Paper Group ANR 1250
From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots. Oriented Point Sampling for Plane Detection in Unorganized Point Clouds. Tensor Regression Using Low-rank and Sparse Tucker Decompositions. BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators. Op …
From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots
| Title | From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots |
| Authors | Shizhe Chen, Qin Jin, Jianlong Fu |
| Abstract | The neural machine translation model has suffered from the lack of large-scale parallel corpora. In contrast, we humans can learn multi-lingual translations even without parallel texts by referring our languages to the external world. To mimic such human learning behavior, we employ images as pivots to enable zero-resource translation learning. However, a picture tells a thousand words, which makes multi-lingual sentences pivoted by the same image noisy as mutual translations and thus hinders the translation model learning. In this work, we propose a progressive learning approach for image-pivoted zero-resource machine translation. Since words are less diverse when grounded in the image, we first learn word-level translation with image pivots, and then progress to learn the sentence-level translation by utilizing the learned word translation to suppress noises in image-pivoted multi-lingual sentences. Experimental results on two widely used image-pivot translation datasets, IAPR-TC12 and Multi30k, show that the proposed approach significantly outperforms other state-of-the-art methods. |
| Tasks | Machine Translation |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00872v1 |
| https://arxiv.org/pdf/1906.00872v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600872 |
| Repo | |
| Framework | |
Oriented Point Sampling for Plane Detection in Unorganized Point Clouds
| Title | Oriented Point Sampling for Plane Detection in Unorganized Point Clouds |
| Authors | Bo Sun, Philippos Mordohai |
| Abstract | Plane detection in 3D point clouds is a crucial pre-processing step for applications such as point cloud segmentation, semantic mapping and SLAM. In contrast to many recent plane detection methods that are only applicable on organized point clouds, our work is targeted to unorganized point clouds that do not permit a 2D parametrization. We compare three methods for detecting planes in point clouds efficiently. One is a novel method proposed in this paper that generates plane hypotheses by sampling from a set of points with estimated normals. We named this method Oriented Point Sampling (OPS) to contrast with more conventional techniques that require the sampling of three unoriented points to generate plane hypotheses. We also implemented an efficient plane detection method based on local sampling of three unoriented points and compared it with OPS and the 3D-KHT algorithm, which is based on octrees, on the detection of planes on 10,000 point clouds from the SUN RGB-D dataset. |
| Tasks | |
| Published | 2019-05-04 |
| URL | https://arxiv.org/abs/1905.02553v1 |
| https://arxiv.org/pdf/1905.02553v1.pdf | |
| PWC | https://paperswithcode.com/paper/oriented-point-sampling-for-plane-detection |
| Repo | |
| Framework | |
Tensor Regression Using Low-rank and Sparse Tucker Decompositions
| Title | Tensor Regression Using Low-rank and Sparse Tucker Decompositions |
| Authors | Talal Ahmed, Haroon Raja, Waheed U. Bajwa |
| Abstract | This paper studies a tensor-structured linear regression model with a scalar response variable and tensor-structured predictors, such that the regression parameters form a tensor of order $d$ (i.e., a $d$-fold multiway array) in $\mathbb{R}^{n_1 \times n_2 \times \cdots \times n_d}$. This work focuses on the task of estimating the regression tensor from $m$ realizations of the response variable and the predictors where $m\ll n = \prod \nolimits_{i} n_i$. Despite the ill-posedness of this estimation problem, it can still be solved if the parameter tensor belongs to the space of sparse, low Tucker-rank tensors. Accordingly, the estimation procedure is posed as a non-convex optimization program over the space of sparse, low Tucker-rank tensors, and a tensor variant of projected gradient descent is proposed to solve the resulting non-convex problem. In addition, mathematical guarantees are provided that establish the proposed method converges to the correct solution under the right set of conditions. Further, an upper bound on sample complexity of tensor parameter estimation for the model under consideration is characterized for the special case when the individual (scalar) predictors independently draw values from a sub-Gaussian distribution. The sample complexity bound is shown to have a polylogarithmic dependence on $\bar{n} = \max \big{n_i: i\in {1,2,\ldots,d } \big}$ and, orderwise, it matches the bound one can obtain from a heuristic parameter counting argument. Finally, numerical experiments demonstrate the efficacy of the proposed tensor model and estimation method on a synthetic dataset and a neuroimaging dataset pertaining to attention deficit hyperactivity disorder. Specifically, the proposed method exhibits better sample complexities on both synthetic and real datasets, demonstrating the usefulness of the model and the method in settings where $n \gg m$. |
