Paper Group ANR 621
Extended Answer and Uncertainty Aware Neural Question Generation. Multivariate Forecasting Evaluation: On Sensitive and Strictly Proper Scoring Rules. “Tom” pet robot applied to urban autism. Semantic Segmentation of Video Sequences with Convolutional LSTMs. Deep Neural Network Approximation Theory. Lower Bounds for Non-Convex Stochastic Optimizati …
Extended Answer and Uncertainty Aware Neural Question Generation
| Title | Extended Answer and Uncertainty Aware Neural Question Generation |
| Authors | Hongwei Zeng, Zhuo Zhi, Jun Liu, Bifan Wei |
| Abstract | In this paper, we study automatic question generation, the task of creating questions from corresponding text passages where some certain spans of the text can serve as the answers. We propose an Extended Answer-aware Network (EAN) which is trained with Word-based Coverage Mechanism (WCM) and decodes with Uncertainty-aware Beam Search (UBS). The EAN represents the target answer by its surrounding sentence with an encoder, and incorporates the information of the extended answer into paragraph representation with gated paragraph-to-answer attention to tackle the problem of the inadequate representation of the target answer. To reduce undesirable repetition, the WCM penalizes repeatedly attending to the same words at different time-steps in the training stage. The UBS aims to seek a better balance between the model confidence in copying words from an input text paragraph and the confidence in generating words from a vocabulary. We conduct experiments on the SQuAD dataset, and the results show our approach achieves significant performance improvement. |
| Tasks | Question Generation |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08112v1 |
| https://arxiv.org/pdf/1911.08112v1.pdf | |
| PWC | https://paperswithcode.com/paper/extended-answer-and-uncertainty-aware-neural |
| Repo | |
| Framework | |
Multivariate Forecasting Evaluation: On Sensitive and Strictly Proper Scoring Rules
| Title | Multivariate Forecasting Evaluation: On Sensitive and Strictly Proper Scoring Rules |
| Authors | Florian Ziel, Kevin Berk |
| Abstract | In recent years, probabilistic forecasting is an emerging topic, which is why there is a growing need of suitable methods for the evaluation of multivariate predictions. We analyze the sensitivity of the most common scoring rules, especially regarding quality of the forecasted dependency structures. Additionally, we propose scoring rules based on the copula, which uniquely describes the dependency structure for every probability distribution with continuous marginal distributions. Efficient estimation of the considered scoring rules and evaluation methods such as the Diebold-Mariano test are discussed. In detailed simulation studies, we compare the performance of the renowned scoring rules and the ones we propose. Besides extended synthetic studies based on recently published results we also consider a real data example. We find that the energy score, which is probably the most widely used multivariate scoring rule, performs comparably well in detecting forecast errors, also regarding dependencies. This contradicts other studies. The results also show that a proposed copula score provides very strong distinction between models with correct and incorrect dependency structure. We close with a comprehensive discussion on the proposed methodology. |
| Tasks | |
| Published | 2019-10-16 |
| URL | https://arxiv.org/abs/1910.07325v1 |
| https://arxiv.org/pdf/1910.07325v1.pdf | |
| PWC | https://paperswithcode.com/paper/multivariate-forecasting-evaluation-on |
| Repo | |
| Framework | |
“Tom” pet robot applied to urban autism
| Title | “Tom” pet robot applied to urban autism |
| Authors | Xingqian Li, Chenwei Lou, Jian Zhao, HuaPeng Wei, Hongwei Zhao |
| Abstract | With the fast development of network information technology, more and more people are immersed in the virtual community environment brought by the network, ignoring the social interaction in real life. The consequent urban autism problem has become more and more serious. Promoting offline communication between people " and “eliminating loneliness through emotional communication between pet robots and breeders” to solve this problem, and has developed a design called “Tom”. “Tom” is a smart pet robot with a pet robot-based social mechanism Called “Tom-Talker”. The main contribution of this paper is to propose a social mechanism called “Tom-Talker” that encourages users to socialize offline. And “Tom-Talker” also has a corresponding reward mechanism and a friend recommendation algorithm. It also proposes a pet robot named “Tom” with an emotional interaction algorithm to recognize users’ emotions, simulate animal emotions and communicate emotionally with use s. This paper designs experiments and analyzes the results. The results show that our pet robots have a good effect on solving urban autism problems. |
