Paper Group NANR 87
Talk The Walk: Navigating Grids in New York City through Grounded Dialogue. Serial Recall Effects in Neural Language Modeling. Learning Morphosyntactic Analyzers from the Bible via Iterative Annotation Projection across 26 Languages. Neural Machine Translation with Reordering Embeddings. Auditing Deep Learning processes through Kernel-based Explana …
Talk The Walk: Navigating Grids in New York City through Grounded Dialogue
| Title | Talk The Walk: Navigating Grids in New York City through Grounded Dialogue |
| Authors | Harm de Vries, Kurt Shuster, Dhruv Batra, Devi Parikh, Jason Weston, Douwe Kiela |
| Abstract | We introduce `"Talk The Walk”, the first large-scale dialogue dataset grounded in action and perception. The task involves two agents (a ‘guide’ and a ‘tourist’) that communicate via natural language in order to achieve a common goal: having the tourist navigate to a given target location. The task and dataset, which are described in detail, are challenging and their full solution is an open problem that we pose to the community. We (i) focus on the task of tourist localization and develop the novel Masked Attention for Spatial Convolutions (MASC) mechanism that allows for grounding tourist utterances into the guide’s map, (ii) show it yields significant improvements for both emergent and natural language communication, and (iii) using this method, we establish non-trivial baselines on the full task. | |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HyxhusA9Fm |
| https://openreview.net/pdf?id=HyxhusA9Fm | |
| PWC | https://paperswithcode.com/paper/talk-the-walk-navigating-grids-in-new-york |
| Repo | |
| Framework | |
Serial Recall Effects in Neural Language Modeling
| Title | Serial Recall Effects in Neural Language Modeling |
| Authors | Hassan Hajipoor, Hadi Amiri, Maseud Rahgozar, Farhad Oroumchian |
| Abstract | Serial recall experiments study the ability of humans to recall words in the order in which they occurred. The following serial recall effects are generally investigated in studies with humans: word length and frequency, primacy and recency, semantic confusion, repetition, and transposition effects. In this research, we investigate neural language models in the context of these serial recall effects. Our work provides a framework to better understand and analyze neural language models and opens a new window to develop accurate language models. |
| Tasks | Language Modelling |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1073/ |
| https://www.aclweb.org/anthology/N19-1073 | |
| PWC | https://paperswithcode.com/paper/serial-recall-effects-in-neural-language |
| Repo | |
| Framework | |
Learning Morphosyntactic Analyzers from the Bible via Iterative Annotation Projection across 26 Languages
| Title | Learning Morphosyntactic Analyzers from the Bible via Iterative Annotation Projection across 26 Languages |
| Authors | Garrett Nicolai, David Yarowsky |
| Abstract | A large percentage of computational tools are concentrated in a very small subset of the planet{'}s languages. Compounding the issue, many languages lack the high-quality linguistic annotation necessary for the construction of such tools with current machine learning methods. In this paper, we address both issues simultaneously: leveraging the high accuracy of English taggers and parsers, we project morphological information onto translations of the Bible in 26 varied test languages. Using an iterative discovery, constraint, and training process, we build inflectional lexica in the target languages. Through a combination of iteration, ensembling, and reranking, we see double-digit relative error reductions in lemmatization and morphological analysis over a strong initial system. |
| Tasks | Lemmatization, Morphological Analysis |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1172/ |
| https://www.aclweb.org/anthology/P19-1172 | |
| PWC | https://paperswithcode.com/paper/learning-morphosyntactic-analyzers-from-the |
| Repo | |
| Framework | |
Neural Machine Translation with Reordering Embeddings
| Title | Neural Machine Translation with Reordering Embeddings |
| Authors | Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita |
| Abstract | The reordering model plays an important role in phrase-based statistical machine translation. However, there are few works that exploit the reordering information in neural machine translation. In this paper, we propose a reordering mechanism to learn the reordering embedding of a word based on its contextual information. These learned reordering embeddings are stacked together with self-attention networks to learn sentence representation for machine translation. The reordering mechanism can be easily integrated into both the encoder and the decoder in the Transformer translation system. Experimental results on WMT{'}14 English-to-German, NIST Chinese-to-English, and WAT Japanese-to-English translation tasks demonstrate that the proposed methods can significantly improve the performance of the Transformer. |
| Tasks | Machine Translation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1174/ |
| https://www.aclweb.org/anthology/P19-1174 | |
| PWC | https://paperswithcode.com/paper/neural-machine-translation-with-reordering |
| Repo | |
| Framework | |
Auditing Deep Learning processes through Kernel-based Explanatory Models
| Title | Auditing Deep Learning processes through Kernel-based Explanatory Models |
| Authors | Danilo Croce, Daniele Rossini, Roberto Basili |
| Abstract | While NLP systems become more pervasive, their accountability gains value as a focal point of effort. Epistemological opaqueness of nonlinear learning methods, such as deep learning models, can be a major drawback for their adoptions. In this paper, we discuss the application of Layerwise Relevance Propagation over a linguistically motivated neural architecture, the Kernel-based Deep Architecture, in order to trace back connections between linguistic properties of input instances and system decisions. Such connections then guide the construction of argumentations on network{'}s inferences, i.e., explanations based on real examples, semantically related to the input. We propose here a methodology to evaluate the transparency and coherence of analogy-based explanations modeling an audit stage for the system. Quantitative analysis on two semantic tasks, i.e., question classification and semantic role labeling, show that the explanatory capabilities (native in KDAs) are effective and they pave the way to more complex argumentation methods. |
