Paper Group NANR 152
Efficient and Flexible Inference for Stochastic Systems. Convex Phase Retrieval without Lifting via PhaseMax. TextImager as a Generic Interface to R. A Morphological Parser for Odawa. Asynchronous Parallel Coordinate Minimization for MAP Inference. Crowdsourcing discourse interpretations: On the influence of context and the reliability of a connect …
Efficient and Flexible Inference for Stochastic Systems
| Title | Efficient and Flexible Inference for Stochastic Systems |
| Authors | Stefan Bauer, Nico S. Gorbach, Djordje Miladinovic, Joachim M. Buhmann |
| Abstract | Many real world dynamical systems are described by stochastic differential equations. Thus parameter inference is a challenging and important problem in many disciplines. We provide a grid free and flexible algorithm offering parameter and state inference for stochastic systems and compare our approch based on variational approximations to state of the art methods showing significant advantages both in runtime and accuracy. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7274-efficient-and-flexible-inference-for-stochastic-systems |
| http://papers.nips.cc/paper/7274-efficient-and-flexible-inference-for-stochastic-systems.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-and-flexible-inference-for |
| Repo | |
| Framework | |
Convex Phase Retrieval without Lifting via PhaseMax
| Title | Convex Phase Retrieval without Lifting via PhaseMax |
| Authors | Tom Goldstein, Christoph Studer |
| Abstract | Semidefinite relaxation methods transform a variety of non-convex optimization problems into convex problems, but square the number of variables. We study a new type of convex relaxation for phase retrieval problems, called PhaseMax, that convexifies the underlying problem without lifting. The resulting problem formulation can be solved using standard convex optimization routines, while still working in the original, low-dimensional variable space. We prove, using a random spherical distribution measurement model, that PhaseMax succeeds with high probability for a sufficiently large number of measurements. We compare our approach to other phase retrieval methods and demonstrate that our theory accurately predicts the success of PhaseMax. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=636 |
| http://proceedings.mlr.press/v70/goldstein17a/goldstein17a.pdf | |
| PWC | https://paperswithcode.com/paper/convex-phase-retrieval-without-lifting-via |
| Repo | |
| Framework | |
TextImager as a Generic Interface to R
| Title | TextImager as a Generic Interface to R |
| Authors | Tolga Uslu, Wahed Hemati, Alex Mehler, er, Daniel Baumartz |
| Abstract | R is a very powerful framework for statistical modeling. Thus, it is of high importance to integrate R with state-of-the-art tools in NLP. In this paper, we present the functionality and architecture of such an integration by means of TextImager. We use the OpenCPU API to integrate R based on our own R-Server. This allows for communicating with R-packages and combining them with TextImager{'}s NLP-components. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3005/ |
| https://www.aclweb.org/anthology/E17-3005 | |
| PWC | https://paperswithcode.com/paper/textimager-as-a-generic-interface-to-r |
| Repo | |
| Framework | |
A Morphological Parser for Odawa
| Title | A Morphological Parser for Odawa |
| Authors | Dustin Bowers, Antti Arppe, Jordan Lachler, Sjur Moshagen, Trond Trosterud |
| Abstract | |
| Tasks | |
| Published | 2017-03-01 |
| URL | https://www.aclweb.org/anthology/W17-0101/ |
| https://www.aclweb.org/anthology/W17-0101 | |
| PWC | https://paperswithcode.com/paper/a-morphological-parser-for-odawa |
| Repo | |
| Framework | |
Asynchronous Parallel Coordinate Minimization for MAP Inference
| Title | Asynchronous Parallel Coordinate Minimization for MAP Inference |
| Authors | Ofer Meshi, Alexander Schwing |
| Abstract | Finding the maximum a-posteriori (MAP) assignment is a central task in graphical models. Since modern applications give rise to very large problem instances, there is increasing need for efficient solvers. In this work we propose to improve the efficiency of coordinate-minimization-based dual-decomposition solvers by running their updates asynchronously in parallel. In this case message-passing inference is performed by multiple processing units simultaneously without coordination, all reading and writing to shared memory. We analyze the convergence properties of the resulting algorithms and identify settings where speedup gains can be expected. Our numerical evaluations show that this approach indeed achieves significant speedups in common computer vision tasks. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7156-asynchronous-parallel-coordinate-minimization-for-map-inference |
| http://papers.nips.cc/paper/7156-asynchronous-parallel-coordinate-minimization-for-map-inference.pdf | |
| PWC | https://paperswithcode.com/paper/asynchronous-parallel-coordinate-minimization |
| Repo | |
| Framework | |
Crowdsourcing discourse interpretations: On the influence of context and the reliability of a connective insertion task
| Title | Crowdsourcing discourse interpretations: On the influence of context and the reliability of a connective insertion task |
| Authors | Merel Scholman, Vera Demberg |