| Tasks | |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03725v1 |
| https://arxiv.org/pdf/1911.03725v1.pdf | |
| PWC | https://paperswithcode.com/paper/tensor-regression-using-low-rank-and-sparse |
| Repo | |
| Framework | |
BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators
| Title | BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators |
| Authors | Fabio Ramos, Rafael Carvalhaes Possas, Dieter Fox |
| Abstract | We introduce BayesSim, a framework for robotics simulations allowing a full Bayesian treatment for the parameters of the simulator. As simulators become more sophisticated and able to represent the dynamics more accurately, fundamental problems in robotics such as motion planning and perception can be solved in simulation and solutions transferred to the physical robot. However, even the most complex simulator might still not be able to represent reality in all its details either due to inaccurate parametrization or simplistic assumptions in the dynamic models. BayesSim provides a principled framework to reason about the uncertainty of simulation parameters. Given a black box simulator (or generative model) that outputs trajectories of state and action pairs from unknown simulation parameters, followed by trajectories obtained with a physical robot, we develop a likelihood-free inference method that computes the posterior distribution of simulation parameters. This posterior can then be used in problems where Sim2Real is critical, for example in policy search. We compare the performance of BayesSim in obtaining accurate posteriors in a number of classical control and robotics problems. Results show that the posterior computed from BayesSim can be used for domain randomization outperforming alternative methods that randomize based on uniform priors. |
| Tasks | Motion Planning |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01728v1 |
| https://arxiv.org/pdf/1906.01728v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayessim-adaptive-domain-randomization-via |
| Repo | |
| Framework | |
Optimal Best Markovian Arm Identification with Fixed Confidence
| Title | Optimal Best Markovian Arm Identification with Fixed Confidence |
| Authors | Vrettos Moulos |
| Abstract | We give a complete characterization of the sampling complexity of best Markovian arm identification in one-parameter Markovian bandit models. We derive instance specific nonasymptotic and asymptotic lower bounds which generalize those of the IID setting. We analyze the Track-and-Stop strategy, initially proposed for the IID setting, and we prove that asymptotically it is at most a factor of four apart from the lower bound. Our one-parameter Markovian bandit model is based on the notion of an exponential family of stochastic matrices for which we establish many useful properties. For the analysis of the Track-and-Stop strategy we derive a novel concentration inequality for Markov chains that may be of interest in its own right. |
| Tasks | |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.00636v2 |
| https://arxiv.org/pdf/1912.00636v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-best-markovian-arm-identification-1 |
| Repo | |
| Framework | |
Robust Tensor Completion Using Transformed Tensor SVD
| Title | Robust Tensor Completion Using Transformed Tensor SVD |
| Authors | Guangjing Song, Michael K. Ng, Xiongjun Zhang |
| Abstract | In this paper, we study robust tensor completion by using transformed tensor singular value decomposition (SVD), which employs unitary transform matrices instead of discrete Fourier transform matrix that is used in the traditional tensor SVD. The main motivation is that a lower tubal rank tensor can be obtained by using other unitary transform matrices than that by using discrete Fourier transform matrix. This would be more effective for robust tensor completion. Experimental results for hyperspectral, video and face datasets have shown that the recovery performance for the robust tensor completion problem by using transformed tensor SVD is better in PSNR than that by using Fourier transform and other robust tensor completion methods. |
| Tasks | |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01113v1 |
| https://arxiv.org/pdf/1907.01113v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-tensor-completion-using-transformed |
| Repo | |
| Framework | |
Constructing large scale biomedical knowledge bases from scratch with rapid annotation of interpretable patterns
| Title | Constructing large scale biomedical knowledge bases from scratch with rapid annotation of interpretable patterns |
