October 17, 2019

2927 words 14 mins read

Paper Group ANR 734

Collapsed Variational Inference for Nonparametric Bayesian Group Factor Analysis. Entity Retrieval and Text Mining for Online Reputation Monitoring. Automatic Rendering of Building Floor Plan Images from Textual Descriptions in English. Implicit Argument Prediction as Reading Comprehension. Learning Bounds for Greedy Approximation with Explicit Fea …

Collapsed Variational Inference for Nonparametric Bayesian Group Factor Analysis


Title	Collapsed Variational Inference for Nonparametric Bayesian Group Factor Analysis
Authors	Sikun Yang, Heinz Koeppl
Abstract	Group factor analysis (GFA) methods have been widely used to infer the common structure and the group-specific signals from multiple related datasets in various fields including systems biology and neuroimaging. To date, most available GFA models require Gibbs sampling or slice sampling to perform inference, which prevents the practical application of GFA to large-scale data. In this paper we present an efficient collapsed variational inference (CVI) algorithm for the nonparametric Bayesian group factor analysis (NGFA) model built upon an hierarchical beta Bernoulli process. Our CVI algorithm proceeds by marginalizing out the group-specific beta process parameters, and then approximating the true posterior in the collapsed space using mean field methods. Experimental results on both synthetic and real-world data demonstrate the effectiveness of our CVI algorithm for the NGFA compared with state-of-the-art GFA methods.
Tasks
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03566v2
PDF	http://arxiv.org/pdf/1809.03566v2.pdf
PWC	https://paperswithcode.com/paper/collapsed-variational-inference-for
Repo
Framework

Entity Retrieval and Text Mining for Online Reputation Monitoring


Title	Entity Retrieval and Text Mining for Online Reputation Monitoring
Authors	Pedro Saleiro
Abstract	Online Reputation Monitoring (ORM) is concerned with the use of computational tools to measure the reputation of entities online, such as politicians or companies. In practice, current ORM methods are constrained to the generation of data analytics reports, which aggregate statistics of popularity and sentiment on social media. We argue that this format is too restrictive as end users often like to have the flexibility to search for entity-centric information that is not available in predefined charts. As such, we propose the inclusion of entity retrieval capabilities as a first step towards the extension of current ORM capabilities. However, an entity’s reputation is also influenced by the entity’s relationships with other entities. Therefore, we address the problem of Entity-Relationship (E-R) retrieval in which the goal is to search for multiple connected entities. This is a challenging problem which traditional entity search systems cannot cope with. Besides E-R retrieval we also believe ORM would benefit of text-based entity-centric prediction capabilities, such as predicting entity popularity on social media based on news events or the outcome of political surveys. However, none of these tasks can provide useful results if there is no effective entity disambiguation and sentiment analysis tailored to the context of ORM. Consequently, this thesis address two computational problems in Online Reputation Monitoring: Entity Retrieval and Text Mining. We researched and developed methods to extract, retrieve and predict entity-centric information spread across the Web.
Tasks	Entity Disambiguation, Sentiment Analysis
Published	2018-01-23
URL	http://arxiv.org/abs/1801.07743v1
PDF	http://arxiv.org/pdf/1801.07743v1.pdf
PWC	https://paperswithcode.com/paper/entity-retrieval-and-text-mining-for-online
Repo
Framework

Automatic Rendering of Building Floor Plan Images from Textual Descriptions in English


Title	Automatic Rendering of Building Floor Plan Images from Textual Descriptions in English
Authors	Mahak Jain, Anurag Sanyal, Shreya Goyal, Chiranjoy Chattopadhyay, Gaurav Bhatnagar
Abstract	Human beings understand natural language description and could able to imagine a corresponding visual for the same. For example, given a description of the interior of a house, we could imagine its structure and arrangements of furniture. Automatic synthesis of real-world images from text descriptions has been explored in the computer vision community. However, there is no such attempt in the area of document images, like floor plans. Floor plan synthesis from sketches, as well as data-driven models, were proposed earlier. Ours is the first attempt to render building floor plan images from textual description automatically. Here, the input is a natural language description of the internal structure and furniture arrangements within a house, and the output is the 2D floor plan image of the same. We have experimented on publicly available benchmark floor plan datasets. We were able to render realistic synthesized floor plan images from the description written in English.
Tasks
Published	2018-11-29
URL	http://arxiv.org/abs/1811.11938v1
PDF	http://arxiv.org/pdf/1811.11938v1.pdf
PWC	https://paperswithcode.com/paper/automatic-rendering-of-building-floor-plan
Repo
Framework

