July 28, 2019

2929 words 14 mins read

Paper Group ANR 272

Learning to Parse and Translate Improves Neural Machine Translation. Capturing natural-colour 3D models of insects for species discovery. The Algorithmic Inflection of Russian and Generation of Grammatically Correct Text. Variational Adaptive-Newton Method for Explorative Learning. Active Self-Paced Learning for Cost-Effective and Progressive Face …

Learning to Parse and Translate Improves Neural Machine Translation


Title	Learning to Parse and Translate Improves Neural Machine Translation
Authors	Akiko Eriguchi, Yoshimasa Tsuruoka, Kyunghyun Cho
Abstract	There has been relatively little attention to incorporating linguistic prior to neural machine translation. Much of the previous work was further constrained to considering linguistic prior on the source side. In this paper, we propose a hybrid model, called NMT+RNNG, that learns to parse and translate by combining the recurrent neural network grammar into the attention-based neural machine translation. Our approach encourages the neural machine translation model to incorporate linguistic prior during training, and lets it translate on its own afterward. Extensive experiments with four language pairs show the effectiveness of the proposed NMT+RNNG.
Tasks	Machine Translation
Published	2017-02-12
URL	http://arxiv.org/abs/1702.03525v2
PDF	http://arxiv.org/pdf/1702.03525v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-parse-and-translate-improves
Repo
Framework

Capturing natural-colour 3D models of insects for species discovery


Title	Capturing natural-colour 3D models of insects for species discovery
Authors	Chuong V. Nguyen, David R. Lovell, Matt Adcock, John La Salle
Abstract	Collections of biological specimens are fundamental to scientific understanding and characterization of natural diversity. This paper presents a system for liberating useful information from physical collections by bringing specimens into the digital domain so they can be more readily shared, analyzed, annotated and compared. It focuses on insects and is strongly motivated by the desire to accelerate and augment current practices in insect taxonomy which predominantly use text, 2D diagrams and images to describe and characterize species. While these traditional kinds of descriptions are informative and useful, they cannot cover insect specimens “from all angles” and precious specimens are still exchanged between researchers and collections for this reason. Furthermore, insects can be complex in structure and pose many challenges to computer vision systems. We present a new prototype for a practical, cost-effective system of off-the-shelf components to acquire natural-colour 3D models of insects from around 3mm to 30mm in length. Colour images are captured from different angles and focal depths using a digital single lens reflex (DSLR) camera rig and two-axis turntable. These 2D images are processed into 3D reconstructions using software based on a visual hull algorithm. The resulting models are compact (around 10 megabytes), afford excellent optical resolution, and can be readily embedded into documents and web pages, as well as viewed on mobile devices. The system is portable, safe, relatively affordable, and complements the sort of volumetric data that can be acquired by computed tomography. This system provides a new way to augment the description and documentation of insect species holotypes, reducing the need to handle or ship specimens. It opens up new opportunities to collect data for research, education, art, entertainment, biodiversity assessment and biosecurity control.
Tasks
Published	2017-09-07
URL	http://arxiv.org/abs/1709.02039v1
PDF	http://arxiv.org/pdf/1709.02039v1.pdf
PWC	https://paperswithcode.com/paper/capturing-natural-colour-3d-models-of-insects
Repo
Framework

The Algorithmic Inflection of Russian and Generation of Grammatically Correct Text


Title	The Algorithmic Inflection of Russian and Generation of Grammatically Correct Text
Authors	T. M. Sadykov, T. A. Zhukov
Abstract	We present a deterministic algorithm for Russian inflection. This algorithm is implemented in a publicly available web-service www.passare.ru which provides functions for inflection of single words, word matching and synthesis of grammatically correct Russian text. The inflectional functions have been tested against the annotated corpus of Russian language OpenCorpora.
Tasks
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02551v1
PDF	http://arxiv.org/pdf/1706.02551v1.pdf
PWC	https://paperswithcode.com/paper/the-algorithmic-inflection-of-russian-and
Repo
Framework

