October 18, 2019

2818 words 14 mins read

Paper Group ANR 597

Paracompositionality, MWEs and Argument Substitution. Distinguishing Question Subjectivity from Difficulty for Improved Crowdsourcing. Attentive Recurrent Tensor Model for Community Question Answering. Fast Fourier-Based Generation of the Compression Matrix for Deterministic Compressed Sensing. Ladder Networks for Semi-Supervised Hyperspectral Imag …

Paracompositionality, MWEs and Argument Substitution


Title	Paracompositionality, MWEs and Argument Substitution
Authors	Cem Bozsahin, Arzu Burcu Guven
Abstract	Multi-word expressions, verb-particle constructions, idiomatically combining phrases, and phrasal idioms have something in common: not all of their elements contribute to the argument structure of the predicate implicated by the expression. Radically lexicalized theories of grammar that avoid string-, term-, logical form-, and tree-writing, and categorial grammars that avoid wrap operation, make predictions about the categories involved in verb-particles and phrasal idioms. They may require singleton types, which can only substitute for one value, not just for one kind of value. These types are asymmetric: they can be arguments only. They also narrowly constrain the kind of semantic value that can correspond to such syntactic categories. Idiomatically combining phrases do not subcategorize for singleton types, and they exploit another locally computable and compositional property of a correspondence, that every syntactic expression can project its head word. Such MWEs can be seen as empirically realized categorial possibilities, rather than lacuna in a theory of lexicalizable syntactic categories.
Tasks
Published	2018-05-22
URL	http://arxiv.org/abs/1805.08438v1
PDF	http://arxiv.org/pdf/1805.08438v1.pdf
PWC	https://paperswithcode.com/paper/paracompositionality-mwes-and-argument
Repo
Framework

Distinguishing Question Subjectivity from Difficulty for Improved Crowdsourcing


Title	Distinguishing Question Subjectivity from Difficulty for Improved Crowdsourcing
Authors	Yuan Jin, Mark Carman, Ye Zhu, Wray Buntine
Abstract	The questions in a crowdsourcing task typically exhibit varying degrees of difficulty and subjectivity. Their joint effects give rise to the variation in responses to the same question by different crowd-workers. This variation is low when the question is easy to answer and objective, and high when it is difficult and subjective. Unfortunately, current quality control methods for crowdsourcing consider only the question difficulty to account for the variation. As a result,these methods cannot distinguish workers personal preferences for different correct answers of a partially subjective question from their ability/expertise to avoid objectively wrong answers for that question. To address this issue, we present a probabilistic model which (i) explicitly encodes question difficulty as a model parameter and (ii) implicitly encodes question subjectivity via latent preference factors for crowd-workers. We show that question subjectivity induces grouping of crowd-workers, revealed through clustering of their latent preferences. Moreover, we develop a quantitative measure of the subjectivity of a question. Experiments show that our model(1) improves the performance of both quality control for crowd-sourced answers and next answer prediction for crowd-workers,and (2) can potentially provide coherent rankings of questions in terms of their difficulty and subjectivity, so that task providers can refine their designs of the crowdsourcing tasks, e.g. by removing highly subjective questions or inappropriately difficult questions.
Tasks
Published	2018-02-12
URL	http://arxiv.org/abs/1802.04009v2
PDF	http://arxiv.org/pdf/1802.04009v2.pdf
PWC	https://paperswithcode.com/paper/distinguishing-question-subjectivity-from
Repo
Framework

Attentive Recurrent Tensor Model for Community Question Answering


Title	Attentive Recurrent Tensor Model for Community Question Answering
Authors	Gaurav Bhatt, Shivam Sharma, Balasubramanian Raman
Abstract	A major challenge to the problem of community question answering is the lexical and semantic gap between the sentence representations. Some solutions to minimize this gap includes the introduction of extra parameters to deep models or augmenting the external handcrafted features. In this paper, we propose a novel attentive recurrent tensor network for solving the lexical and semantic gap in community question answering. We introduce token-level and phrase-level attention strategy that maps input sequences to the output using trainable parameters. Further, we use the tensor parameters to introduce a 3-way interaction between question, answer and external features in vector space. We introduce simplified tensor matrices with L2 regularization that results in smooth optimization during training. The proposed model achieves state-of-the-art performance on the task of answer sentence selection (TrecQA and WikiQA datasets) while outperforming the current state-of-the-art on the tasks of best answer selection (Yahoo! L4) and answer triggering task (WikiQA).
Tasks	Answer Selection, Community Question Answering, L2 Regularization, Question Answering
Published	2018-01-21
URL	http://arxiv.org/abs/1801.06792v1
PDF	http://arxiv.org/pdf/1801.06792v1.pdf
PWC	https://paperswithcode.com/paper/attentive-recurrent-tensor-model-for
Repo
Framework