| Authors | Julien Fauqueur, Ashok Thillaisundaram, Theodosia Togia |
| Abstract | Knowledge base construction is crucial for summarising, understanding and inferring relationships between biomedical entities. However, for many practical applications such as drug discovery, the scarcity of relevant facts (e.g. gene X is therapeutic target for disease Y) severely limits a domain expert’s ability to create a usable knowledge base, either directly or by training a relation extraction model. In this paper, we present a simple and effective method of extracting new facts with a pre-specified binary relationship type from the biomedical literature, without requiring any training data or hand-crafted rules. Our system discovers, ranks and presents the most salient patterns to domain experts in an interpretable form. By marking patterns as compatible with the desired relationship type, experts indirectly batch-annotate candidate pairs whose relationship is expressed with such patterns in the literature. Even with a complete absence of seed data, experts are able to discover thousands of high-quality pairs with the desired relationship within minutes. When a small number of relevant pairs do exist - even when their relationship is more general (e.g. gene X is biologically associated with disease Y) than the relationship of interest - our system leverages them in order to i) learn a better ranking of the patterns to be annotated or ii) generate weakly labelled pairs in a fully automated manner. We evaluate our method both intrinsically and via a downstream knowledge base completion task, and show that it is an effective way of constructing knowledge bases when few or no relevant facts are already available. |
| Tasks | Drug Discovery, Knowledge Base Completion, Relation Extraction |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01417v2 |
| https://arxiv.org/pdf/1907.01417v2.pdf | |
| PWC | https://paperswithcode.com/paper/constructing-large-scale-biomedical-knowledge |
| Repo | |
| Framework | |
Graduated Fidelity Lattices for Motion Planning under Uncertainty
| Title | Graduated Fidelity Lattices for Motion Planning under Uncertainty |
| Authors | Adrián González-Sieira, Manuel Mucientes, Alberto Bugarín |
| Abstract | We present a novel approach for motion planning in mobile robotics under sensing and motion uncertainty based on state lattices with graduated fidelity. The probability of collision is reliably estimated considering the robot shape, and the fidelity adapts to the complexity of the environment, improving the planning efficiency while maintaining the performance. Safe and optimal paths are found with an informed search algorithm, for which a novel multi-resolution heuristic is presented. Results for different scenarios and robot shapes are given, showing the validity of the proposed methods. |
| Tasks | Motion Planning |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13531v1 |
| https://arxiv.org/pdf/1905.13531v1.pdf | |
| PWC | https://paperswithcode.com/paper/graduated-fidelity-lattices-for-motion |
| Repo | |
| Framework | |
Forecasting Spatio-Temporal Renewable Scenarios: a Deep Generative Approach
| Title | Forecasting Spatio-Temporal Renewable Scenarios: a Deep Generative Approach |
| Authors | Congmei Jiang, Yize Chen, Yongfang Mao, Yi Chai, Mingbiao Yu |
| Abstract | The operation and planning of large-scale power systems are becoming more challenging with the increasing penetration of stochastic renewable generation. In order to minimize the decision risks in power systems with large amount of renewable resources, there is a growing need to model the short-term generation uncertainty. By producing a group of possible future realizations for certain set of renewable generation plants, scenario approach has become one popular way for renewables uncertainty modeling. However, due to the complex spatial and temporal correlations underlying in renewable generations, traditional model-based approaches for forecasting future scenarios often require extensive knowledge, while fitted models are often hard to scale. To address such modeling burdens, we propose a learning-based, data-driven scenario forecasts method based on generative adversarial networks (GANs), which is a class of deep-learning generative algorithms used for modeling unknown distributions. We firstly utilize an improved GANs with convergence guarantees to learn the intrinsic patterns and model the unknown distributions of (multiple-site) renewable generation time-series. Then by solving an optimization problem, we are able to generate forecasted scenarios without any scenario number and forecasting horizon restrictions. Our method is totally model-free, and could forecast scenarios under different level of forecast uncertainties. Extensive numerical simulations using real-world data from NREL wind and solar integration datasets validate the performance of proposed method in forecasting both wind and solar power scenarios. |