| Tasks | Semantic Role Labeling |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1415/ |
| https://www.aclweb.org/anthology/D19-1415 | |
| PWC | https://paperswithcode.com/paper/auditing-deep-learning-processes-through |
| Repo | |
| Framework | |
Study on Unsupervised Statistical Machine Translation for Backtranslation
| Title | Study on Unsupervised Statistical Machine Translation for Backtranslation |
| Authors | Anush Kumar, Nihal V. Nayak, Ch, Aditya ra, Mydhili K. Nair |
| Abstract | Machine Translation systems have drastically improved over the years for several language pairs. Monolingual data is often used to generate synthetic sentences to augment the training data which has shown to improve the performance of machine translation models. In our paper, we make use of an Unsupervised Statistical Machine Translation (USMT) to generate synthetic sentences. Our study compares the performance improvements in Neural Machine Translation model when using synthetic sentences from supervised and unsupervised Machine Translation models. Our approach of using USMT for backtranslation shows promise in low resource conditions and achieves an improvement of 3.2 BLEU score over the Neural Machine Translation model. |
| Tasks | Machine Translation, Unsupervised Machine Translation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1068/ |
| https://www.aclweb.org/anthology/R19-1068 | |
| PWC | https://paperswithcode.com/paper/study-on-unsupervised-statistical-machine |
| Repo | |
| Framework | |
Generating Diverse Translations with Sentence Codes
| Title | Generating Diverse Translations with Sentence Codes |
| Authors | Raphael Shu, Hideki Nakayama, Kyunghyun Cho |
| Abstract | Users of machine translation systems may desire to obtain multiple candidates translated in different ways. In this work, we attempt to obtain diverse translations by using sentence codes to condition the sentence generation. We describe two methods to extract the codes, either with or without the help of syntax information. For diverse generation, we sample multiple candidates, each of which conditioned on a unique code. Experiments show that the sampled translations have much higher diversity scores when using reasonable sentence codes, where the translation quality is still on par with the baselines even under strong constraint imposed by the codes. In qualitative analysis, we show that our method is able to generate paraphrase translations with drastically different structures. The proposed approach can be easily adopted to existing translation systems as no modification to the model is required. |
| Tasks | Machine Translation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1177/ |
| https://www.aclweb.org/anthology/P19-1177 | |
| PWC | https://paperswithcode.com/paper/generating-diverse-translations-with-sentence |
| Repo | |
| Framework | |
Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks
| Title | Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks |
| Authors | Ziyi Liu, Le Wang, Qilin Zhang, Zhanning Gao, Zhenxing Niu, Nanning Zheng, Gang Hua |
| Abstract | Weakly-supervised temporal action localization (WS-TAL) is a promising but challenging task with only video-level action categorical labels available during training. Without requiring temporal action boundary annotations in training data, WS-TAL could possibly exploit automatically retrieved video tags as video-level labels. However, such coarse video-level supervision inevitably incurs confusions, especially in untrimmed videos containing multiple action instances. To address this challenge, we propose the Contrast-based Localization EvaluAtioN Network (CleanNet) with our new action proposal evaluator, which provides pseudo-supervision by leveraging the temporal contrast in snippet-level action classification predictions. Essentially, the new action proposal evaluator enforces an additional temporal contrast constraint so that high-evaluation-score action proposals are more likely to coincide with true action instances. Moreover, the new action localization module is an integral part of CleanNet which enables end-to-end training. This is in contrast to many existing WS-TAL methods where action localization is merely a post-processing step. Experiments on THUMOS14 and ActivityNet datasets validate the efficacy of CleanNet against existing state-ofthe- art WS-TAL algorithms. |
| Tasks | Action Classification, Action Localization, Temporal Action Localization, Weakly Supervised Action Localization, Weakly-supervised Temporal Action Localization |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Weakly_Supervised_Temporal_Action_Localization_Through_Contrast_Based_Evaluation_Networks_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Weakly_Supervised_Temporal_Action_Localization_Through_Contrast_Based_Evaluation_Networks_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-temporal-action |
| Repo | |
| Framework | |
Dynamic PET Image Reconstruction Using Nonnegative Matrix Factorization Incorporated With Deep Image Prior
| Title | Dynamic PET Image Reconstruction Using Nonnegative Matrix Factorization Incorporated With Deep Image Prior |
| Authors | Tatsuya Yokota, Kazuya Kawai, Muneyuki Sakata, Yuichi Kimura, Hidekata Hontani |