Variational Adaptive-Newton Method for Explorative Learning


Title	Variational Adaptive-Newton Method for Explorative Learning
Authors	Mohammad Emtiyaz Khan, Wu Lin, Voot Tangkaratt, Zuozhu Liu, Didrik Nielsen
Abstract	We present the Variational Adaptive Newton (VAN) method which is a black-box optimization method especially suitable for explorative-learning tasks such as active learning and reinforcement learning. Similar to Bayesian methods, VAN estimates a distribution that can be used for exploration, but requires computations that are similar to continuous optimization methods. Our theoretical contribution reveals that VAN is a second-order method that unifies existing methods in distinct fields of continuous optimization, variational inference, and evolution strategies. Our experimental results show that VAN performs well on a wide-variety of learning tasks. This work presents a general-purpose explorative-learning method that has the potential to improve learning in areas such as active learning and reinforcement learning.
Tasks	Active Learning
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05560v1
PDF	http://arxiv.org/pdf/1711.05560v1.pdf
PWC	https://paperswithcode.com/paper/variational-adaptive-newton-method-for
Repo
Framework

Active Self-Paced Learning for Cost-Effective and Progressive Face Identification


Title	Active Self-Paced Learning for Cost-Effective and Progressive Face Identification
Authors	Liang Lin, Keze Wang, Deyu Meng, Wangmeng Zuo, Lei Zhang
Abstract	This paper aims to develop a novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals. By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert re-certification. We first initialize the classifier using a few annotated samples for each individual, and extract image features using the convolutional neural nets. Then, a number of candidates are selected from the unannotated samples for classifier updating, in which we apply the current classifiers ranking the samples by the prediction confidence. In particular, our approach utilizes the high-confidence and low-confidence samples in the self-paced and the active user-query way, respectively. The neural nets are later fine-tuned based on the updated classifiers. Such heuristic implementation is formulated as solving a concise active SPL optimization problem, which also advances the SPL development by supplementing a rational dynamic curriculum constraint. The new model finely accords with the “instructor-student-collaborative” learning mode in human education. The advantages of this proposed framework are two-folds: i) The required number of annotated samples is significantly decreased while the comparable performance is guaranteed. A dramatic reduction of user effort is also achieved over other state-of-the-art active learning techniques. ii) The mixture of SPL and AL effectively improves not only the classifier accuracy compared to existing AL/SPL methods but also the robustness against noisy data. We evaluate our framework on two challenging datasets, and demonstrate very promising results. (http://hcp.sysu.edu.cn/projects/aspl/)
Tasks	Active Learning, Face Identification
Published	2017-01-13
URL	http://arxiv.org/abs/1701.03555v2
PDF	http://arxiv.org/pdf/1701.03555v2.pdf
PWC	https://paperswithcode.com/paper/active-self-paced-learning-for-cost-effective
Repo
Framework

Boosted Zero-Shot Learning with Semantic Correlation Regularization


Title	Boosted Zero-Shot Learning with Semantic Correlation Regularization
Authors	Te Pi, Xi Li, Zhongfei, Zhang
Abstract	We study zero-shot learning (ZSL) as a transfer learning problem, and focus on the two key aspects of ZSL, model effectiveness and model adaptation. For effective modeling, we adopt the boosting strategy to learn a zero-shot classifier from weak models to a strong model. For adaptable knowledge transfer, we devise a Semantic Correlation Regularization (SCR) approach to regularize the boosted model to be consistent with the inter-class semantic correlations. With SCR embedded in the boosting objective, and with a self-controlled sample selection for learning robustness, we propose a unified framework, Boosted Zero-shot classification with Semantic Correlation Regularization (BZ-SCR). By balancing the SCR-regularized boosted model selection and the self-controlled sample selection, BZ-SCR is capable of capturing both discriminative and adaptable feature-to-class semantic alignments, while ensuring the reliability and adaptability of the learned samples. The experiments on two ZSL datasets show the superiority of BZ-SCR over the state-of-the-arts.
Tasks	Model Selection, Transfer Learning, Zero-Shot Learning
Published	2017-07-25
URL	http://arxiv.org/abs/1707.08008v1
PDF	http://arxiv.org/pdf/1707.08008v1.pdf
PWC	https://paperswithcode.com/paper/boosted-zero-shot-learning-with-semantic
Repo
Framework