Implicit Argument Prediction as Reading Comprehension


Title	Implicit Argument Prediction as Reading Comprehension
Authors	Pengxiang Cheng, Katrin Erk
Abstract	Implicit arguments, which cannot be detected solely through syntactic cues, make it harder to extract predicate-argument tuples. We present a new model for implicit argument prediction that draws on reading comprehension, casting the predicate-argument tuple with the missing argument as a query. We also draw on pointer networks and multi-hop computation. Our model shows good performance on an argument cloze task as well as on a nominal implicit argument prediction task.
Tasks	Reading Comprehension
Published	2018-11-08
URL	http://arxiv.org/abs/1811.03554v1
PDF	http://arxiv.org/pdf/1811.03554v1.pdf
PWC	https://paperswithcode.com/paper/implicit-argument-prediction-as-reading
Repo
Framework

Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple Kernels


Title	Learning Bounds for Greedy Approximation with Explicit Feature Maps from Multiple Kernels
Authors	Shahin Shahrampour, Vahid Tarokh
Abstract	Nonlinear kernels can be approximated using finite-dimensional feature maps for efficient risk minimization. Due to the inherent trade-off between the dimension of the (mapped) feature space and the approximation accuracy, the key problem is to identify promising (explicit) features leading to a satisfactory out-of-sample performance. In this work, we tackle this problem by efficiently choosing such features from multiple kernels in a greedy fashion. Our method sequentially selects these explicit features from a set of candidate features using a correlation metric. We establish an out-of-sample error bound capturing the trade-off between the error in terms of explicit features (approximation error) and the error due to spectral properties of the best model in the Hilbert space associated to the combined kernel (spectral error). The result verifies that when the (best) underlying data model is sparse enough, i.e., the spectral error is negligible, one can control the test error with a small number of explicit features, that can scale poly-logarithmically with data. Our empirical results show that given a fixed number of explicit features, the method can achieve a lower test error with a smaller time cost, compared to the state-of-the-art in data-dependent random features.
Tasks
Published	2018-10-09
URL	http://arxiv.org/abs/1810.03817v1
PDF	http://arxiv.org/pdf/1810.03817v1.pdf
PWC	https://paperswithcode.com/paper/learning-bounds-for-greedy-approximation-with
Repo
Framework

Automated Classification of Text Sentiment


Title	Automated Classification of Text Sentiment
Authors	Emmanuel Dufourq, Bruce A. Bassett
Abstract	The ability to identify sentiment in text, referred to as sentiment analysis, is one which is natural to adult humans. This task is, however, not one which a computer can perform by default. Identifying sentiments in an automated, algorithmic manner will be a useful capability for business and research in their search to understand what consumers think about their products or services and to understand human sociology. Here we propose two new Genetic Algorithms (GAs) for the task of automated text sentiment analysis. The GAs learn whether words occurring in a text corpus are either sentiment or amplifier words, and their corresponding magnitude. Sentiment words, such as ‘horrible’, add linearly to the final sentiment. Amplifier words in contrast, which are typically adjectives/adverbs like ‘very’, multiply the sentiment of the following word. This increases, decreases or negates the sentiment of the following word. The sentiment of the full text is then the sum of these terms. This approach grows both a sentiment and amplifier dictionary which can be reused for other purposes and fed into other machine learning algorithms. We report the results of multiple experiments conducted on large Amazon data sets. The results reveal that our proposed approach was able to outperform several public and/or commercial sentiment analysis algorithms.
Tasks	Sentiment Analysis
Published	2018-04-05
URL	http://arxiv.org/abs/1804.01963v1
PDF	http://arxiv.org/pdf/1804.01963v1.pdf
PWC	https://paperswithcode.com/paper/automated-classification-of-text-sentiment
Repo
Framework

