Paper Group ANR 323
Lexical Disambiguation in Natural Language Questions (NLQs). Building Robust Deep Neural Networks for Road Sign Detection. Adaptive Scaling. Computational Social Choice and Computational Complexity: BFFs?. Text-based Adventures of the Golovin AI Agent. High-Precision Localization Using Ground Texture. Good Arm Identification via Bandit Feedback. Fa …
Lexical Disambiguation in Natural Language Questions (NLQs)
| Title | Lexical Disambiguation in Natural Language Questions (NLQs) |
| Authors | Omar Al-Harbi, Shaidah Jusoh, Norita Md Norwawi |
| Abstract | Question processing is a fundamental step in a question answering (QA) application, and its quality impacts the performance of QA application. The major challenging issue in processing question is how to extract semantic of natural language questions (NLQs). A human language is ambiguous. Ambiguity may occur at two levels; lexical and syntactic. In this paper, we propose a new approach for resolving lexical ambiguity problem by integrating context knowledge and concepts knowledge of a domain, into shallow natural language processing (SNLP) techniques. Concepts knowledge is modeled using ontology, while context knowledge is obtained from WordNet, and it is determined based on neighborhood words in a question. The approach will be applied to a university QA system. |
| Tasks | Question Answering |
| Published | 2017-09-26 |
| URL | http://arxiv.org/abs/1709.09250v1 |
| http://arxiv.org/pdf/1709.09250v1.pdf | |
| PWC | https://paperswithcode.com/paper/lexical-disambiguation-in-natural-language |
| Repo | |
| Framework | |
Building Robust Deep Neural Networks for Road Sign Detection
| Title | Building Robust Deep Neural Networks for Road Sign Detection |
| Authors | Arkar Min Aung, Yousef Fadila, Radian Gondokaryono, Luis Gonzalez |
| Abstract | Deep Neural Networks are built to generalize outside of training set in mind by using techniques such as regularization, early stopping and dropout. But considerations to make them more resilient to adversarial examples are rarely taken. As deep neural networks become more prevalent in mission-critical and real-time systems, miscreants start to attack them by intentionally making deep neural networks to misclassify an object of one type to be seen as another type. This can be catastrophic in some scenarios where the classification of a deep neural network can lead to a fatal decision by a machine. In this work, we used GTSRB dataset to craft adversarial samples by Fast Gradient Sign Method and Jacobian Saliency Method, used those crafted adversarial samples to attack another Deep Convolutional Neural Network and built the attacked network to be more resilient against adversarial attacks by making it more robust by Defensive Distillation and Adversarial Training |
| Tasks | |
| Published | 2017-12-26 |
| URL | http://arxiv.org/abs/1712.09327v1 |
| http://arxiv.org/pdf/1712.09327v1.pdf | |
| PWC | https://paperswithcode.com/paper/building-robust-deep-neural-networks-for-road |
| Repo | |
| Framework | |
Adaptive Scaling
| Title | Adaptive Scaling |
| Authors | Ting Li, Bingyi Jing, Ningchen Ying, Xianshi Yu |
| Abstract | Preprocessing data is an important step before any data analysis. In this paper, we focus on one particular aspect, namely scaling or normalization. We analyze various scaling methods in common use and study their effects on different statistical learning models. We will propose a new two-stage scaling method. First, we use some training data to fit linear regression model and then scale the whole data based on the coefficients of regression. Simulations are conducted to illustrate the advantages of our new scaling method. Some real data analysis will also be given. |
| Tasks | |
| Published | 2017-09-02 |
| URL | http://arxiv.org/abs/1709.00566v1 |
| http://arxiv.org/pdf/1709.00566v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-scaling |
| Repo | |
| Framework | |
Computational Social Choice and Computational Complexity: BFFs?