| Abstract | Traditional discourse annotation tasks are considered costly and time-consuming, and the reliability and validity of these tasks is in question. In this paper, we investigate whether crowdsourcing can be used to obtain reliable discourse relation annotations. We also examine the influence of context on the reliability of the data. The results of a crowdsourced connective insertion task showed that the method can be used to obtain reliable annotations: The majority of the inserted connectives converged with the original label. Further, the method is sensitive to the fact that multiple senses can often be inferred for a single relation. Regarding the presence of context, the results show no significant difference in distributions of insertions between conditions overall. However, a by-item comparison revealed several characteristics of segments that determine whether the presence of context makes a difference in annotations. The findings discussed in this paper can be taken as evidence that crowdsourcing can be used as a valuable method to obtain insights into the sense(s) of relations. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0803/ |
| https://www.aclweb.org/anthology/W17-0803 | |
| PWC | https://paperswithcode.com/paper/crowdsourcing-discourse-interpretations-on |
| Repo | |
| Framework | |
A Soft-label Method for Noise-tolerant Distantly Supervised Relation Extraction
| Title | A Soft-label Method for Noise-tolerant Distantly Supervised Relation Extraction |
| Authors | Tianyu Liu, Kexiang Wang, Baobao Chang, Zhifang Sui |
| Abstract | Distant-supervised relation extraction inevitably suffers from wrong labeling problems because it heuristically labels relational facts with knowledge bases. Previous sentence level denoise models don{'}t achieve satisfying performances because they use hard labels which are determined by distant supervision and immutable during training. To this end, we introduce an entity-pair level denoise method which exploits semantic information from correctly labeled entity pairs to correct wrong labels dynamically during training. We propose a joint score function which combines the relational scores based on the entity-pair representation and the confidence of the hard label to obtain a new label, namely a soft label, for certain entity pair. During training, soft labels instead of hard labels serve as gold labels. Experiments on the benchmark dataset show that our method dramatically reduces noisy instances and outperforms other state-of-the-art systems. |
| Tasks | Relation Extraction |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1189/ |
| https://www.aclweb.org/anthology/D17-1189 | |
| PWC | https://paperswithcode.com/paper/a-soft-label-method-for-noise-tolerant |
| Repo | |
| Framework | |
Contextual Characteristics of Concrete and Abstract Words
| Title | Contextual Characteristics of Concrete and Abstract Words |
| Authors | Diego Frassinelli, Daniela Naumann, Jason Utt, Sabine Schulte m Walde |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6910/ |
| https://www.aclweb.org/anthology/W17-6910 | |
| PWC | https://paperswithcode.com/paper/contextual-characteristics-of-concrete-and |
| Repo | |
| Framework | |
Proto-Indo-European Lexicon: The Generative Etymological Dictionary of Indo-European Languages
| Title | Proto-Indo-European Lexicon: The Generative Etymological Dictionary of Indo-European Languages |
| Authors | Jouna Pyysalo |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0234/ |
| https://www.aclweb.org/anthology/W17-0234 | |
| PWC | https://paperswithcode.com/paper/proto-indo-european-lexicon-the-generative |
| Repo | |
| Framework | |
Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks
| Title | Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks |
| Authors | Wei-Sheng Lai, Jia-Bin Huang, Ming-Hsuan Yang |
| Abstract | Convolutional neural networks (CNNs) have recently been applied to the optical flow estimation problem. As training the CNNs requires sufficiently large ground truth training data, existing approaches resort to synthetic, unrealistic datasets. On the other hand, unsupervised methods are capable of leveraging real-world videos for training where the ground truth flow fields are not available. These methods, however, rely on the fundamental assumptions of brightness constancy and spatial smoothness priors which do not hold near motion boundaries. In this paper, we propose to exploit unlabeled videos for semi-supervised learning of optical flow with a Generative Adversarial Network. Our key insight is that the adversarial loss can capture the structural patterns of flow warp errors without making explicit assumptions. Extensive experiments on benchmark datasets demonstrate that the proposed semi-supervised algorithm performs favorably against purely supervised and semi-supervised learning schemes. |
| Tasks | Optical Flow Estimation |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6639-semi-supervised-learning-for-optical-flow-with-generative-adversarial-networks |
| http://papers.nips.cc/paper/6639-semi-supervised-learning-for-optical-flow-with-generative-adversarial-networks.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-for-optical-flow |
| Repo | |
| Framework | |
Web-Scale Language-Independent Cataloging of Noisy Product Listings for E-Commerce
| Title | Web-Scale Language-Independent Cataloging of Noisy Product Listings for E-Commerce |
