Paper Group ANR 870
Modeling Topical Coherence in Discourse without Supervision. Closing the AI Knowledge Gap. Bottleneck Supervised U-Net for Pixel-wise Liver and Tumor Segmentation. An Online RFID Localization in the Manufacturing Shopfloor. The Domain Transform Solver. Nuclear Norm Regularized Estimation of Panel Regression Models. Improbotics: Exploring the Imitat …
Modeling Topical Coherence in Discourse without Supervision
| Title | Modeling Topical Coherence in Discourse without Supervision |
| Authors | Disha Shrivastava, Abhijit Mishra, Karthik Sankaranarayanan |
| Abstract | Coherence of text is an important attribute to be measured for both manually and automatically generated discourse; but well-defined quantitative metrics for it are still elusive. In this paper, we present a metric for scoring topical coherence of an input paragraph on a real-valued scale by analyzing its underlying topical structure. We first extract all possible topics that the sentences of a paragraph of text are related to. Coherence of this text is then measured by computing: (a) the degree of uncertainty of the topics with respect to the paragraph, and (b) the relatedness between these topics. All components of our modular framework rely only on unlabeled data and WordNet, thus making it completely unsupervised, which is an important feature for general-purpose usage of any metric. Experiments are conducted on two datasets - a publicly available dataset for essay grading (representing human discourse), and a synthetic dataset constructed by mixing content from multiple paragraphs covering diverse topics. Our evaluation shows that the measured coherence scores are positively correlated with the ground truth for both the datasets. Further validation to our coherence scores is provided by conducting human evaluation on the synthetic data, showing a significant agreement of 79.3% |
| Tasks | |
| Published | 2018-09-02 |
| URL | http://arxiv.org/abs/1809.00410v1 |
| http://arxiv.org/pdf/1809.00410v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-topical-coherence-in-discourse |
| Repo | |
| Framework | |
Closing the AI Knowledge Gap
| Title | Closing the AI Knowledge Gap |
| Authors | Ziv Epstein, Blakeley H. Payne, Judy Hanwen Shen, Abhimanyu Dubey, Bjarke Felbo, Matthew Groh, Nick Obradovich, Manuel Cebrian, Iyad Rahwan |
| Abstract | AI researchers employ not only the scientific method, but also methodology from mathematics and engineering. However, the use of the scientific method - specifically hypothesis testing - in AI is typically conducted in service of engineering objectives. Growing interest in topics such as fairness and algorithmic bias show that engineering-focused questions only comprise a subset of the important questions about AI systems. This results in the AI Knowledge Gap: the number of unique AI systems grows faster than the number of studies that characterize these systems’ behavior. To close this gap, we argue that the study of AI could benefit from the greater inclusion of researchers who are well positioned to formulate and test hypotheses about the behavior of AI systems. We examine the barriers preventing social and behavioral scientists from conducting such studies. Our diagnosis suggests that accelerating the scientific study of AI systems requires new incentives for academia and industry, mediated by new tools and institutions. To address these needs, we propose a two-sided marketplace called TuringBox. On one side, AI contributors upload existing and novel algorithms to be studied scientifically by others. On the other side, AI examiners develop and post machine intelligence tasks designed to evaluate and characterize algorithmic behavior. We discuss this market’s potential to democratize the scientific study of AI behavior, and thus narrow the AI Knowledge Gap. |
| Tasks | |
| Published | 2018-03-20 |
| URL | http://arxiv.org/abs/1803.07233v1 |
| http://arxiv.org/pdf/1803.07233v1.pdf | |
| PWC | https://paperswithcode.com/paper/closing-the-ai-knowledge-gap |
| Repo | |
| Framework | |
Bottleneck Supervised U-Net for Pixel-wise Liver and Tumor Segmentation
| Title | Bottleneck Supervised U-Net for Pixel-wise Liver and Tumor Segmentation |
| Authors | Song Li, Geoffrey Kwok Fai Tso |
| Abstract | In this paper, we propose a bottleneck supervised (BS) U-Net model for liver and tumor segmentation. Our main contributions are: first, we propose a variation of the original U-Net that incorporates dense modules, inception modules and dilated convolution in the encoding path; second, we propose a bottleneck supervised (BS) U-Net that contains an encoding U-Net and a segmentation U-Net. To train the BS U-Net, the encoding U-Net is first trained to get encodings of the label maps that contain the anatomical information (shape and location). Subsequently, this information is used to guide the training of the segmentation U-Net so as to reserve the anatomical features of the target objects. More specifically, the loss function for segmentation U-Net is set to be the weighted average of the dice loss and the MSE loss between the encodings and the bottleneck feature vectors. The model is applied to a public liver and tumor CT scan dataset. Experimental results show that besides achieving excellent overall segmentation performance, BS U-Net also works great in controlling shape distortion, reducing false positive and false negative cases. |