| Title | Computational Social Choice and Computational Complexity: BFFs? |
| Authors | Lane A. Hemaspaandra |
| Abstract | We discuss the connection between computational social choice (comsoc) and computational complexity. We stress the work so far on, and urge continued focus on, two less-recognized aspects of this connection. Firstly, this is very much a two-way street: Everyone knows complexity classification is used in comsoc, but we also highlight benefits to complexity that have arisen from its use in comsoc. Secondly, more subtle, less-known complexity tools often can be very productively used in comsoc. |
| Tasks | |
| Published | 2017-10-30 |
| URL | http://arxiv.org/abs/1710.10753v2 |
| http://arxiv.org/pdf/1710.10753v2.pdf | |
| PWC | https://paperswithcode.com/paper/computational-social-choice-and-computational |
| Repo | |
| Framework | |
Text-based Adventures of the Golovin AI Agent
| Title | Text-based Adventures of the Golovin AI Agent |
| Authors | Bartosz Kostka, Jaroslaw Kwiecien, Jakub Kowalski, Pawel Rychlikowski |
| Abstract | The domain of text-based adventure games has been recently established as a new challenge of creating the agent that is both able to understand natural language, and acts intelligently in text-described environments. In this paper, we present our approach to tackle the problem. Our agent, named Golovin, takes advantage of the limited game domain. We use genre-related corpora (including fantasy books and decompiled games) to create language models suitable to this domain. Moreover, we embed mechanisms that allow us to specify, and separately handle, important tasks as fighting opponents, managing inventory, and navigating on the game map. We validated usefulness of these mechanisms, measuring agent’s performance on the set of 50 interactive fiction games. Finally, we show that our agent plays on a level comparable to the winner of the last year Text-Based Adventure AI Competition. |
| Tasks | |
| Published | 2017-05-16 |
| URL | http://arxiv.org/abs/1705.05637v1 |
| http://arxiv.org/pdf/1705.05637v1.pdf | |
| PWC | https://paperswithcode.com/paper/text-based-adventures-of-the-golovin-ai-agent |
| Repo | |
| Framework | |
High-Precision Localization Using Ground Texture
| Title | High-Precision Localization Using Ground Texture |
| Authors | Linguang Zhang, Adam Finkelstein, Szymon Rusinkiewicz |
| Abstract | Location-aware applications play an increasingly critical role in everyday life. However, satellite-based localization (e.g., GPS) has limited accuracy and can be unusable in dense urban areas and indoors. We introduce an image-based global localization system that is accurate to a few millimeters and performs reliable localization both indoors and outside. The key idea is to capture and index distinctive local keypoints in ground textures. This is based on the observation that ground textures including wood, carpet, tile, concrete, and asphalt may look random and homogeneous, but all contain cracks, scratches, or unique arrangements of fibers. These imperfections are persistent, and can serve as local features. Our system incorporates a downward-facing camera to capture the fine texture of the ground, together with an image processing pipeline that locates the captured texture patch in a compact database constructed offline. We demonstrate the capability of our system to robustly, accurately, and quickly locate test images on various types of outdoor and indoor ground surfaces. |
| Tasks | |
| Published | 2017-10-29 |
| URL | https://arxiv.org/abs/1710.10687v3 |
| https://arxiv.org/pdf/1710.10687v3.pdf | |
| PWC | https://paperswithcode.com/paper/high-precision-localization-using-ground |
| Repo | |
| Framework | |
Good Arm Identification via Bandit Feedback
| Title | Good Arm Identification via Bandit Feedback |
| Authors | Hideaki Kano, Junya Honda, Kentaro Sakamaki, Kentaro Matsuura, Atsuyoshi Nakamura, Masashi Sugiyama |