Fast Fourier-Based Generation of the Compression Matrix for Deterministic Compressed Sensing


Title	Fast Fourier-Based Generation of the Compression Matrix for Deterministic Compressed Sensing
Authors	Sai Charan Jajimi
Abstract	The primary goal of this work is to review the importance of data compression and present a fast Fourier-based method for generating the deterministic compression matrix in the area of deterministic compressed sensing. The principle concepts of data compression such as general process of data compression, sparse signals, coherence matrix and Restricted Isometry Property (RIP) have been defined. We have introduced two methods of sparse data compression. The first method is formed by utilizing a stochastic matrix which is a common approach, and the second method is created by utilizing a deterministic matrix which is proposed more recently. The main goal of this work is to improve the execution time of the deterministic matrix generation. The execution time is related to the generation method of the deterministic matrix. Furthermore, we have implemented a software which makes it possible to compare different methods of reconstructing data compression. To make this comparison, it is necessary to draw and compare certain graphs, e.g. phase transition, the ratio of output signal to noise and input signal to noise, signal to noise output and also the ratio of percentage of accurate reconstructing and order of sparse signals for various reconstructing methods. To facilitate this process, the user would be able to draw his/her favorite graphs in GUI environment.
Tasks
Published	2018-07-01
URL	http://arxiv.org/abs/1807.01238v1
PDF	http://arxiv.org/pdf/1807.01238v1.pdf
PWC	https://paperswithcode.com/paper/fast-fourier-based-generation-of-the
Repo
Framework

Ladder Networks for Semi-Supervised Hyperspectral Image Classification


Title	Ladder Networks for Semi-Supervised Hyperspectral Image Classification
Authors	Julian Büchel, Okan Ersoy
Abstract	We used the Ladder Network [Rasmus et al. (2015)] to perform Hyperspectral Image Classification in a semi-supervised setting. The Ladder Network distinguishes itself from other semi-supervised methods by jointly optimizing a supervised and unsupervised cost. In many settings this has proven to be more successful than other semi-supervised techniques, such as pretraining using unlabeled data. We furthermore show that the convolutional Ladder Network outperforms most of the current techniques used in hyperspectral image classification and achieves new state-of-the-art performance on the Pavia University dataset given only 5 labeled data points per class.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01222v1
PDF	http://arxiv.org/pdf/1812.01222v1.pdf
PWC	https://paperswithcode.com/paper/ladder-networks-for-semi-supervised
Repo
Framework

A Wasserstein GAN model with the total variational regularization


Title	A Wasserstein GAN model with the total variational regularization
Authors	Lijun Zhang, Yujin Zhang, Yongbin Gao
Abstract	It is well known that the generative adversarial nets (GANs) are remarkably difficult to train. The recently proposed Wasserstein GAN (WGAN) creates principled research directions towards addressing these issues. But we found in practice that gradient penalty WGANs (GP-WGANs) still suffer from training instability. In this paper, we combine a Total Variational (TV) regularizing term into the WGAN formulation instead of weight clipping or gradient penalty, which implies that the Lipschitz constraint is enforced on the critic network. Our proposed method is more stable at training than GP-WGANs and works well across varied GAN architectures. We also present a method to control the trade-off between image diversity and visual quality. It does not bring any computation burden.
Tasks
Published	2018-12-03
URL	http://arxiv.org/abs/1812.00810v1
PDF	http://arxiv.org/pdf/1812.00810v1.pdf
PWC	https://paperswithcode.com/paper/a-wasserstein-gan-model-with-the-total
Repo
Framework

A Framework for Robot Programming in Cobotic Environments: First user experiments


Title	A Framework for Robot Programming in Cobotic Environments: First user experiments
Authors	Ying Siu Liang, Damien Pellier, Humbert Fiorino, Sylvie Pesty
Abstract	The increasing presence of robots in industries has not gone unnoticed. Large industrial players have incorporated them into their production lines, but smaller companies hesitate due to high initial costs and the lack of programming expertise. In this work we introduce a framework that combines two disciplines, Programming by Demonstration and Automated Planning, to allow users without any programming knowledge to program a robot. The user teaches the robot atomic actions together with their semantic meaning and represents them in terms of preconditions and effects. Using these atomic actions the robot can generate action sequences autonomously to reach any goal given by the user. We evaluated the usability of our framework in terms of user experiments with a Baxter Research Robot and showed that it is well-adapted to users without any programming experience.
Tasks
Published	2018-10-19
URL	http://arxiv.org/abs/1810.08492v1
PDF	http://arxiv.org/pdf/1810.08492v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-robot-programming-in-cobotic
Repo
Framework