| Tasks | |
| Published | 2018-10-16 |
| URL | http://arxiv.org/abs/1810.10331v2 |
| http://arxiv.org/pdf/1810.10331v2.pdf | |
| PWC | https://paperswithcode.com/paper/bottleneck-supervised-u-net-for-pixel-wise |
| Repo | |
| Framework | |
An Online RFID Localization in the Manufacturing Shopfloor
| Title | An Online RFID Localization in the Manufacturing Shopfloor |
| Authors | Andri Ashfahani, Mahardhika Pratama, Edwin Lughofer, Qing Cai, Huang Sheng |
| Abstract | {Radio Frequency Identification technology has gained popularity for cheap and easy deployment. In the realm of manufacturing shopfloor, it can be used to track the location of manufacturing objects to achieve better efficiency. The underlying challenge of localization lies in the non-stationary characteristics of manufacturing shopfloor which calls for an adaptive life-long learning strategy in order to arrive at accurate localization results. This paper presents an evolving model based on a novel evolving intelligent system, namely evolving Type-2 Quantum Fuzzy Neural Network (eT2QFNN), which features an interval type-2 quantum fuzzy set with uncertain jump positions. The quantum fuzzy set possesses a graded membership degree which enables better identification of overlaps between classes. The eT2QFNN works fully in the evolving mode where all parameters including the number of rules are automatically adjusted and generated on the fly. The parameter adjustment scenario relies on decoupled extended Kalman filter method. Our numerical study shows that eT2QFNN is able to deliver comparable accuracy compared to state-of-the-art algorithms. |
| Tasks | |
| Published | 2018-05-20 |
| URL | https://arxiv.org/abs/1805.07715v2 |
| https://arxiv.org/pdf/1805.07715v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-online-rfid-localization-in-the |
| Repo | |
| Framework | |
The Domain Transform Solver
| Title | The Domain Transform Solver |
| Authors | Akash Bapat, Jan-Michael Frahm |
| Abstract | We present a framework for edge-aware optimization that is an order of magnitude faster than the state of the art while having comparable performance. Our key insight is that the optimization can be formulated by leveraging properties of the domain transform, a method for edge-aware filtering that defines a distance-preserving 1D mapping of the input space. This enables our method to improve performance for a variety of problems including stereo, depth super-resolution, and render from defocus, while keeping the computational complexity linear in the number of pixels. Our method is highly parallelizable and adaptable, and it has demonstrable scalability with respect to image resolution. |
| Tasks | Super-Resolution |
| Published | 2018-05-11 |
| URL | http://arxiv.org/abs/1805.04590v1 |
| http://arxiv.org/pdf/1805.04590v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-domain-transform-solver |
| Repo | |
| Framework | |
Nuclear Norm Regularized Estimation of Panel Regression Models
| Title | Nuclear Norm Regularized Estimation of Panel Regression Models |
| Authors | Hyungsik Roger Moon, Martin Weidner |
| Abstract | In this paper we investigate panel regression models with interactive fixed effects. We propose two new estimation methods that are based on minimizing convex objective functions. The first method minimizes the sum of squared residuals with a nuclear (trace) norm regularization. The second method minimizes the nuclear norm of the residuals. We establish the consistency of the two resulting estimators. Those estimators have a very important computational advantage compared to the existing least squares (LS) estimator, in that they are defined as minimizers of a convex objective function. In addition, the nuclear norm penalization helps to resolve a potential identification problem for interactive fixed effect models, in particular when the regressors are low-rank and the number of the factors is unknown. We also show how to construct estimators that are asymptotically equivalent to the least squares (LS) estimator in Bai (2009) and Moon and Weidner (2017) by using our nuclear norm regularized or minimized estimators as initial values for a finite number of LS minimizing iteration steps. This iteration avoids any non-convex minimization, while the original LS estimation problem is generally non-convex, and can have multiple local minima. |
| Tasks | |
| Published | 2018-10-25 |
| URL | http://arxiv.org/abs/1810.10987v2 |
| http://arxiv.org/pdf/1810.10987v2.pdf | |
| PWC | https://paperswithcode.com/paper/nuclear-norm-regularized-estimation-of-panel |
| Repo | |
| Framework | |
Improbotics: Exploring the Imitation Game using Machine Intelligence in Improvised Theatre
| Title | Improbotics: Exploring the Imitation Game using Machine Intelligence in Improvised Theatre |