| Abstract | We consider a novel stochastic multi-armed bandit problem called {\em good arm identification} (GAI), where a good arm is defined as an arm with expected reward greater than or equal to a given threshold. GAI is a pure-exploration problem that a single agent repeats a process of outputting an arm as soon as it is identified as a good one before confirming the other arms are actually not good. The objective of GAI is to minimize the number of samples for each process. We find that GAI faces a new kind of dilemma, the {\em exploration-exploitation dilemma of confidence}, which is different difficulty from the best arm identification. As a result, an efficient design of algorithms for GAI is quite different from that for the best arm identification. We derive a lower bound on the sample complexity of GAI that is tight up to the logarithmic factor $\mathrm{O}(\log \frac{1}{\delta})$ for acceptance error rate $\delta$. We also develop an algorithm whose sample complexity almost matches the lower bound. We also confirm experimentally that our proposed algorithm outperforms naive algorithms in synthetic settings based on a conventional bandit problem and clinical trial researches for rheumatoid arthritis. |
| Tasks | |
| Published | 2017-10-17 |
| URL | http://arxiv.org/abs/1710.06360v2 |
| http://arxiv.org/pdf/1710.06360v2.pdf | |
| PWC | https://paperswithcode.com/paper/good-arm-identification-via-bandit-feedback |
| Repo | |
| Framework | |
Faithful Inversion of Generative Models for Effective Amortized Inference
| Title | Faithful Inversion of Generative Models for Effective Amortized Inference |
| Authors | Stefan Webb, Adam Golinski, Robert Zinkov, N. Siddharth, Tom Rainforth, Yee Whye Teh, Frank Wood |
| Abstract | Inference amortization methods share information across multiple posterior-inference problems, allowing each to be carried out more efficiently. Generally, they require the inversion of the dependency structure in the generative model, as the modeller must learn a mapping from observations to distributions approximating the posterior. Previous approaches have involved inverting the dependency structure in a heuristic way that fails to capture these dependencies correctly, thereby limiting the achievable accuracy of the resulting approximations. We introduce an algorithm for faithfully, and minimally, inverting the graphical model structure of any generative model. Such inverses have two crucial properties: (a) they do not encode any independence assertions that are absent from the model and; (b) they are local maxima for the number of true independencies encoded. We prove the correctness of our approach and empirically show that the resulting minimally faithful inverses lead to better inference amortization than existing heuristic approaches. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://arxiv.org/abs/1712.00287v5 |
| http://arxiv.org/pdf/1712.00287v5.pdf | |
| PWC | https://paperswithcode.com/paper/faithful-inversion-of-generative-models-for |
| Repo | |
| Framework | |
SYSTRAN Purely Neural MT Engines for WMT2017
| Title | SYSTRAN Purely Neural MT Engines for WMT2017 |
| Authors | Yongchao Deng, Jungi Kim, Guillaume Klein, Catherine Kobus, Natalia Segal, Christophe Servan, Bo Wang, Dakun Zhang, Josep Crego, Jean Senellart |
| Abstract | This paper describes SYSTRAN’s systems submitted to the WMT 2017 shared news translation task for English-German, in both translation directions. Our systems are built using OpenNMT, an open-source neural machine translation system, implementing sequence-to-sequence models with LSTM encoder/decoders and attention. We experimented using monolingual data automatically back-translated. Our resulting models are further hyper-specialised with an adaptation technique that finely tunes models according to the evaluation test sentences. |
| Tasks | Machine Translation |
| Published | 2017-09-12 |
| URL | http://arxiv.org/abs/1709.03814v1 |
| http://arxiv.org/pdf/1709.03814v1.pdf | |
| PWC | https://paperswithcode.com/paper/systran-purely-neural-mt-engines-for-wmt2017 |
| Repo | |
| Framework | |
Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning
| Title | Summoning Demons: The Pursuit of Exploitable Bugs in Machine Learning |
| Authors | Rock Stevens, Octavian Suciu, Andrew Ruef, Sanghyun Hong, Michael Hicks, Tudor Dumitraş |