A framework for remote sensing images processing using deep learning technique


Title	A framework for remote sensing images processing using deep learning technique
Authors	Rémi Cresson
Abstract	Deep learning techniques are becoming increasingly important to solve a number of image processing tasks. Among common algorithms, Convolutional Neural Networks and Recurrent Neural Networks based systems achieve state of the art results on satellite and aerial imagery in many applications. While these approaches are subject to scientific interest, there is currently no operational and generic implementation available at user-level for the remote sensing community. In this paper, we presents a framework enabling the use of deep learning techniques with remote sensing images and geospatial data. Our solution takes roots in two extensively used open-source libraries, the remote sensing image processing library Orfeo ToolBox, and the high performance numerical computation library TensorFlow. It can apply deep nets without restriction on images size and is computationally efficient, regardless hardware configuration.
Tasks
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06535v2
PDF	http://arxiv.org/pdf/1807.06535v2.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-remote-sensing-images
Repo
Framework

Analysis of Railway Accidents’ Narratives Using Deep Learning


Title	Analysis of Railway Accidents’ Narratives Using Deep Learning
Authors	Mojtaba Heidarysafa, Kamran Kowsari, Laura E. Barnes, Donald E. Brown
Abstract	Automatic understanding of domain specific texts in order to extract useful relationships for later use is a non-trivial task. One such relationship would be between railroad accidents’ causes and their correspondent descriptions in reports. From 2001 to 2016 rail accidents in the U.S. cost more than $4.6B. Railroads involved in accidents are required to submit an accident report to the Federal Railroad Administration (FRA). These reports contain a variety of fixed field entries including primary cause of the accidents (a coded variable with 389 values) as well as a narrative field which is a short text description of the accident. Although these narratives provide more information than a fixed field entry, the terminologies used in these reports are not easy to understand by a non-expert reader. Therefore, providing an assisting method to fill in the primary cause from such domain specific texts(narratives) would help to label the accidents with more accuracy. Another important question for transportation safety is whether the reported accident cause is consistent with narrative description. To address these questions, we applied deep learning methods together with powerful word embeddings such as Word2Vec and GloVe to classify accident cause values for the primary cause field using the text in the narratives. The results show that such approaches can both accurately classify accident causes based on report narratives and find important inconsistencies in accident reporting.
Tasks	Word Embeddings
Published	2018-10-17
URL	http://arxiv.org/abs/1810.07382v2
PDF	http://arxiv.org/pdf/1810.07382v2.pdf
PWC	https://paperswithcode.com/paper/analysis-of-railway-accidents-narratives
Repo
Framework

Few-shot learning of neural networks from scratch by pseudo example optimization


Title	Few-shot learning of neural networks from scratch by pseudo example optimization
Authors	Akisato Kimura, Zoubin Ghahramani, Koh Takeuchi, Tomoharu Iwata, Naonori Ueda
Abstract	In this paper, we propose a simple but effective method for training neural networks with a limited amount of training data. Our approach inherits the idea of knowledge distillation that transfers knowledge from a deep or wide reference model to a shallow or narrow target model. The proposed method employs this idea to mimic predictions of reference estimators that are more robust against overfitting than the network we want to train. Different from almost all the previous work for knowledge distillation that requires a large amount of labeled training data, the proposed method requires only a small amount of training data. Instead, we introduce pseudo training examples that are optimized as a part of model parameters. Experimental results for several benchmark datasets demonstrate that the proposed method outperformed all the other baselines, such as naive training of the target model and standard knowledge distillation.
Tasks	Few-Shot Learning
Published	2018-02-08
URL	http://arxiv.org/abs/1802.03039v3
PDF	http://arxiv.org/pdf/1802.03039v3.pdf
PWC	https://paperswithcode.com/paper/few-shot-learning-of-neural-networks-from
Repo
Framework

Identifying Semantic Divergences in Parallel Text without Annotations


Title	Identifying Semantic Divergences in Parallel Text without Annotations
Authors	Yogarshi Vyas, Xing Niu, Marine Carpuat
Abstract	Recognizing that even correct translations are not always semantically equivalent, we automatically detect meaning divergences in parallel sentence pairs with a deep neural model of bilingual semantic similarity which can be trained for any parallel corpus without any manual annotation. We show that our semantic model detects divergences more accurately than models based on surface features derived from word alignments, and that these divergences matter for neural machine translation.
Tasks	Machine Translation, Semantic Similarity, Semantic Textual Similarity
Published	2018-03-29
URL	http://arxiv.org/abs/1803.11112v1
PDF	http://arxiv.org/pdf/1803.11112v1.pdf
PWC	https://paperswithcode.com/paper/identifying-semantic-divergences-in-parallel
Repo
Framework

