October 15, 2019

2411 words 12 mins read

Paper Group NANR 112

Paper Group NANR 112

Texture and Steerability based Image Authentication. Local and Global Optimization Techniques in Graph-Based Clustering. Keynote: Use more Machine Translation and Keep Your Customers Happy. Character-level Supervision for Low-resource POS Tagging. Gating out sensory noise in a spike-based Long Short-Term Memory network. Learning a neural response m …

Texture and Steerability based Image Authentication

Title Texture and Steerability based Image Authentication
Authors S.B.G. Tilak Babu, Ch. Srinivasa Rao
Abstract Copy-Move Forgery Detection (CMFD) method is useful for identifying copy and pasted portions in an image. CMFD has demand in forensic investigation, legal evidence and in many other fields. In this paper, the gists of different newly arrived methodologies in current literature are discussed. Some existing methodologies can be able to localize the forged region and some are not. An efficient method for localization of copy move forgery is proposed in this work for identifying forgery. In the proposed methodology, CMFD is achieved by giving suspected image to Steerable Pyramid Transform (SPT), Local Binary Pattern (LBP) is applied on each oriented subband obtained from SPT to extract feature set, then it is used to trained Support Vector Machine (SVM) to classify images into forged or not. Then localization process is carried out on forged images. Results of proposed methodology are showing robustness even though the forged image has undergone some post processing attacks viz., rotation, flip, JPEG compression.
Tasks
Published 2018-01-18
URL https://ieeexplore.ieee.org/document/8262925
PDF https://www.researchgate.net/publication/322649811_Texture_and_steerability_based_image_authentication
PWC https://paperswithcode.com/paper/texture-and-steerability-based-image
Repo
Framework

Local and Global Optimization Techniques in Graph-Based Clustering

Title Local and Global Optimization Techniques in Graph-Based Clustering
Authors Daiki Ikami, Toshihiko Yamasaki, Kiyoharu Aizawa
Abstract The goal of graph-based clustering is to divide a dataset into disjoint subsets with members similar to each other from an affinity (similarity) matrix between data. The most popular method of solving graph-based clustering is spectral clustering. However, spectral clustering has drawbacks. Spectral clustering can only be applied to macro-average-based cost functions, which tend to generate undesirable small clusters. This study first introduces a novel cost function based on micro-average. We propose a local optimization method, which is widely applicable to graph-based clustering cost functions. We also propose an initial-guess-free algorithm to avoid its initialization dependency. Moreover, we present two global optimization techniques. The experimental results exhibit significant clustering performances from our proposed methods, including 100% clustering accuracy in the COIL-20 dataset.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Ikami_Local_and_Global_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Ikami_Local_and_Global_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/local-and-global-optimization-techniques-in
Repo
Framework

Keynote: Use more Machine Translation and Keep Your Customers Happy

Title Keynote: Use more Machine Translation and Keep Your Customers Happy
Authors Glen Poor
Abstract
Tasks Machine Translation
Published 2018-03-01
URL https://www.aclweb.org/anthology/W18-1903/
PDF https://www.aclweb.org/anthology/W18-1903
PWC https://paperswithcode.com/paper/keynote-use-more-machine-translation-and-keep
Repo
Framework

Character-level Supervision for Low-resource POS Tagging

Title Character-level Supervision for Low-resource POS Tagging
Authors Katharina Kann, Johannes Bjerva, Isabelle Augenstein, Barbara Plank, Anders S{\o}gaard
Abstract Neural part-of-speech (POS) taggers are known to not perform well with little training data. As a step towards overcoming this problem, we present an architecture for learning more robust neural POS taggers by jointly training a hierarchical, recurrent model and a recurrent character-based sequence-to-sequence network supervised using an auxiliary objective. This way, we introduce stronger character-level supervision into the model, which enables better generalization to unseen words and provides regularization, making our encoding less prone to overfitting. We experiment with three auxiliary tasks: lemmatization, character-based word autoencoding, and character-based random string autoencoding. Experiments with minimal amounts of labeled data on 34 languages show that our new architecture outperforms a single-task baseline and, surprisingly, that, on average, raw text autoencoding can be as beneficial for low-resource POS tagging as using lemma information. Our neural POS tagger closes the gap to a state-of-the-art POS tagger (MarMoT) for low-resource scenarios by 43{%}, even outperforming it on languages with templatic morphology, e.g., Arabic, Hebrew, and Turkish, by some margin.
Tasks Feature Engineering, Lemmatization, Multi-Task Learning
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3401/
PDF https://www.aclweb.org/anthology/W18-3401
PWC https://paperswithcode.com/paper/character-level-supervision-for-low-resource
Repo
Framework