| Tasks | |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05652v1 |
| https://arxiv.org/pdf/1905.05652v1.pdf | |
| PWC | https://paperswithcode.com/paper/tom-pet-robot-applied-to-urban-autism |
| Repo | |
| Framework | |
Semantic Segmentation of Video Sequences with Convolutional LSTMs
| Title | Semantic Segmentation of Video Sequences with Convolutional LSTMs |
| Authors | Andreas Pfeuffer, Karina Schulz, Klaus Dietmayer |
| Abstract | Most of the semantic segmentation approaches have been developed for single image segmentation, and hence, video sequences are currently segmented by processing each frame of the video sequence separately. The disadvantage of this is that temporal image information is not considered, which improves the performance of the segmentation approach. One possibility to include temporal information is to use recurrent neural networks. However, there are only a few approaches using recurrent networks for video segmentation so far. These approaches extend the encoder-decoder network architecture of well-known segmentation approaches and place convolutional LSTM layers between encoder and decoder. However, in this paper it is shown that this position is not optimal, and that other positions in the network exhibit better performance. Nowadays, state-of-the-art segmentation approaches rarely use the classical encoder-decoder structure, but use multi-branch architectures. These architectures are more complex, and hence, it is more difficult to place the recurrent units at a proper position. In this work, the multi-branch architectures are extended by convolutional LSTM layers at different positions and evaluated on two different datasets in order to find the best one. It turned out that the proposed approach outperforms the pure CNN-based approach for up to 1.6 percent. |
| Tasks | Semantic Segmentation, Video Semantic Segmentation |
| Published | 2019-05-03 |
| URL | https://arxiv.org/abs/1905.01058v1 |
| https://arxiv.org/pdf/1905.01058v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-segmentation-of-video-sequences-with |
| Repo | |
| Framework | |
Deep Neural Network Approximation Theory
| Title | Deep Neural Network Approximation Theory |
| Authors | Philipp Grohs, Dmytro Perekrestenko, Dennis Elbrächter, Helmut Bölcskei |
| Abstract | Deep neural networks have become state-of-the-art technology for a wide range of practical machine learning tasks such as image classification, handwritten digit recognition, speech recognition, or game intelligence. This paper develops the fundamental limits of learning in deep neural networks by characterizing what is possible if no constraints on the learning algorithm and the amount of training data are imposed. Concretely, we consider information-theoretically optimal approximation through deep neural networks with the guiding theme being a relation between the complexity of the function (class) to be approximated and the complexity of the approximating network in terms of connectivity and memory requirements for storing the network topology and the associated quantized weights. The theory we develop educes remarkable universality properties of deep networks. Specifically, deep networks are optimal approximants for vastly different function classes such as affine systems and Gabor systems. This universality is afforded by a concurrent invariance property of deep networks to time-shifts, scalings, and frequency-shifts. In addition, deep networks provide exponential approximation accuracy i.e., the approximation error decays exponentially in the number of non-zero weights in the network of vastly different functions such as the squaring operation, multiplication, polynomials, sinusoidal functions, general smooth functions, and even one-dimensional oscillatory textures and fractal functions such as the Weierstrass function, both of which do not have any known methods achieving exponential approximation accuracy. In summary, deep neural networks provide information-theoretically optimal approximation of a very wide range of functions and function classes used in mathematical signal processing. |
| Tasks | Handwritten Digit Recognition, Image Classification, Speech Recognition |
| Published | 2019-01-08 |
| URL | http://arxiv.org/abs/1901.02220v1 |
| http://arxiv.org/pdf/1901.02220v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-neural-network-approximation-theory |
| Repo | |
| Framework | |
Lower Bounds for Non-Convex Stochastic Optimization
| Title | Lower Bounds for Non-Convex Stochastic Optimization |
| Authors | Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Nathan Srebro, Blake Woodworth |