Solving the Conjugacy Decision Problem via Machine Learning


Title	Solving the Conjugacy Decision Problem via Machine Learning
Authors	Jonathan Gryak, Robert M. Haralick, Delaram Kahrobaei
Abstract	Machine learning and pattern recognition techniques have been successfully applied to algorithmic problems in free groups. In this paper, we seek to extend these techniques to finitely presented non-free groups, with a particular emphasis on polycyclic and metabelian groups that are of interest to non-commutative cryptography. As a prototypical example, we utilize supervised learning methods to construct classifiers that can solve the conjugacy decision problem, i.e., determine whether or not a pair of elements from a specified group are conjugate. The accuracies of classifiers created using decision trees, random forests, and N-tuple neural network models are evaluated for several non-free groups. The very high accuracy of these classifiers suggests an underlying mathematical relationship with respect to conjugacy in the tested groups.
Tasks
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10417v2
PDF	http://arxiv.org/pdf/1705.10417v2.pdf
PWC	https://paperswithcode.com/paper/solving-the-conjugacy-decision-problem-via
Repo
Framework

Prediction of infectious disease epidemics via weighted density ensembles


Title	Prediction of infectious disease epidemics via weighted density ensembles
Authors	Evan L. Ray, Nicholas G. Reich
Abstract	Accurate and reliable predictions of infectious disease dynamics can be valuable to public health organizations that plan interventions to decrease or prevent disease transmission. A great variety of models have been developed for this task, using different model structures, covariates, and targets for prediction. Experience has shown that the performance of these models varies; some tend to do better or worse in different seasons or at different points within a season. Ensemble methods combine multiple models to obtain a single prediction that leverages the strengths of each model. We considered a range of ensemble methods that each form a predictive density for a target of interest as a weighted sum of the predictive densities from component models. In the simplest case, equal weight is assigned to each component model; in the most complex case, the weights vary with the region, prediction target, week of the season when the predictions are made, a measure of component model uncertainty, and recent observations of disease incidence. We applied these methods to predict measures of influenza season timing and severity in the United States, both at the national and regional levels, using three component models. We trained the models on retrospective predictions from 14 seasons (1997/1998 - 2010/2011) and evaluated each model’s prospective, out-of-sample performance in the five subsequent influenza seasons. In this test phase, the ensemble methods showed overall performance that was similar to the best of the component models, but offered more consistent performance across seasons than the component models. Ensemble methods offer the potential to deliver more reliable predictions to public health decision makers.
Tasks
Published	2017-03-31
URL	http://arxiv.org/abs/1703.10936v1
PDF	http://arxiv.org/pdf/1703.10936v1.pdf
PWC	https://paperswithcode.com/paper/prediction-of-infectious-disease-epidemics
Repo
Framework

Determinism in the Certification of UNSAT Proofs


Title	Determinism in the Certification of UNSAT Proofs
Authors	Tomer Libal, Xaviera Steele
Abstract	The search for increased trustworthiness of SAT solvers is very active and uses various methods. Some of these methods obtain a proof from the provers then check it, normally by replicating the search based on the proof’s information. Because the certification process involves another nontrivial proof search, the trust we can place in it is decreased. Some attempts to amend this use certifiers which have been verified by proofs assistants such as Isabelle/HOL and Coq. Our approach is different because it is based on an extremely simplified certifier. This certifier enjoys a very high level of trust but is very inefficient. In this paper, we experiment with this approach and conclude that by placing some restrictions on the formats, one can mostly eliminate the need for search and in principle, can certify proofs of arbitrary size.
Tasks
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01488v1
PDF	http://arxiv.org/pdf/1712.01488v1.pdf
PWC	https://paperswithcode.com/paper/determinism-in-the-certification-of-unsat
Repo
Framework

Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems


Title	Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems
Authors	Wang Ling, Dani Yogatama, Chris Dyer, Phil Blunsom
Abstract	Solving algebraic word problems requires executing a series of arithmetic operations—a program—to obtain a final answer. However, since programs can be arbitrarily complicated, inducing them directly from question-answer pairs is a formidable challenge. To make this task more feasible, we solve these problems by generating answer rationales, sequences of natural language and human-readable mathematical expressions that derive the final answer through a series of small steps. Although rationales do not explicitly specify programs, they provide a scaffolding for their structure via intermediate milestones. To evaluate our approach, we have created a new 100,000-sample dataset of questions, answers and rationales. Experimental results show that indirect supervision of program learning via answer rationales is a promising strategy for inducing arithmetic programs.
Tasks
Published	2017-05-11
URL	http://arxiv.org/abs/1705.04146v3
PDF	http://arxiv.org/pdf/1705.04146v3.pdf
PWC	https://paperswithcode.com/paper/program-induction-by-rationale-generation
Repo
Framework

Recurrent Generative Adversarial Networks for Proximal Learning and Automated Compressive Image Recovery


Title	Recurrent Generative Adversarial Networks for Proximal Learning and Automated Compressive Image Recovery
Authors	Morteza Mardani, Hatef Monajemi, Vardan Papyan, Shreyas Vasanawala, David Donoho, John Pauly
Abstract	Recovering images from undersampled linear measurements typically leads to an ill-posed linear inverse problem, that asks for proper statistical priors. Building effective priors is however challenged by the low train and test overhead dictated by real-time tasks; and the need for retrieving visually “plausible” and physically “feasible” images with minimal hallucination. To cope with these challenges, we design a cascaded network architecture that unrolls the proximal gradient iterations by permeating benefits from generative residual networks (ResNet) to modeling the proximal operator. A mixture of pixel-wise and perceptual costs is then deployed to train proximals. The overall architecture resembles back-and-forth projection onto the intersection of feasible and plausible images. Extensive computational experiments are examined for a global task of reconstructing MR images of pediatric patients, and a more local task of superresolving CelebA faces, that are insightful to design efficient architectures. Our observations indicate that for MRI reconstruction, a recurrent ResNet with a single residual block effectively learns the proximal. This simple architecture appears to significantly outperform the alternative deep ResNet architecture by 2dB SNR, and the conventional compressed-sensing MRI by 4dB SNR with 100x faster inference. For image superresolution, our preliminary results indicate that modeling the denoising proximal demands deep ResNets.
Tasks	Denoising
Published	2017-11-27
URL	http://arxiv.org/abs/1711.10046v1
PDF	http://arxiv.org/pdf/1711.10046v1.pdf
PWC	https://paperswithcode.com/paper/recurrent-generative-adversarial-networks-for
Repo
Framework

Drought Stress Classification using 3D Plant Models


Title	Drought Stress Classification using 3D Plant Models
Authors	Siddharth Srivastava, Swati Bhugra, Brejesh Lall, Santanu Chaudhury
Abstract	Quantification of physiological changes in plants can capture different drought mechanisms and assist in selection of tolerant varieties in a high throughput manner. In this context, an accurate 3D model of plant canopy provides a reliable representation for drought stress characterization in contrast to using 2D images. In this paper, we propose a novel end-to-end pipeline including 3D reconstruction, segmentation and feature extraction, leveraging deep neural networks at various stages, for drought stress study. To overcome the high degree of self-similarities and self-occlusions in plant canopy, prior knowledge of leaf shape based on features from deep siamese network are used to construct an accurate 3D model using structure from motion on wheat plants. The drought stress is characterized with a deep network based feature aggregation. We compare the proposed methodology on several descriptors, and show that the network outperforms conventional methods.
Tasks	3D Reconstruction
Published	2017-09-21
URL	http://arxiv.org/abs/1709.09496v2
PDF	http://arxiv.org/pdf/1709.09496v2.pdf
PWC	https://paperswithcode.com/paper/drought-stress-classification-using-3d-plant
Repo
Framework