Gating out sensory noise in a spike-based Long Short-Term Memory network

Title Gating out sensory noise in a spike-based Long Short-Term Memory network
Authors Davide Zambrano, Isabella Pozzi, Roeland Nusselder, Sander Bohte
Abstract Spiking neural networks are being investigated both as biologically plausible models of neural computation and also as a potentially more efficient type of neural network. While convolutional spiking neural networks have been demonstrated to achieve near state-of-the-art performance, only one solution has been proposed to convert gated recurrent neural networks, so far. Recurrent neural networks in the form of networks of gating memory cells have been central in state-of-the-art solutions in problem domains that involve sequence recognition or generation. Here, we design an analog gated LSTM cell where its neurons can be substituted for efficient stochastic spiking neurons. These adaptive spiking neurons implement an adaptive form of sigma-delta coding to convert internally computed analog activation values to spike-trains. For such neurons, we approximate the effective activation function, which resembles a sigmoid. We show how analog neurons with such activation functions can be used to create an analog LSTM cell; networks of these cells can then be trained with standard backpropagation. We train these LSTM networks on a noisy and noiseless version of the original sequence prediction task from Hochreiter & Schmidhuber (1997), and also on a noisy and noiseless version of a classical working memory reinforcement learning task, the T-Maze. Substituting the analog neurons for corresponding adaptive spiking neurons, we then show that almost all resulting spiking neural network equivalents correctly compute the original tasks.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=rk8R_JWRW
PDF https://openreview.net/pdf?id=rk8R_JWRW
PWC https://paperswithcode.com/paper/gating-out-sensory-noise-in-a-spike-based
Repo
Framework

Learning a neural response metric for retinal prosthesis

Title Learning a neural response metric for retinal prosthesis
Authors Nishal P Shah, Sasidhar Madugula, EJ Chichilnisky, Yoram Singer, Jonathon Shlens
Abstract Retinal prostheses for treating incurable blindness are designed to electrically stimulate surviving retinal neurons, causing them to send artificial visual signals to the brain. However, electrical stimulation generally cannot precisely reproduce normal patterns of neural activity in the retina. Therefore, an electrical stimulus must be selected that produces a neural response as close as possible to the desired response. This requires a technique for computing a distance between the desired response and the achievable response that is meaningful in terms of the visual signal being conveyed. Here we propose a method to learn such a metric on neural responses, directly from recorded light responses of a population of retinal ganglion cells (RGCs) in the primate retina. The learned metric produces a measure of similarity of RGC population responses that accurately reflects the similarity of the visual input. Using data from electrical stimulation experiments, we demonstrate that this metric may improve the performance of a prosthesis.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=HJhIM0xAW
PDF https://openreview.net/pdf?id=HJhIM0xAW
PWC https://paperswithcode.com/paper/learning-a-neural-response-metric-for-retinal
Repo
Framework

Lexi: A tool for adaptive, personalized text simplification

Title Lexi: A tool for adaptive, personalized text simplification
Authors Joachim Bingel, Gustavo Paetzold, Anders S{\o}gaard
Abstract Most previous research in text simplification has aimed to develop generic solutions, assuming very homogeneous target audiences with consistent intra-group simplification needs. We argue that this assumption does not hold, and that instead we need to develop simplification systems that adapt to the individual needs of specific users. As a first step towards personalized simplification, we propose a framework for adaptive lexical simplification and introduce Lexi, a free open-source and easily extensible tool for adaptive, personalized text simplification. Lexi is easily installed as a browser extension, enabling easy access to the service for its users.
Tasks Lexical Simplification, Text Simplification
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1021/
PDF https://www.aclweb.org/anthology/C18-1021
PWC https://paperswithcode.com/paper/lexi-a-tool-for-adaptive-personalized-text
Repo
Framework