| Authors | Kory W. Mathewson, Piotr Mirowski |
| Abstract | Theatrical improvisation (impro or improv) is a demanding form of live, collaborative performance. Improv is a humorous and playful artform built on an open-ended narrative structure which simultaneously celebrates effort and failure. It is thus an ideal test bed for the development and deployment of interactive artificial intelligence (AI)-based conversational agents, or artificial improvisors. This case study introduces an improv show experiment featuring human actors and artificial improvisors. We have previously developed a deep-learning-based artificial improvisor, trained on movie subtitles, that can generate plausible, context-based, lines of dialogue suitable for theatre (Mathewson and Mirowski 2017). In this work, we have employed it to control what a subset of human actors say during an improv performance. We also give human-generated lines to a different subset of performers. All lines are provided to actors with headphones and all performers are wearing headphones. This paper describes a Turing test, or imitation game, taking place in a theatre, with both the audience members and the performers left to guess who is a human and who is a machine. In order to test scientific hypotheses about the perception of humans versus machines we collect anonymous feedback from volunteer performers and audience members. Our results suggest that rehearsal increases proficiency and possibility to control events in the performance. That said, consistency with real world experience is limited by the interface and the mechanisms used to perform the show. We also show that human-generated lines are shorter, more positive, and have less difficult words with more grammar and spelling mistakes than the artificial improvisor generated lines. |
| Tasks | |
| Published | 2018-09-06 |
| URL | http://arxiv.org/abs/1809.01807v1 |
| http://arxiv.org/pdf/1809.01807v1.pdf | |
| PWC | https://paperswithcode.com/paper/improbotics-exploring-the-imitation-game |
| Repo | |
| Framework | |
Stability of meanings versus rate of replacement of words: an experimental test
| Title | Stability of meanings versus rate of replacement of words: an experimental test |
| Authors | Michele Pasquini, Maurizio Serva |
| Abstract | The words of a language are randomly replaced in time by new ones, but it has long been known that words corresponding to some items (meanings) are less frequently replaced than others. Usually, the rate of replacement for a given item is not directly observable, but it is inferred by the estimated stability which, on the contrary, is observable. This idea goes back a long way in the lexicostatistical literature, nevertheless nothing ensures that it gives the correct answer. The family of Romance languages allows for a direct test of the estimated stabilities against the replacement rates since the proto-language (Latin) is known and the replacement rates can be explicitly computed. The output of the test is threefold:first, we prove that the standard approach which tries to infer the replacement rates trough the estimated stabilities is sound; second, we are able to rewrite the fundamental formula of Glottochronology for a non universal replacement rate (a rate which depends on the item); third, we give indisputable evidence that the stability ranking is far from being the same for different families of languages. This last result is also supported by comparison with the Malagasy family of dialects. As a side result we also provide some evidence that Vulgar Latin and not Late Classical Latin is at the root of modern Romance languages. |
| Tasks | |
| Published | 2018-02-20 |
| URL | http://arxiv.org/abs/1802.06764v2 |
| http://arxiv.org/pdf/1802.06764v2.pdf | |
| PWC | https://paperswithcode.com/paper/stability-of-meanings-versus-rate-of |
| Repo | |
| Framework | |
DINFRA: A One Stop Shop for Computing Multilingual Semantic Relatedness
| Title | DINFRA: A One Stop Shop for Computing Multilingual Semantic Relatedness |
| Authors | Siamak Barzegar, Juliano Efson Sales, Andre Freitas, Siegfried Handschuh, Brian Davis |
| Abstract | This demonstration presents an infrastructure for computing multilingual semantic relatedness and correlation for twelve natural languages by using three distributional semantic models (DSMs). Our demonsrator - DInfra (Distributional Infrastructure) provides researchers and developers with a highly useful platform for processing large-scale corpora and conducting experiments with distributional semantics. We integrate several multilingual DSMs in our webservice so the end user can obtain a result without worrying about the complexities involved in building DSMs. Our webservice allows the users to have easy access to a wide range of comparisons of DSMs with different parameters. In addition, users can configure and access DSM parameters using an easy to use API. |
| Tasks | |
| Published | 2018-05-16 |
| URL | http://arxiv.org/abs/1805.09644v1 |
| http://arxiv.org/pdf/1805.09644v1.pdf | |