Robustness to Adversarial Examples through an Ensemble of Specialists


Title	Robustness to Adversarial Examples through an Ensemble of Specialists
Authors	Mahdieh Abbasi, Christian Gagné
Abstract	We are proposing to use an ensemble of diverse specialists, where speciality is defined according to the confusion matrix. Indeed, we observed that for adversarial instances originating from a given class, labeling tend to be done into a small subset of (incorrect) classes. Therefore, we argue that an ensemble of specialists should be better able to identify and reject fooling instances, with a high entropy (i.e., disagreement) over the decisions in the presence of adversaries. Experimental results obtained confirm that interpretation, opening a way to make the system more robust to adversarial examples through a rejection mechanism, rather than trying to classify them properly at any cost.
Tasks
Published	2017-02-22
URL	http://arxiv.org/abs/1702.06856v3
PDF	http://arxiv.org/pdf/1702.06856v3.pdf
PWC	https://paperswithcode.com/paper/robustness-to-adversarial-examples-through-an
Repo
Framework

Harmonic Grammar, Optimality Theory, and Syntax Learnability: An Empirical Exploration of Czech Word Order


Title	Harmonic Grammar, Optimality Theory, and Syntax Learnability: An Empirical Exploration of Czech Word Order
Authors	Ann Irvine, Mark Dredze
Abstract	This work presents a systematic theoretical and empirical comparison of the major algorithms that have been proposed for learning Harmonic and Optimality Theory grammars (HG and OT, respectively). By comparing learning algorithms, we are also able to compare the closely related OT and HG frameworks themselves. Experimental results show that the additional expressivity of the HG framework over OT affords performance gains in the task of predicting the surface word order of Czech sentences. We compare the perceptron with the classic Gradual Learning Algorithm (GLA), which learns OT grammars, as well as the popular Maximum Entropy model. In addition to showing that the perceptron is theoretically appealing, our work shows that the performance of the HG model it learns approaches that of the upper bound in prediction accuracy on a held out test set and that it is capable of accurately modeling observed variation.
Tasks
Published	2017-02-19
URL	http://arxiv.org/abs/1702.05793v1
PDF	http://arxiv.org/pdf/1702.05793v1.pdf
PWC	https://paperswithcode.com/paper/harmonic-grammar-optimality-theory-and-syntax
Repo
Framework

Learning Joint Multilingual Sentence Representations with Neural Machine Translation


Title	Learning Joint Multilingual Sentence Representations with Neural Machine Translation
Authors	Holger Schwenk, Matthijs Douze
Abstract	In this paper, we use the framework of neural machine translation to learn joint sentence representations across six very different languages. Our aim is that a representation which is independent of the language, is likely to capture the underlying semantics. We define a new cross-lingual similarity measure, compare up to 1.4M sentence representations and study the characteristics of close sentences. We provide experimental evidence that sentences that are close in embedding space are indeed semantically highly related, but often have quite different structure and syntax. These relations also hold when comparing sentences in different languages.
Tasks	Joint Multilingual Sentence Representations, Machine Translation
Published	2017-04-13
URL	http://arxiv.org/abs/1704.04154v2
PDF	http://arxiv.org/pdf/1704.04154v2.pdf
PWC	https://paperswithcode.com/paper/learning-joint-multilingual-sentence
Repo
Framework