| Abstract | We lower bound the complexity of finding $\epsilon$-stationary points (with gradient norm at most $\epsilon$) using stochastic first-order methods. In a well-studied model where algorithms access smooth, potentially non-convex functions through queries to an unbiased stochastic gradient oracle with bounded variance, we prove that (in the worst case) any algorithm requires at least $\epsilon^{-4}$ queries to find an $\epsilon$ stationary point. The lower bound is tight, and establishes that stochastic gradient descent is minimax optimal in this model. In a more restrictive model where the noisy gradient estimates satisfy a mean-squared smoothness property, we prove a lower bound of $\epsilon^{-3}$ queries, establishing the optimality of recently proposed variance reduction techniques. |
| Tasks | Stochastic Optimization |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02365v1 |
| https://arxiv.org/pdf/1912.02365v1.pdf | |
| PWC | https://paperswithcode.com/paper/lower-bounds-for-non-convex-stochastic |
| Repo | |
| Framework | |
Argumentative Relation Classification as Plausibility Ranking
| Title | Argumentative Relation Classification as Plausibility Ranking |
| Authors | Juri Opitz |
| Abstract | We formulate argumentative relation classification (support vs. attack) as a text-plausibility ranking task. To this aim, we propose a simple reconstruction trick which enables us to build minimal pairs of plausible and implausible texts by simulating natural contexts in which two argumentative units are likely or unlikely to appear. We show that this method is competitive with previous work albeit it is considerably simpler. In a recently introduced content-based version of the task, where contextual discourse clues are hidden, the approach offers a performance increase of more than 10% macro F1. With respect to the scarce attack-class, the method achieves a large increase in precision while the incurred loss in recall is small or even nonexistent. |
| Tasks | Relation Classification |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.09031v1 |
| https://arxiv.org/pdf/1909.09031v1.pdf | |
| PWC | https://paperswithcode.com/paper/argumentative-relation-classification-as |
| Repo | |
| Framework | |
Information Flow Theory (IFT) of Biologic and Machine Consciousness: Implications for Artificial General Intelligence and the Technological Singularity
| Title | Information Flow Theory (IFT) of Biologic and Machine Consciousness: Implications for Artificial General Intelligence and the Technological Singularity |
| Authors | B. S. Bleier |
| Abstract | The subjective experience of consciousness is at once familiar and yet deeply mysterious. Strategies exploring the top-down mechanisms of conscious thought within the human brain have been unable to produce a generalized explanatory theory that scales through evolution and can be applied to artificial systems. Information Flow Theory (IFT) provides a novel framework for understanding both the development and nature of consciousness in any system capable of processing information. In prioritizing the direction of information flow over information computation, IFT produces a range of unexpected predictions. The purpose of this manuscript is to introduce the basic concepts of IFT and explore the manifold implications regarding artificial intelligence, superhuman consciousness, and our basic perception of reality. |
| Tasks | |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1907.00703v1 |
| https://arxiv.org/pdf/1907.00703v1.pdf | |
| PWC | https://paperswithcode.com/paper/information-flow-theory-ift-of-biologic-and |
| Repo | |
| Framework | |
A Bayesian Dynamic Multilayered Block Network Model
| Title | A Bayesian Dynamic Multilayered Block Network Model |
| Authors | Hector Rodriguez-Deniz, Mattias Villani, Augusto Voltes-Dorta |
| Abstract | As network data become increasingly available, new opportunities arise to understand dynamic and multilayer network systems in many applied disciplines. Statistical modeling for multilayer networks is currently an active research area that aims to develop methods to carry out inference on such data. Recent contributions focus on latent space representation of the multilayer structure with underlying stochastic processes to account for network dynamics. Existing multilayer models are however typically limited to rather small networks. In this paper we introduce a dynamic multilayer block network model with a latent space represention for blocks rather than nodes. A block structure is natural for many real networks, such as social or transportation networks, where community structure naturally arises. A Gibbs sampler based on P'olya-Gamma data augmentation is presented for the proposed model. Results from extensive simulations on synthetic data show that the inference algorithm scales well with the size of the network. We present a case study using real data from an airline system, a classic example of hub-and-spoke network. |
| Tasks | Data Augmentation |
| Published | 2019-11-29 |
| URL | https://arxiv.org/abs/1911.13136v1 |
| https://arxiv.org/pdf/1911.13136v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayesian-dynamic-multilayered-block-network |