Exploring Chunk Based Templates for Generating a subset of English Text

Title Exploring Chunk Based Templates for Generating a subset of English Text
Authors Nikhilesh Bhatnagar, Manish Shrivastava, Radhika Mamidi
Abstract Natural Language Generation (NLG) is a research task which addresses the automatic generation of natural language text representative of an input non-linguistic collection of knowledge. In this paper, we address the task of the generation of grammatical sentences in an isolated context given a partial bag-of-words which the generated sentence must contain. We view the task as a search problem (a problem of choice) involving combinations of smaller chunk based templates extracted from a training corpus to construct a complete sentence. To achieve that, we propose a fitness function which we use in conjunction with an evolutionary algorithm as the search procedure to arrive at a potentially grammatical sentence (modeled by the fitness score) which satisfies the input constraints.
Tasks Text Generation
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-3017/
PDF https://www.aclweb.org/anthology/P18-3017
PWC https://paperswithcode.com/paper/exploring-chunk-based-templates-for
Repo
Framework

OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU

Title OpenNMT System Description for WNMT 2018: 800 words/sec on a single-core CPU
Authors Jean Senellart, Dakun Zhang, Bo Wang, Guillaume Klein, Ramatch, Jean-Pierre irin, Josep Crego, Alex Rush, er
Abstract We present a system description of the OpenNMT Neural Machine Translation entry for the WNMT 2018 evaluation. In this work, we developed a heavily optimized NMT inference model targeting a high-performance CPU system. The final system uses a combination of four techniques, all of them lead to significant speed-ups in combination: (a) sequence distillation, (b) architecture modifications, (c) precomputation, particularly of vocabulary, and (d) CPU targeted quantization. This work achieves the fastest performance of the shared task, and led to the development of new features that have been integrated to OpenNMT and available to the community.
Tasks Machine Translation, Neural Architecture Search, Quantization
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2715/
PDF https://www.aclweb.org/anthology/W18-2715
PWC https://paperswithcode.com/paper/opennmt-system-description-for-wnmt-2018-800
Repo
Framework

The LODeXporter: Flexible Generation of Linked Open Data Triples from NLP Frameworks for Automatic Knowledge Base Construction

Title The LODeXporter: Flexible Generation of Linked Open Data Triples from NLP Frameworks for Automatic Knowledge Base Construction
Authors Ren{'e} Witte, Bahar Sateli
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1385/
PDF https://www.aclweb.org/anthology/L18-1385
PWC https://paperswithcode.com/paper/the-lodexporter-flexible-generation-of-linked
Repo
Framework

Context Sensitive Neural Lemmatization with Lematus

Title Context Sensitive Neural Lemmatization with Lematus
Authors Toms Bergmanis, Sharon Goldwater
Abstract The main motivation for developing contextsensitive lemmatizers is to improve performance on unseen and ambiguous words. Yet previous systems have not carefully evaluated whether the use of context actually helps in these cases. We introduce Lematus, a lemmatizer based on a standard encoder-decoder architecture, which incorporates character-level sentence context. We evaluate its lemmatization accuracy across 20 languages in both a full data setting and a lower-resource setting with 10k training examples in each language. In both settings, we show that including context significantly improves results against a context-free version of the model. Context helps more for ambiguous words than for unseen words, though the latter has a greater effect on overall performance differences between languages. We also compare to three previous context-sensitive lemmatization systems, which all use pre-extracted edit trees as well as hand-selected features and/or additional sources of information such as tagged training data. Without using any of these, our context-sensitive model outperforms the best competitor system (Lemming) in the fulldata setting, and performs on par in the lowerresource setting.
Tasks Lemmatization, Machine Translation, Word Embeddings
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1126/
PDF https://www.aclweb.org/anthology/N18-1126
PWC https://paperswithcode.com/paper/context-sensitive-neural-lemmatization-with
Repo
Framework