Curriculum-Based Neighborhood Sampling For Sequence Prediction


Title	Curriculum-Based Neighborhood Sampling For Sequence Prediction
Authors	James O’ Neill, Danushka Bollegala
Abstract	The task of multi-step ahead prediction in language models is challenging considering the discrepancy between training and testing. At test time, a language model is required to make predictions given past predictions as input, instead of the past targets that are provided during training. This difference, known as exposure bias, can lead to the compounding of errors along a generated sequence at test time. In order to improve generalization in neural language models and address compounding errors, we propose a curriculum learning based method that gradually changes an initially deterministic teacher policy to a gradually more stochastic policy, which we refer to as \textit{Nearest-Neighbor Replacement Sampling}. A chosen input at a given timestep is replaced with a sampled nearest neighbor of the past target with a truncated probability proportional to the cosine similarity between the original word and its top $k$ most similar words. This allows the teacher to explore alternatives when the teacher provides a sub-optimal policy or when the initial policy is difficult for the learner to model. The proposed strategy is straightforward, online and requires little additional memory requirements. We report our main findings on two language modelling benchmarks and find that the proposed approach performs particularly well when used in conjunction with scheduled sampling, that too attempts to mitigate compounding errors in language models.
Tasks	Language Modelling
Published	2018-09-16
URL	http://arxiv.org/abs/1809.05916v1
PDF	http://arxiv.org/pdf/1809.05916v1.pdf
PWC	https://paperswithcode.com/paper/curriculum-based-neighborhood-sampling-for
Repo
Framework

Modelling cross-dependencies between Spain’s regional tourism markets with an extension of the Gaussian process regression model


Title	Modelling cross-dependencies between Spain’s regional tourism markets with an extension of the Gaussian process regression model
Authors	Oscar Claveria, Enric Monte, Salvador Torra
Abstract	This study presents an extension of the Gaussian process regression model for multiple-input multiple-output forecasting. This approach allows modelling the cross-dependencies between a given set of input variables and generating a vectorial prediction. Making use of the existing correlations in international tourism demand to all seventeen regions of Spain, the performance of the proposed model is assessed in a multiple-step-ahead forecasting comparison. The results of the experiment in a multivariate setting show that the Gaussian process regression model significantly improves the forecasting accuracy of a multi-layer perceptron neural network used as a benchmark. The results reveal that incorporating the connections between different markets in the modelling process may prove very useful to refine predictions at a regional level.
Tasks
Published	2018-05-02
URL	http://arxiv.org/abs/1805.00861v1
PDF	http://arxiv.org/pdf/1805.00861v1.pdf
PWC	https://paperswithcode.com/paper/modelling-cross-dependencies-between-spains
Repo
Framework

Simulation to Scaled City: Zero-Shot Policy Transfer for Traffic Control via Autonomous Vehicles


Title	Simulation to Scaled City: Zero-Shot Policy Transfer for Traffic Control via Autonomous Vehicles
Authors	Kathy Jang, Eugene Vinitsky, Behdad Chalaki, Ben Remer, Logan Beaver, Andreas Malikopoulos, Alexandre Bayen
Abstract	Using deep reinforcement learning, we train control policies for autonomous vehicles leading a platoon of vehicles onto a roundabout. Using Flow, a library for deep reinforcement learning in micro-simulators, we train two policies, one policy with noise injected into the state and action space and one without any injected noise. In simulation, the autonomous vehicle learns an emergent metering behavior for both policies in which it slows to allow for smoother merging. We then directly transfer this policy without any tuning to the University of Delaware Scaled Smart City (UDSSC), a 1:25 scale testbed for connected and automated vehicles. We characterize the performance of both policies on the scaled city. We show that the noise-free policy winds up crashing and only occasionally metering. However, the noise-injected policy consistently performs the metering behavior and remains collision-free, suggesting that the noise helps with the zero-shot policy transfer. Additionally, the transferred, noise-injected policy leads to a 5% reduction of average travel time and a reduction of 22% in maximum travel time in the UDSSC. Videos of the controllers can be found at https://sites.google.com/view/iccps-policy-transfer.
Tasks	Autonomous Vehicles
Published	2018-12-14
URL	http://arxiv.org/abs/1812.06120v2
PDF	http://arxiv.org/pdf/1812.06120v2.pdf
PWC	https://paperswithcode.com/paper/simulation-to-scaled-city-zero-shot-policy
Repo
Framework