| Repo | |
| Framework | |
Completing partial recipes using item-based collaborative filtering to recommend ingredients
| Title | Completing partial recipes using item-based collaborative filtering to recommend ingredients |
| Authors | Paula Fermín Cueto, Meeke Roet, Agnieszka Słowik |
| Abstract | Increased public interest in healthy lifestyles has motivated the study of algorithms that encourage people to follow a healthy diet. Applying collaborative filtering to build recommendation systems in domains where only implicit feedback is available is also a rapidly growing research area. In this report we combine these two trends by developing a recommendation system to suggest ingredients that can be added to a partial recipe. We implement the item-based collaborative filtering algorithm using a high-dimensional, sparse dataset of recipes, which inherently contains only implicit feedback. We explore the effect of different similarity measures and dimensionality reduction on the quality of the recommendations, and find that our best method achieves a recall@10 of circa 40%. |
| Tasks | Dimensionality Reduction, Recommendation Systems |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.12380v2 |
| https://arxiv.org/pdf/1907.12380v2.pdf | |
| PWC | https://paperswithcode.com/paper/completing-partial-recipes-using-item-based |
| Repo | |
| Framework | |
A Cooperative Coordination Solver for Travelling Thief Problems
| Title | A Cooperative Coordination Solver for Travelling Thief Problems |
| Authors | Majid Namazi, Conrad Sanderson, M. A. Hakim Newton, Abdul Sattar |
| Abstract | The travelling thief problem (TTP) is a representative of multi-component optimisation problems with interacting components. TTP combines the knapsack problem (KP) and the travelling salesman problem (TSP). A thief performs a cyclic tour through a set of cities, and pursuant to a collection plan, collects a subset of items into a rented knapsack with finite capacity. The aim is to maximise profit while minimising renting cost. Existing TTP solvers typically solve the KP and TSP components in an interleaved manner: the solution of one component is kept fixed while the solution of the other component is modified. This suggests low coordination between solving the two components, possibly leading to low quality TTP solutions. The 2-OPT heuristic is often used for solving the TSP component, which reverses a segment in the tour. Within TTP, 2-OPT does not take into account the collection plan, which can result in a lower objective value. This in turn can result in the tour modification to be rejected by a solver. We propose an expanded form of 2-OPT to change the collection plan in coordination with tour modification. Items regarded as less profitable and collected in cities located earlier in the reversed segment are substituted by items that tend to be more profitable and not collected in cities located later in the reversed segment. The collection plan is further changed through a modified form of the hill-climbing bit-flip search, where changes in the collection state are only permitted for boundary items, which are defined as lowest profitable collected items or highest profitable uncollected items. This restriction reduces the time spent on the KP component, allowing more tours to be evaluated by the TSP component within a time budget. The proposed approaches form the basis of a new cooperative coordination solver, which is shown to outperform several state-of-the-art TTP solvers. |
| Tasks | |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03124v2 |
| https://arxiv.org/pdf/1911.03124v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-cooperative-coordination-solver-for |
| Repo | |
| Framework | |
Universal Material Translator: Towards Spoof Fingerprint Generalization
| Title | Universal Material Translator: Towards Spoof Fingerprint Generalization |
| Authors | Rohit Gajawada, Additya Popli, Tarang Chugh, Anoop Namboodiri, Anil K. Jain |
| Abstract | Spoof detectors are classifiers that are trained to distinguish spoof fingerprints from bonafide ones. However, state of the art spoof detectors do not generalize well on unseen spoof materials. This study proposes a style transfer based augmentation wrapper that can be used on any existing spoof detector and can dynamically improve the robustness of the spoof detection system on spoof materials for which we have very low data. Our method is an approach for synthesizing new spoof images from a few spoof examples that transfers the style or material properties of the spoof examples to the content of bonafide fingerprints to generate a larger number of examples to train the classifier on. We demonstrate the effectiveness of our approach on materials in the publicly available LivDet 2015 dataset and show that the proposed approach leads to robustness to fingerprint spoofs of the target material. |