Morphological Reinflection in Context: CU Boulder’s Submission to CoNLL–SIGMORPHON 2018 Shared Task

Title Morphological Reinflection in Context: CU Boulder’s Submission to CoNLL–SIGMORPHON 2018 Shared Task
Authors Ling Liu, Ilamvazhuthy Subbiah, Adam Wiemerslage, Jonathan Lilley, Sarah Moeller
Abstract
Tasks Machine Translation, Morphological Inflection
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-3010/
PDF https://www.aclweb.org/anthology/K18-3010
PWC https://paperswithcode.com/paper/morphological-reinflection-in-context-cu
Repo
Framework

Large-scale Cloze Test Dataset Designed by Teachers

Title Large-scale Cloze Test Dataset Designed by Teachers
Authors Qizhe Xie, Guokun Lai, Zihang Dai, Eduard Hovy
Abstract Cloze test is widely adopted in language exams to evaluate students’ language proficiency. In this paper, we propose the first large-scale human-designed cloze test dataset CLOTH in which the questions were used in middle-school and high-school language exams. With the missing blanks carefully created by teachers and candidate choices purposely designed to be confusing, CLOTH requires a deeper language understanding and a wider attention span than previous automatically generated cloze datasets. We show humans outperform dedicated designed baseline models by a significant margin, even when the model is trained on sufficiently large external data. We investigate the source of the performance gap, trace model deficiencies to some distinct properties of CLOTH, and identify the limited ability of comprehending a long-term context to be the key bottleneck. In addition, we find that human-designed data leads to a larger gap between the model’s performance and human performance when compared to automatically generated data.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=rJJzTyWCZ
PDF https://openreview.net/pdf?id=rJJzTyWCZ
PWC https://paperswithcode.com/paper/large-scale-cloze-test-dataset-designed-by
Repo
Framework

Conversational Decision-Making Model for Predicting the King’s Decision in the Annals of the Joseon Dynasty

Title Conversational Decision-Making Model for Predicting the King’s Decision in the Annals of the Joseon Dynasty
Authors JinYeong Bak, Alice Oh
Abstract Styles of leaders when they make decisions in groups vary, and the different styles affect the performance of the group. To understand the key words and speakers associated with decisions, we initially formalize the problem as one of predicting leaders{'} decisions from discussion with group members. As a dataset, we introduce conversational meeting records from a historical corpus, and develop a hierarchical RNN structure with attention and pre-trained speaker embedding in the form of a, Conversational Decision Making Model (CDMM). The CDMM outperforms other baselines to predict leaders{'} final decisions from the data. We explain why CDMM works better than other methods by showing the key words and speakers discovered from the attentions as evidence.
Tasks Decision Making
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1115/
PDF https://www.aclweb.org/anthology/D18-1115
PWC https://paperswithcode.com/paper/conversational-decision-making-model-for
Repo
Framework

Large Scale Optimal Transport and Mapping Estimation

Title Large Scale Optimal Transport and Mapping Estimation
Authors Vivien Seguy, Bharath Bhushan Damodaran, Remi Flamary, Nicolas Courty, Antoine Rolet, Mathieu Blondel
Abstract This paper presents a novel two-step approach for the fundamental problem of learning an optimal map from one distribution to another. First, we learn an optimal transport (OT) plan, which can be thought as a one-to-many map between the two distributions. To that end, we propose a stochastic dual approach of regularized OT, and show empirically that it scales better than a recent related approach when the amount of samples is very large. Second, we estimate a Monge map as a deep neural network learned by approximating the barycentric projection of the previously-obtained OT plan. This parameterization allows generalization of the mapping outside the support of the input measure. We prove two theoretical stability results of regularized OT which show that our estimations converge to the OT and Monge map between the underlying continuous measures. We showcase our proposed approach on two applications: domain adaptation and generative modeling.
Tasks Domain Adaptation
Published 2018-01-01
URL https://openreview.net/forum?id=B1zlp1bRW
PDF https://openreview.net/pdf?id=B1zlp1bRW
PWC https://paperswithcode.com/paper/large-scale-optimal-transport-and-mapping-1
Repo
Framework
comments powered by Disqus