducted to identify the list of the freely available Arabic corpora and language resources. Our preliminary results showed an initial list of 66 sources. We presents our findings in the various categories studied and we provided the direct links to get the data when possible.
Tasks
Published	2017-02-25
URL	http://arxiv.org/abs/1702.07835v1
PDF	http://arxiv.org/pdf/1702.07835v1.pdf
PWC	https://paperswithcode.com/paper/critical-survey-of-the-freely-available
Repo
Framework