| PWC | https://paperswithcode.com/paper/dinfra-a-one-stop-shop-for-computing |
| Repo | |
| Framework | |
Generative Single Image Reflection Separation
| Title | Generative Single Image Reflection Separation |
| Authors | Donghoon Lee, Ming-Hsuan Yang, Songhwai Oh |
| Abstract | Single image reflection separation is an ill-posed problem since two scenes, a transmitted scene and a reflected scene, need to be inferred from a single observation. To make the problem tractable, in this work we assume that categories of two scenes are known. It allows us to address the problem by generating both scenes that belong to the categories while their contents are constrained to match with the observed image. A novel network architecture is proposed to render realistic images of both scenes based on adversarial learning. The network can be trained in a weakly supervised manner, i.e., it learns to separate an observed image without corresponding ground truth images of transmission and reflection scenes which are difficult to collect in practice. Experimental results on real and synthetic datasets demonstrate that the proposed algorithm performs favorably against existing methods. |
| Tasks | |
| Published | 2018-01-12 |
| URL | http://arxiv.org/abs/1801.04102v1 |
| http://arxiv.org/pdf/1801.04102v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-single-image-reflection-separation |
| Repo | |
| Framework | |
Extended Vertical Lists for Temporal Pattern Mining from Multivariate Time Series
| Title | Extended Vertical Lists for Temporal Pattern Mining from Multivariate Time Series |
| Authors | Anton Kocheturov, Petar Momcilovic, Azra Bihorac, Panos M. Pardalos |
| Abstract | Temporal Pattern Mining (TPM) is the problem of mining predictive complex temporal patterns from multivariate time series in a supervised setting. We develop a new method called the Fast Temporal Pattern Mining with Extended Vertical Lists. This method utilizes an extension of the Apriori property which requires a more complex pattern to appear within records only at places where all of its subpatterns are detected as well. The approach is based on a novel data structure called the Extended Vertical List that tracks positions of the first state of the pattern inside records. Extensive computational results indicate that the new method performs significantly faster than the previous version of the algorithm for TMP. However, the speed-up comes at the expense of memory usage. |
| Tasks | Time Series |
| Published | 2018-04-26 |
| URL | http://arxiv.org/abs/1804.10025v1 |
| http://arxiv.org/pdf/1804.10025v1.pdf | |
| PWC | https://paperswithcode.com/paper/extended-vertical-lists-for-temporal-pattern |
| Repo | |
| Framework | |
Deep Fundamental Matrix Estimation without Correspondences
| Title | Deep Fundamental Matrix Estimation without Correspondences |
| Authors | Omid Poursaeed, Guandao Yang, Aditya Prakash, Qiuren Fang, Hanqing Jiang, Bharath Hariharan, Serge Belongie |
| Abstract | Estimating fundamental matrices is a classic problem in computer vision. Traditional methods rely heavily on the correctness of estimated key-point correspondences, which can be noisy and unreliable. As a result, it is difficult for these methods to handle image pairs with large occlusion or significantly different camera poses. In this paper, we propose novel neural network architectures to estimate fundamental matrices in an end-to-end manner without relying on point correspondences. New modules and layers are introduced in order to preserve mathematical properties of the fundamental matrix as a homogeneous rank-2 matrix with seven degrees of freedom. We analyze performance of the proposed models using various metrics on the KITTI dataset, and show that they achieve competitive performance with traditional methods without the need for extracting correspondences. |
| Tasks | |
| Published | 2018-10-03 |
| URL | http://arxiv.org/abs/1810.01575v1 |
| http://arxiv.org/pdf/1810.01575v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-fundamental-matrix-estimation-without |
| Repo | |
| Framework | |
Forecasting the successful execution of horizontal strategy in a diversified corporation via a DEMATEL-supported artificial neural network - A case study
| Title | Forecasting the successful execution of horizontal strategy in a diversified corporation via a DEMATEL-supported artificial neural network - A case study |
| Authors | Hossein Sabzian, Hossein Gharib, Javad Noori, Mohammad Ali Shafia, Mohammad Javad Sheikh |