| Tasks | Time Series |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.05274v1 |
| http://arxiv.org/pdf/1903.05274v1.pdf | |
| PWC | https://paperswithcode.com/paper/forecasting-spatio-temporal-renewable |
| Repo | |
| Framework | |
Encoding Categorical Variables with Conjugate Bayesian Models for WeWork Lead Scoring Engine
| Title | Encoding Categorical Variables with Conjugate Bayesian Models for WeWork Lead Scoring Engine |
| Authors | Austin Slakey, Daniel Salas, Yoni Schamroth |
| Abstract | Applied Data Scientists throughout various industries are commonly faced with the challenging task of encoding high-cardinality categorical features into digestible inputs for machine learning algorithms. This paper describes a Bayesian encoding technique developed for WeWork’s lead scoring engine which outputs the probability of a person touring one of our office spaces based on interaction, enrichment, and geospatial data. We present a paradigm for ensemble modeling which mitigates the need to build complicated preprocessing and encoding schemes for categorical variables. In particular, domain-specific conjugate Bayesian models are employed as base learners for features in a stacked ensemble model. For each column of a categorical feature matrix we fit a problem-specific prior distribution, for example, the Beta distribution for a binary classification problem. In order to analytically derive the moments of the posterior distribution, we update the prior with the conjugate likelihood of the corresponding target variable for each unique value of the given categorical feature. This function of column and value encodes the categorical feature matrix so that the final learner in the ensemble model ingests low-dimensional numerical input. Experimental results on both curated and real world datasets demonstrate impressive accuracy and computational efficiency on a variety of problem archetypes. Particularly, for the lead scoring engine at WeWork – where some categorical features have as many as 300,000 levels – we have seen an AUC improvement from 0.87 to 0.97 through implementing conjugate Bayesian model encoding. |
| Tasks | |
| Published | 2019-04-30 |
| URL | http://arxiv.org/abs/1904.13001v1 |
| http://arxiv.org/pdf/1904.13001v1.pdf | |
| PWC | https://paperswithcode.com/paper/encoding-categorical-variables-with-conjugate |
| Repo | |
| Framework | |
Hindsight Credit Assignment
| Title | Hindsight Credit Assignment |
| Authors | Anna Harutyunyan, Will Dabney, Thomas Mesnard, Mohammad Azar, Bilal Piot, Nicolas Heess, Hado van Hasselt, Greg Wayne, Satinder Singh, Doina Precup, Remi Munos |
| Abstract | We consider the problem of efficient credit assignment in reinforcement learning. In order to efficiently and meaningfully utilize new data, we propose to explicitly assign credit to past decisions based on the likelihood of them having led to the observed outcome. This approach uses new information in hindsight, rather than employing foresight. Somewhat surprisingly, we show that value functions can be rewritten through this lens, yielding a new family of algorithms. We study the properties of these algorithms, and empirically show that they successfully address important credit assignment challenges, through a set of illustrative tasks. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02503v1 |
| https://arxiv.org/pdf/1912.02503v1.pdf | |
| PWC | https://paperswithcode.com/paper/hindsight-credit-assignment-1 |
| Repo | |
| Framework | |
Concurrent Parsing of Constituency and Dependency
| Title | Concurrent Parsing of Constituency and Dependency |
| Authors | Junru Zhou, Shuailiang Zhang, Hai Zhao |
| Abstract | Constituent and dependency representation for syntactic structure share a lot of linguistic and computational characteristics, this paper thus makes the first attempt by introducing a new model that is capable of parsing constituent and dependency at the same time, so that lets either of the parsers enhance each other. Especially, we evaluate the effect of different shared network components and empirically verify that dependency parsing may be much more beneficial from constituent parsing structure. The proposed parser achieves new state-of-the-art performance for both parsing tasks, constituent and dependency on PTB and CTB benchmarks. |
| Tasks | Dependency Parsing |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.06379v2 |
| https://arxiv.org/pdf/1908.06379v2.pdf | |
| PWC | https://paperswithcode.com/paper/concurrent-parsing-of-constituency-and |
| Repo | |
| Framework | |
Neural Network based Deep Transfer Learning for Cross-domain Dependency Parsing
| Title | Neural Network based Deep Transfer Learning for Cross-domain Dependency Parsing |
| Authors | Zhentao Xia, Likai Wang, Weiguang Qu, Junsheng Zhou, Yanhui Gu |