Chan-Vese Reformulation for Selective Image Segmentation


Title	Chan-Vese Reformulation for Selective Image Segmentation
Authors	Michael Roberts, Jack Spencer
Abstract	Selective segmentation involves incorporating user input to partition an image into foreground and background, by discriminating between objects of a similar type. Typically, such methods involve introducing additional constraints to generic segmentation approaches. However, we show that this is often inconsistent with respect to common assumptions about the image. The proposed method introduces a new fitting term that is more useful in practice than the Chan-Vese framework. In particular, the idea is to define a term that allows for the background to consist of multiple regions of inhomogeneity. We provide comparitive experimental results to alternative approaches to demonstrate the advantages of the proposed method, broadening the possible application of these methods.
Tasks	Semantic Segmentation
Published	2018-11-21
URL	https://arxiv.org/abs/1811.08751v2
PDF	https://arxiv.org/pdf/1811.08751v2.pdf
PWC	https://paperswithcode.com/paper/chan-vese-reformulation-for-selective-image
Repo
Framework

Learning to Support: Exploiting Structure Information in Support Sets for One-Shot Learning


Title	Learning to Support: Exploiting Structure Information in Support Sets for One-Shot Learning
Authors	Jinchao Liu, Stuart J. Gibson, Margarita Osadchy
Abstract	Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only a few representatives of these classes. This problem has previously been approached by meta-learning. Here we propose a novel meta-learner which shows state-of-the-art performance on common benchmarks for one/few shot classification. Our model features three novel components: First is a feed-forward embedding that takes random class support samples (after a customary CNN embedding) and transfers them to a better class representation in terms of a classification problem. Second is a novel attention mechanism, inspired by competitive learning, which causes class representatives to compete with each other to become a temporary class prototype with respect to the query point. This mechanism allows switching between representatives depending on the position of the query point. Once a prototype is chosen for each class, the predicated label is computed using a simple attention mechanism over prototypes of all considered classes. The third feature is the ability of our meta-learner to incorporate deeper CNN embedding, enabling larger capacity. Finally, to ease the training procedure and reduce overfitting, we averages the top $t$ models (evaluated on the validation) over the optimization trajectory. We show that this approach can be viewed as an approximation to an ensemble, which saves the factor of $t$ in training and test times and the factor of of $t$ in the storage of the final model.
Tasks	Meta-Learning, One-Shot Learning
Published	2018-08-22
URL	http://arxiv.org/abs/1808.07270v1
PDF	http://arxiv.org/pdf/1808.07270v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-support-exploiting-structure
Repo
Framework

Fast Neural Machine Translation Implementation


Title	Fast Neural Machine Translation Implementation
Authors	Hieu Hoang, Tomasz Dwojak, Rihards Krislauks, Daniel Torregrosa, Kenneth Heafield
Abstract	This paper describes the submissions to the efficiency track for GPUs at the Workshop for Neural Machine Translation and Generation by members of the University of Edinburgh, Adam Mickiewicz University, Tilde and University of Alicante. We focus on efficient implementation of the recurrent deep-learning model as implemented in Amun, the fast inference engine for neural machine translation. We improve the performance with an efficient mini-batching algorithm, and by fusing the softmax operation with the k-best extraction algorithm. Submissions using Amun were first, second and third fastest in the GPU efficiency track.
Tasks	Machine Translation
Published	2018-05-24
URL	http://arxiv.org/abs/1805.09863v3
PDF	http://arxiv.org/pdf/1805.09863v3.pdf
PWC	https://paperswithcode.com/paper/fast-neural-machine-translation
Repo
Framework

Testing to distinguish measures on metric spaces


Title	Testing to distinguish measures on metric spaces
Authors	Andrew J. Blumberg, Prithwish Bhaumik, Stephen G. Walker
Abstract	We study the problem of distinguishing between two distributions on a metric space; i.e., given metric measure spaces $({\mathbb X}, d, \mu_1)$ and $({\mathbb X}, d, \mu_2)$, we are interested in the problem of determining from finite data whether or not $\mu_1$ is $\mu_2$. The key is to use pairwise distances between observations and, employing a reconstruction theorem of Gromov, we can perform such a test using a two sample Kolmogorov–Smirnov test. A real analysis using phylogenetic trees and flu data is presented.
Tasks
Published	2018-02-04
URL	http://arxiv.org/abs/1802.01152v1
PDF	http://arxiv.org/pdf/1802.01152v1.pdf
PWC	https://paperswithcode.com/paper/testing-to-distinguish-measures-on-metric
Repo
Framework