| Authors | Pradipto Das, Y Xia, i, Aaron Levine, Giuseppe Di Fabbrizio, Ankur Datta |
| Abstract | The cataloging of product listings through taxonomy categorization is a fundamental problem for any e-commerce marketplace, with applications ranging from personalized search recommendations to query understanding. However, manual and rule based approaches to categorization are not scalable. In this paper, we compare several classifiers for categorizing listings in both English and Japanese product catalogs. We show empirically that a combination of words from product titles, navigational breadcrumbs, and list prices, when available, improves results significantly. We outline a novel method using correspondence topic models and a lightweight manual process to reduce noise from mis-labeled data in the training set. We contrast linear models, gradient boosted trees (GBTs) and convolutional neural networks (CNNs), and show that GBTs and CNNs yield the highest gains in error reduction. Finally, we show GBTs applied in a language-agnostic way on a large-scale Japanese e-commerce dataset have improved taxonomy categorization performance over current state-of-the-art based on deep belief network models. |
| Tasks | Product Categorization, Topic Models |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1091/ |
| https://www.aclweb.org/anthology/E17-1091 | |
| PWC | https://paperswithcode.com/paper/web-scale-language-independent-cataloging-of |
| Repo | |
| Framework | |
Active Heteroscedastic Regression
| Title | Active Heteroscedastic Regression |
| Authors | Kamalika Chaudhuri, Prateek Jain, Nagarajan Natarajan |
| Abstract | An active learner is given a model class $\Theta$, a large sample of unlabeled data drawn from an underlying distribution and access to a labeling oracle that can provide a label for any of the unlabeled instances. The goal of the learner is to find a model $\theta \in \Theta$ that fits the data to a given accuracy while making as few label queries to the oracle as possible. In this work, we consider a theoretical analysis of the label requirement of active learning for regression under a heteroscedastic noise model, where the noise depends on the instance. We provide bounds on the convergence rates of active and passive learning for heteroscedastic regression. Our results illustrate that just like in binary classification, some partial knowledge of the nature of the noise can lead to significant gains in the label requirement of active learning. |
| Tasks | Active Learning |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=785 |
| http://proceedings.mlr.press/v70/chaudhuri17a/chaudhuri17a.pdf | |
| PWC | https://paperswithcode.com/paper/active-heteroscedastic-regression |
| Repo | |
| Framework | |
CUNI submission in WMT17: Chimera goes neural
| Title | CUNI submission in WMT17: Chimera goes neural |
| Authors | Roman Sudarikov, David Mare{\v{c}}ek, Tom Kocmi, Du{\v{s}}an Vari{\v{s}}, Ond{\v{r}}ej Bojar |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4720/ |
| https://www.aclweb.org/anthology/W17-4720 | |
| PWC | https://paperswithcode.com/paper/cuni-submission-in-wmt17-chimera-goes-neural |
| Repo | |
| Framework | |
Fast Bayesian Intensity Estimation for the Permanental Process
| Title | Fast Bayesian Intensity Estimation for the Permanental Process |
| Authors | Christian J. Walder, Adrian N. Bishop |
| Abstract | The Cox process is a stochastic process which generalises the Poisson process by letting the underlying intensity function itself be a stochastic process. In this paper we present a fast Bayesian inference scheme for the permanental process, a Cox process under which the square root of the intensity is a Gaussian process. In particular we exploit connections with reproducing kernel Hilbert spaces, to derive efficient approximate Bayesian inference algorithms based on the Laplace approximation to the predictive distribution and marginal likelihood. We obtain a simple algorithm which we apply to toy and real-world problems, obtaining orders of magnitude speed improvements over previous work. |
| Tasks | Bayesian Inference |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=622 |
| http://proceedings.mlr.press/v70/walder17a/walder17a.pdf | |
| PWC | https://paperswithcode.com/paper/fast-bayesian-intensity-estimation-for-the |
| Repo | |
| Framework | |
Detecting Metaphorical Phrases in the Polish Language
| Title | Detecting Metaphorical Phrases in the Polish Language |
| Authors | Aleks Wawer, er, Agnieszka Mykowiecka |
| Abstract | In this paper we describe experiments with automated detection of metaphors in the Polish language. We focus our analysis on noun phrases composed of an adjective and a noun, and distinguish three types of expressions: with literal sense, with metaphorical sense, and expressions both literal and methaphorical (context-dependent). We propose a method of automatically recognizing expression type using word embeddings and neural networks. We evaluate multiple neural network architectures and demonstrate that the method significantly outperforms strong baselines. |
| Tasks | Machine Translation, Natural Language Inference, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1099/ |
| https://doi.org/10.26615/978-954-452-049-6_099 | |
| PWC | https://paperswithcode.com/paper/detecting-metaphorical-phrases-in-the-polish |
| Repo | |
| Framework | |