| Abstract | In this paper, we describe the details of the neural dependency parser sub-mitted by our team to the NLPCC 2019 Shared Task of Semi-supervised do-main adaptation subtask on Cross-domain Dependency Parsing. Our system is based on the stack-pointer networks(STACKPTR). Considering the im-portance of context, we utilize self-attention mechanism for the representa-tion vectors to capture the meaning of words. In addition, to adapt three dif-ferent domains, we utilize neural network based deep transfer learning which transfers the pre-trained partial network in the source domain to be a part of deep neural network in the three target domains (product comments, product blogs and web fiction) respectively. Results on the three target domains demonstrate that our model performs competitively. |
| Tasks | Dependency Parsing, Transfer Learning |
| Published | 2019-08-08 |
| URL | https://arxiv.org/abs/1908.02895v1 |
| https://arxiv.org/pdf/1908.02895v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-based-deep-transfer-learning |
| Repo | |
| Framework | |
Disinformation Detection: A review of linguistic feature selection and classification models in news veracity assessments
| Title | Disinformation Detection: A review of linguistic feature selection and classification models in news veracity assessments |
| Authors | Jillian Tompkins |
| Abstract | Over the past couple of years, the topic of “fake news” and its influence over people’s opinions has become a growing cause for concern. Although the spread of disinformation on the Internet is not a new phenomenon, the widespread use of social media has exacerbated its effects, providing more channels for dissemination and the potential to “go viral.” Nowhere was this more evident than during the 2016 United States Presidential Election. Although the current of disinformation spread via trolls, bots, and hyperpartisan media outlets likely reinforced existing biases rather than sway undecided voters, the effects of this deluge of disinformation are by no means trivial. The consequences range in severity from an overall distrust in news media, to an ill-informed citizenry, and in extreme cases, provocation of violent action. It is clear that human ability to discern lies from truth is flawed at best. As such, greater attention has been given towards applying machine learning approaches to detect deliberately deceptive news articles. This paper looks at the work that has already been done in this area. |
| Tasks | Feature Selection |
| Published | 2019-10-26 |
| URL | https://arxiv.org/abs/1910.12073v1 |
| https://arxiv.org/pdf/1910.12073v1.pdf | |
| PWC | https://paperswithcode.com/paper/disinformation-detection-a-review-of |
| Repo | |
| Framework | |
Structure-Invariant Testing for Machine Translation
| Title | Structure-Invariant Testing for Machine Translation |
| Authors | Pinjia He, Clara Meister, Zhendong Su |
| Abstract | In recent years, machine translation software has increasingly been integrated into our daily lives. People routinely use machine translation for various applications, such as describing symptoms to a foreign doctor and reading political news in a foreign language. However, due to the complexity and intractability of neural machine translation (NMT) models that power modern machine translation systems, these systems are far from being robust. They can return inferior results that lead to misunderstanding, medical misdiagnoses, or threats to personal safety. Despite its apparent importance, validating the robustness of machine translation is very difficult and has, therefore, been much under-explored. To tackle this challenge, we introduce structure-invariant testing (SIT), a novel, widely applicable metamorphic testing methodology for validating machine translation software. Our key insight is that the translation results of similar source sentences should typically exhibit a similar sentence structure. SIT is designed to leverage this insight to test any machine translation system with unlabeled sentences; it specifically targets mistranslations that are difficult-to-find using state-of-the-art translation quality metrics such as BLEU. We have realized a practical implementation of SIT by (1) substituting one word in a given sentence with semantically similar, syntactically equivalent words to generate similar sentences, and (2) using syntax parse trees (obtained via constituency/dependency parsing) to represent sentence structure. To evaluate SIT, we have used it to test Google Translate and Bing Microsoft Translator with 200 unlabeled sentences as input, which led to 56 and 61 buggy translations with 60% and 61% top-1 accuracy, respectively. The bugs are diverse, including under-translation, over-translation, incorrect modification, word/phrase mistranslation, and unclear logic. |
| Tasks | Dependency Parsing, Machine Translation |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08710v2 |
| https://arxiv.org/pdf/1907.08710v2.pdf | |
| PWC | https://paperswithcode.com/paper/structure-invariant-testing-for-machine |
| Repo | |
| Framework | |