| Tasks | Style Transfer |
| Published | 2019-12-08 |
| URL | https://arxiv.org/abs/1912.03737v1 |
| https://arxiv.org/pdf/1912.03737v1.pdf | |
| PWC | https://paperswithcode.com/paper/universal-material-translator-towards-spoof |
| Repo | |
| Framework | |
An Unsupervised Domain-Independent Framework for Automated Detection of Persuasion Tactics in Text
| Title | An Unsupervised Domain-Independent Framework for Automated Detection of Persuasion Tactics in Text |
| Authors | Rahul Radhakrishnan Iyer, Katia Sycara |
| Abstract | With the increasing growth of social media, people have started relying heavily on the information shared therein to form opinions and make decisions. While such a reliance is motivation for a variety of parties to promote information, it also makes people vulnerable to exploitation by slander, misinformation, terroristic and predatorial advances. In this work, we aim to understand and detect such attempts at persuasion. Existing works on detecting persuasion in text make use of lexical features for detecting persuasive tactics, without taking advantage of the possible structures inherent in the tactics used. We formulate the task as a multi-class classification problem and propose an unsupervised, domain-independent machine learning framework for detecting the type of persuasion used in text, which exploits the inherent sentence structure present in the different persuasion tactics. Our work shows promising results as compared to existing work. |
| Tasks | |
| Published | 2019-12-13 |
| URL | https://arxiv.org/abs/1912.06745v1 |
| https://arxiv.org/pdf/1912.06745v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-unsupervised-domain-independent-framework |
| Repo | |
| Framework | |
Algorithmic Distortion of Informational Landscapes
| Title | Algorithmic Distortion of Informational Landscapes |
| Authors | Camille Roth |
| Abstract | The possible impact of algorithmic recommendation on the autonomy and free choice of Internet users is being increasingly discussed, especially in terms of the rendering of information and the structuring of interactions. This paper aims at reviewing and framing this issue along a double dichotomy. The first one addresses the discrepancy between users’ intentions and actions (1) under some algorithmic influence and (2) without it. The second one distinguishes algorithmic biases on (1) prior information rearrangement and (2) posterior information arrangement. In all cases, we focus on and differentiate situations where algorithms empirically appear to expand the cognitive and social horizon of users, from those where they seem to limit that horizon. We additionally suggest that these biases may not be properly appraised without taking into account the underlying social processes which algorithms are building upon. |
| Tasks | |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.10401v1 |
| https://arxiv.org/pdf/1907.10401v1.pdf | |
| PWC | https://paperswithcode.com/paper/algorithmic-distortion-of-informational |
| Repo | |
| Framework | |
Fingerprint Spoof Generalization
| Title | Fingerprint Spoof Generalization |
| Authors | Tarang Chugh, Anil K. Jain |
| Abstract | We present a style-transfer based wrapper, called Universal Material Generator (UMG), to improve the generalization performance of any fingerprint spoof detector against spoofs made from materials not seen during training. Specifically, we transfer the style (texture) characteristics between fingerprint images of known materials with the goal of synthesizing fingerprint images corresponding to unknown materials, that may occupy the space between the known materials in the deep feature space. Synthetic live fingerprint images are also added to the training dataset to force the CNN to learn generative-noise invariant features which discriminate between lives and spoofs. The proposed approach is shown to improve the generalization performance of a state-of-the-art spoof detector, namely Fingerprint Spoof Buster, from TDR of 75.24% to 91.78% @ FDR = 0.2%. These results are based on a large-scale dataset of 5,743 live and 4,912 spoof images fabricated using 12 different materials. Additionally, the UMG wrapper is shown to improve the average cross-sensor spoof detection performance from 67.60% to 80.63% when tested on the LivDet 2017 dataset. Training the UMG wrapper requires only 100 live fingerprint images from the target sensor, alleviating the time and resources required to generate large-scale live and spoof datasets for a new sensor. We also fabricate physical spoof artifacts using a mixture of known spoof materials to explore the role of cross-material style transfer in improving generalization performance. |
| Tasks | Style Transfer |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02710v1 |
| https://arxiv.org/pdf/1912.02710v1.pdf | |
| PWC | https://paperswithcode.com/paper/fingerprint-spoof-generalization |
| Repo | |
| Framework | |