Similarity between Learning Outcomes from Course Objectives using Semantic Analysis, Blooms taxonomy and Corpus statistics


Title	Similarity between Learning Outcomes from Course Objectives using Semantic Analysis, Blooms taxonomy and Corpus statistics
Authors	Atish Pawar, Vijay Mago
Abstract	The course description provided by instructors is an essential piece of information as it defines what is expected from the instructor and what he/she is going to deliver during a particular course. One of the key components of a course description is the Learning Objectives section. The contents of this section are used by program managers who are tasked to compare and match two different courses during the development of Transfer Agreements between various institutions. This research introduces the development of semantic similarity algorithms to calculate the similarity between two learning objectives of the same domain. We present a novel methodology which deals with the semantic similarity by using a previously established algorithm and integrating it with the domain corpus utilizing domain statistics. The disambiguated domain serves as a supervised learning data for the algorithm. We also introduce Bloom Index to calculate the similarity between action verbs in the Learning Objectives referring to the Blooms taxonomy.
Tasks	Semantic Similarity, Semantic Textual Similarity
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06333v1
PDF	http://arxiv.org/pdf/1804.06333v1.pdf
PWC	https://paperswithcode.com/paper/similarity-between-learning-outcomes-from
Repo
Framework

Adversarial confidence and smoothness regularizations for scalable unsupervised discriminative learning


Title	Adversarial confidence and smoothness regularizations for scalable unsupervised discriminative learning
Authors	Yi-Qing Wang
Abstract	In this paper, we consider a generic probabilistic discriminative learner from the functional viewpoint and argue that, to make it learn well, it is necessary to constrain its hypothesis space to a set of non-trivial piecewise constant functions. To achieve this goal, we present a scalable unsupervised regularization framework. On the theoretical front, we prove that this framework is conducive to a factually confident and smooth discriminative model and connect it to an adversarial Taboo game, spectral clustering and virtual adversarial training. Experimentally, we take deep neural networks as our learners and demonstrate that, when trained under our framework in the unsupervised setting, they not only achieve state-of-the-art clustering results but also generalize well on both synthetic and real data.
Tasks
Published	2018-06-04
URL	http://arxiv.org/abs/1806.00919v1
PDF	http://arxiv.org/pdf/1806.00919v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-confidence-and-smoothness
Repo
Framework

Contextual Slot Carryover for Disparate Schemas


Title	Contextual Slot Carryover for Disparate Schemas
Authors	Chetan Naik, Arpit Gupta, Hancheng Ge, Lambert Mathias, Ruhi Sarikaya
Abstract	In the slot-filling paradigm, where a user can refer back to slots in the context during a conversation, the goal of the contextual understanding system is to resolve the referring expressions to the appropriate slots in the context. In large-scale multi-domain systems, this presents two challenges - scaling to a very large and potentially unbounded set of slot values, and dealing with diverse schemas. We present a neural network architecture that addresses the slot value scalability challenge by reformulating the contextual interpretation as a decision to carryover a slot from a set of possible candidates. To deal with heterogenous schemas, we introduce a simple data-driven method for trans- forming the candidate slots. Our experiments show that our approach can scale to multiple domains and provides competitive results over a strong baseline.
Tasks	Slot Filling
Published	2018-06-05
URL	http://arxiv.org/abs/1806.01773v1
PDF	http://arxiv.org/pdf/1806.01773v1.pdf
PWC	https://paperswithcode.com/paper/contextual-slot-carryover-for-disparate
Repo
Framework