| Abstract | Governments and businesses increasingly rely on data analytics and machine learning (ML) for improving their competitive edge in areas such as consumer satisfaction, threat intelligence, decision making, and product efficiency. However, by cleverly corrupting a subset of data used as input to a target’s ML algorithms, an adversary can perturb outcomes and compromise the effectiveness of ML technology. While prior work in the field of adversarial machine learning has studied the impact of input manipulation on correct ML algorithms, we consider the exploitation of bugs in ML implementations. In this paper, we characterize the attack surface of ML programs, and we show that malicious inputs exploiting implementation bugs enable strictly more powerful attacks than the classic adversarial machine learning techniques. We propose a semi-automated technique, called steered fuzzing, for exploring this attack surface and for discovering exploitable bugs in machine learning programs, in order to demonstrate the magnitude of this threat. As a result of our work, we responsibly disclosed five vulnerabilities, established three new CVE-IDs, and illuminated a common insecure practice across many machine learning systems. Finally, we outline several research directions for further understanding and mitigating this threat. |
| Tasks | Decision Making |
| Published | 2017-01-17 |
| URL | http://arxiv.org/abs/1701.04739v1 |
| http://arxiv.org/pdf/1701.04739v1.pdf | |
| PWC | https://paperswithcode.com/paper/summoning-demons-the-pursuit-of-exploitable |
| Repo | |
| Framework | |
One-Class Semi-Supervised Learning: Detecting Linearly Separable Class by its Mean
| Title | One-Class Semi-Supervised Learning: Detecting Linearly Separable Class by its Mean |
| Authors | Evgeny Bauman, Konstantin Bauman |
| Abstract | In this paper, we presented a novel semi-supervised one-class classification algorithm which assumes that class is linearly separable from other elements. We proved theoretically that class is linearly separable if and only if it is maximal by probability within the sets with the same mean. Furthermore, we presented an algorithm for identifying such linearly separable class utilizing linear programming. We described three application cases including an assumption of linear separability, Gaussian distribution, and the case of linear separability in transformed space of kernel functions. Finally, we demonstrated the work of the proposed algorithm on the USPS dataset and analyzed the relationship of the performance of the algorithm and the size of the initially labeled sample. |
| Tasks | |
| Published | 2017-05-02 |
| URL | http://arxiv.org/abs/1705.00797v1 |
| http://arxiv.org/pdf/1705.00797v1.pdf | |
| PWC | https://paperswithcode.com/paper/one-class-semi-supervised-learning-detecting |
| Repo | |
| Framework | |
Improved Clustering with Augmented k-means
| Title | Improved Clustering with Augmented k-means |
| Authors | J. Andrew Howe |
| Abstract | Identifying a set of homogeneous clusters in a heterogeneous dataset is one of the most important classes of problems in statistical modeling. In the realm of unsupervised partitional clustering, k-means is a very important algorithm for this. In this technical report, we develop a new k-means variant called Augmented k-means, which is a hybrid of k-means and logistic regression. During each iteration, logistic regression is used to predict the current cluster labels, and the cluster belonging probabilities are used to control the subsequent re-estimation of cluster means. Observations which can’t be firmly identified into clusters are excluded from the re-estimation step. This can be valuable when the data exhibit many characteristics of real datasets such as heterogeneity, non-sphericity, substantial overlap, and high scatter. Augmented k-means frequently outperforms k-means by more accurately classifying observations into known clusters and / or converging in fewer iterations. We demonstrate this on both simulated and real datasets. Our algorithm is implemented in Python and will be available with this report. |
| Tasks | |
| Published | 2017-05-22 |
| URL | http://arxiv.org/abs/1705.07592v1 |
| http://arxiv.org/pdf/1705.07592v1.pdf | |
| PWC | https://paperswithcode.com/paper/improved-clustering-with-augmented-k-means |
| Repo | |
| Framework | |
Creating Capsule Wardrobes from Fashion Images
| Title | Creating Capsule Wardrobes from Fashion Images |
| Authors | Wei-Lin Hsiao, Kristen Grauman |