| Abstract | Nowadays, competition is getting tougher as market shrinks because of financial crisis of the late 2000s. Organizations are tensely forced to leverage their core competencies to survive through attracting more customers and gaining more efficacious operations. In such a situation, diversified corporations which run multiple businesses have opportunities to get competitive advantage and differentiate themselves by executing horizontal strategy. Since this strategy completely engages a number of business units of a diversified corporation through resource sharing among them, any effort to implement it will fail if being not supported by enough information. However, for successful execution of horizontal strategy, managers should have reliable information concerning its success probability in advance. To provide such a precious information, a three-step framework has been developed. In the first step, major influencers on successful execution of horizontal strategy have been captured through literature study and interviewing subject matter experts. In the second step through the decision making trial and evaluation laboratory (DEMATEL) methodology, critical success factors (CSFs) have been extracted from major influencers and a success probability assessment index system (SPAIS) has been formed. In the third step, due to the statistical nature (multivariate and distribution free) of SPAIS, an artificial neural network has been designed for enabling organizational managers to forecast the success probability of horizontal strategy execution in a multi-business corporation far better than other classical models. |
| Tasks | Decision Making |
| Published | 2018-05-25 |
| URL | http://arxiv.org/abs/1805.10307v1 |
| http://arxiv.org/pdf/1805.10307v1.pdf | |
| PWC | https://paperswithcode.com/paper/forecasting-the-successful-execution-of |
| Repo | |
| Framework | |
How swarm size during evolution impacts the behavior, generalizability, and brain complexity of animats performing a spatial navigation task
| Title | How swarm size during evolution impacts the behavior, generalizability, and brain complexity of animats performing a spatial navigation task |
| Authors | Dominik Fischer, Sanaz Mostaghim, Larissa Albantakis |
| Abstract | While it is relatively easy to imitate and evolve natural swarm behavior in simulations, less is known about the social characteristics of simulated, evolved swarms, such as the optimal (evolutionary) group size, why individuals in a swarm perform certain actions, and how behavior would change in swarms of different sizes. To address these questions, we used a genetic algorithm to evolve animats equipped with Markov Brains in a spatial navigation task that facilitates swarm behavior. The animats’ goal was to frequently cross between two rooms without colliding with other animats. Animats were evolved in swarms of various sizes. We then evaluated the task performance and social behavior of the final generation from each evolution when placed with swarms of different sizes in order to evaluate their generalizability across conditions. According to our experiments, we find that swarm size during evolution matters: animats evolved in a balanced swarm developed more flexible behavior, higher fitness across conditions, and, in addition, higher brain complexity. |
| Tasks | |
| Published | 2018-04-24 |
| URL | http://arxiv.org/abs/1804.08940v1 |
| http://arxiv.org/pdf/1804.08940v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-swarm-size-during-evolution-impacts-the |
| Repo | |
| Framework | |
Deep Attention Model for Triage of Emergency Department Patients
| Title | Deep Attention Model for Triage of Emergency Department Patients |
| Authors | Djordje Gligorijevic, Jelena Stojanovic, Wayne Satz, Ivan Stojkovic, Kathrin Schreyer, Daniel Del Portal, Zoran Obradovic |
| Abstract | Optimization of patient throughput and wait time in emergency departments (ED) is an important task for hospital systems. For that reason, Emergency Severity Index (ESI) system for patient triage was introduced to help guide manual estimation of acuity levels, which is used by nurses to rank the patients and organize hospital resources. However, despite improvements that it brought to managing medical resources, such triage system greatly depends on nurse’s subjective judgment and is thus prone to human errors. Here, we propose a novel deep model based on the word attention mechanism designed for predicting a number of resources an ED patient would need. Our approach incorporates routinely available continuous and nominal (structured) data with medical text (unstructured) data, including patient’s chief complaint, past medical history, medication list, and nurse assessment collected for 338,500 ED visits over three years in a large urban hospital. Using both structured and unstructured data, the proposed approach achieves the AUC of $\sim 88%$ for the task of identifying resource intensive patients (binary classification), and the accuracy of $\sim 44%$ for predicting exact category of number of resources (multi-class classification task), giving an estimated lift over nurses’ performance by 16% in accuracy. Furthermore, the attention mechanism of the proposed model provides interpretability by assigning attention scores for nurses’ notes which is crucial for decision making and implementation of such approaches in the real systems working on human health. |
| Tasks | Decision Making, Deep Attention |
| Published | 2018-03-28 |
| URL | http://arxiv.org/abs/1804.03240v1 |
| http://arxiv.org/pdf/1804.03240v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-attention-model-for-triage-of-emergency |
| Repo | |
| Framework | |