A New Approach for Resource Scheduling with Deep Reinforcement Learning


Title	A New Approach for Resource Scheduling with Deep Reinforcement Learning
Authors	Yufei Ye, Xiaoqin Ren, Jin Wang, Lingxiao Xu, Wenxia Guo, Wenqiang Huang, Wenhong Tian
Abstract	With the rapid development of deep learning, deep reinforcement learning (DRL) began to appear in the field of resource scheduling in recent years. Based on the previous research on DRL in the literature, we introduce online resource scheduling algorithm DeepRM2 and the offline resource scheduling algorithm DeepRM_Off. Compared with the state-of-the-art DRL algorithm DeepRM and heuristic algorithms, our proposed algorithms have faster convergence speed and better scheduling efficiency with regarding to average slowdown time, job completion time and rewards.
Tasks
Published	2018-06-21
URL	http://arxiv.org/abs/1806.08122v1
PDF	http://arxiv.org/pdf/1806.08122v1.pdf
PWC	https://paperswithcode.com/paper/a-new-approach-for-resource-scheduling-with
Repo
Framework

Imaging with SPADs and DMDs: Seeing through Diffraction-Photons


Title	Imaging with SPADs and DMDs: Seeing through Diffraction-Photons
Authors	Ibrahim Alsolami, Wolfgang Heidrich
Abstract	This paper addresses the problem of imaging in the presence of diffraction-photons. Diffraction-photons arise from the low contrast ratio of DMDs ($\sim,1000:1$), and very much degrade the quality of images captured by SPAD-based systems. Herein, a joint illumination-deconvolution scheme is designed to overcome diffraction-photons, enabling the acquisition of intensity and depth images. Additionally, a proof-of-concept experiment is conducted to demonstrate the viability of the designed scheme. It is shown that by co-designing the illumination and deconvolution phases of imaging, one can substantially overcome diffraction-photons.
Tasks
Published	2018-05-31
URL	https://arxiv.org/abs/1806.00094v2
PDF	https://arxiv.org/pdf/1806.00094v2.pdf
PWC	https://paperswithcode.com/paper/imaging-with-spads-and-dmds-seeing-through
Repo
Framework

Infrastructure Quality Assessment in Africa using Satellite Imagery and Deep Learning


Title	Infrastructure Quality Assessment in Africa using Satellite Imagery and Deep Learning
Authors	Barak Oshri, Annie Hu, Peter Adelson, Xiao Chen, Pascaline Dupas, Jeremy Weinstein, Marshall Burke, David Lobell, Stefano Ermon
Abstract	The UN Sustainable Development Goals allude to the importance of infrastructure quality in three of its seventeen goals. However, monitoring infrastructure quality in developing regions remains prohibitively expensive and impedes efforts to measure progress toward these goals. To this end, we investigate the use of widely available remote sensing data for the prediction of infrastructure quality in Africa. We train a convolutional neural network to predict ground truth labels from the Afrobarometer Round 6 survey using Landsat 8 and Sentinel 1 satellite imagery. Our best models predict infrastructure quality with AUROC scores of 0.881 on Electricity, 0.862 on Sewerage, 0.739 on Piped Water, and 0.786 on Roads using Landsat 8. These performances are significantly better than models that leverage OpenStreetMap or nighttime light intensity on the same tasks. We also demonstrate that our trained model can accurately make predictions in an unseen country after fine-tuning on a small sample of images. Furthermore, the model can be deployed in regions with limited samples to predict infrastructure outcomes with higher performance than nearest neighbor spatial interpolation.
Tasks
Published	2018-06-03
URL	http://arxiv.org/abs/1806.00894v1
PDF	http://arxiv.org/pdf/1806.00894v1.pdf
PWC	https://paperswithcode.com/paper/infrastructure-quality-assessment-in-africa
Repo
Framework