| Abstract | We propose to automatically create capsule wardrobes. Given an inventory of candidate garments and accessories, the algorithm must assemble a minimal set of items that provides maximal mix-and-match outfits. We pose the task as a subset selection problem. To permit efficient subset selection over the space of all outfit combinations, we develop submodular objective functions capturing the key ingredients of visual compatibility, versatility, and user-specific preference. Since adding garments to a capsule only expands its possible outfits, we devise an iterative approach to allow near-optimal submodular function maximization. Finally, we present an unsupervised approach to learn visual compatibility from “in the wild” full body outfit photos; the compatibility metric translates well to cleaner catalog photos and improves over existing methods. Our results on thousands of pieces from popular fashion websites show that automatic capsule creation has potential to mimic skilled fashionistas in assembling flexible wardrobes, while being significantly more scalable. |
| Tasks | |
| Published | 2017-12-07 |
| URL | http://arxiv.org/abs/1712.02662v2 |
| http://arxiv.org/pdf/1712.02662v2.pdf | |
| PWC | https://paperswithcode.com/paper/creating-capsule-wardrobes-from-fashion |
| Repo | |
| Framework | |
Taming Adversarial Domain Transfer with Structural Constraints for Image Enhancement
| Title | Taming Adversarial Domain Transfer with Structural Constraints for Image Enhancement |
| Authors | Elias Vansteenkiste, Patrick Kern |
| Abstract | The goal of this work is to improve images of traffic scenes that are degraded by natural causes such as fog, rain and limited visibility during the night. For these applications, it is next to impossible to get pixel perfect pairs of the same scene, with and without the degrading conditions. This makes it unsuitable for conventional supervised learning approaches, however, it is easy to collect unpaired images of the scenes in a perfect and in a degraded condition. To enhance the images taken in a poor visibility condition, domain transfer models can be trained to transform an image from the degraded to the clear domain. A well-known concept for unsupervised domain transfer are cycle-consistent generative adversarial models. Unfortunately, the resulting generators often change the structure of the scene. This causes an undesirable change in the semantics. We propose three ways to cope with this problem depending on the type of degradation. |
| Tasks | Image Enhancement |
| Published | 2017-12-02 |
| URL | http://arxiv.org/abs/1712.00598v3 |
| http://arxiv.org/pdf/1712.00598v3.pdf | |
| PWC | https://paperswithcode.com/paper/taming-adversarial-domain-transfer-with |
| Repo | |
| Framework | |
Groupwise Maximin Fair Allocation of Indivisible Goods
| Title | Groupwise Maximin Fair Allocation of Indivisible Goods |
| Authors | Siddharth Barman, Arpita Biswas, Sanath Kumar Krishnamurthy, Y. Narahari |
| Abstract | We study the problem of allocating indivisible goods among n agents in a fair manner. For this problem, maximin share (MMS) is a well-studied solution concept which provides a fairness threshold. Specifically, maximin share is defined as the minimum utility that an agent can guarantee for herself when asked to partition the set of goods into n bundles such that the remaining (n-1) agents pick their bundles adversarially. An allocation is deemed to be fair if every agent gets a bundle whose valuation is at least her maximin share. Even though maximin shares provide a natural benchmark for fairness, it has its own drawbacks and, in particular, it is not sufficient to rule out unsatisfactory allocations. Motivated by these considerations, in this work we define a stronger notion of fairness, called groupwise maximin share guarantee (GMMS). In GMMS, we require that the maximin share guarantee is achieved not just with respect to the grand bundle, but also among all the subgroups of agents. Hence, this solution concept strengthens MMS and provides an ex-post fairness guarantee. We show that in specific settings, GMMS allocations always exist. We also establish the existence of approximate GMMS allocations under additive valuations, and develop a polynomial-time algorithm to find such allocations. Moreover, we establish a scale of fairness wherein we show that GMMS implies approximate envy freeness. Finally, we empirically demonstrate the existence of GMMS allocations in a large set of randomly generated instances. For the same set of instances, we additionally show that our algorithm achieves an approximation factor better than the established, worst-case bound. |
| Tasks | |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07621v1 |
| http://arxiv.org/pdf/1711.07621v1.pdf | |
| PWC | https://paperswithcode.com/paper/groupwise-maximin-fair-allocation-of |
| Repo | |
| Framework | |