| Abstract | We propose a method that reconstructs dynamic positron emission tomography (PET) images from given sinograms by using non-negative matrix factorization (NMF) incorporated with a deep image prior (DIP) for appropriately constraining the spatial patterns of resultant images. The proposed method can reconstruct dynamic PET images with higher signal-to-noise ratio (SNR) and blindly decompose an image matrix into pairs of spatial and temporal factors. The former represent homogeneous tissues with different kinetic parameters and the latter represent the time activity curves that are observed in the corresponding homogeneous tissues. We employ U-Nets combined in parallel for DIP and each of the U-nets is used to extract each spatial factor decomposed from the data matrix. Experimental results show that the proposed method outperforms conventional methods and can extract spatial factors that represent the homogeneous tissues. |
| Tasks | Image Reconstruction |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Yokota_Dynamic_PET_Image_Reconstruction_Using_Nonnegative_Matrix_Factorization_Incorporated_With_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Yokota_Dynamic_PET_Image_Reconstruction_Using_Nonnegative_Matrix_Factorization_Incorporated_With_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-pet-image-reconstruction-using |
| Repo | |
| Framework | |
CIIDefence: Defeating Adversarial Attacks by Fusing Class-Specific Image Inpainting and Image Denoising
| Title | CIIDefence: Defeating Adversarial Attacks by Fusing Class-Specific Image Inpainting and Image Denoising |
| Authors | Puneet Gupta, Esa Rahtu |
| Abstract | This paper presents a novel approach for protecting deep neural networks from adversarial attacks, i.e., methods that add well-crafted imperceptible modifications to the original inputs such that they are incorrectly classified with high confidence. The proposed defence mechanism is inspired by the recent works mitigating the adversarial disturbances by the means of image reconstruction and denoising. However, unlike the previous works, we apply the reconstruction only for small and carefully selected image areas that are most influential to the current classification outcome. The selection process is guided by the class activation map responses obtained for multiple top-ranking class labels. The same regions are also the most prominent for the adversarial perturbations and hence most important to purify. The resulting inpainting task is substantially more tractable than the full image reconstruction, while still being able to prevent the adversarial attacks. Furthermore, we combine the selective image inpainting with wavelet based image denoising to produce a non differentiable layer that prevents attacker from using gradient backpropagation. Moreover, the proposed nonlinearity cannot be easily approximated with simple differentiable alternative as demonstrated in the experiments with Backward Pass Differentiable Approximation (BPDA) attack. Finally, we experimentally show that the proposed Class-specific Image Inpainting Defence (CIIDefence) is able to withstand several powerful adversarial attacks including the BPDA. The obtained results are consistently better compared to the other recent defence approaches. |
| Tasks | Denoising, Image Denoising, Image Inpainting, Image Reconstruction |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Gupta_CIIDefence_Defeating_Adversarial_Attacks_by_Fusing_Class-Specific_Image_Inpainting_and_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Gupta_CIIDefence_Defeating_Adversarial_Attacks_by_Fusing_Class-Specific_Image_Inpainting_and_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/ciidefence-defeating-adversarial-attacks-by |
| Repo | |
| Framework | |
Hyperspectral Image Reconstruction Using Deep External and Internal Learning
| Title | Hyperspectral Image Reconstruction Using Deep External and Internal Learning |
| Authors | Tao Zhang, Ying Fu, Lizhi Wang, Hua Huang |
| Abstract | To solve the low spatial and/or temporal resolution problem which the conventional hypelrspectral cameras often suffer from, coded snapshot hyperspectral imaging systems have attracted more attention recently. Recovering a hyperspectral image (HSI) from its corresponding coded image is an ill-posed inverse problem, and learning accurate prior of HSI is essential to solve this inverse problem. In this paper, we present an effective convolutional neural network (CNN) based method for coded HSI reconstruction, which learns the deep prior from the external dataset as well as the internal information of input coded image with spatial-spectral constraint. Our method can effectively exploit spatial-spectral correlation and sufficiently represent the variety nature of HSIs. Experimental results show our method outperforms the state-of-the-art methods under both comprehensive quantitative metrics and perceptive quality. |
| Tasks | Image Reconstruction |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhang_Hyperspectral_Image_Reconstruction_Using_Deep_External_and_Internal_Learning_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Hyperspectral_Image_Reconstruction_Using_Deep_External_and_Internal_Learning_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-image-reconstruction-using-deep |
| Repo | |
| Framework | |
Computational Hyperspectral Imaging Based on Dimension-Discriminative Low-Rank Tensor Recovery
| Title | Computational Hyperspectral Imaging Based on Dimension-Discriminative Low-Rank Tensor Recovery |
| Authors | Shipeng Zhang, Lizhi Wang, Ying Fu, Xiaoming Zhong, Hua Huang |
| Abstract | Exploiting the prior information is fundamental for the image reconstruction in computational hyperspectral imaging. Existing methods usually unfold the 3D signal as a 1D vector and treat the prior information within different dimensions in an indiscriminative manner, which ignores the high-dimensionality nature of hyperspectral image (HSI) and thus results in poor quality reconstruction. In this paper, we propose to make full use of the high-dimensionality structure of the desired HSI to boost the reconstruction quality. We first build a high-order tensor by exploiting the nonlocal similarity in HSI. Then, we propose a dimension-discriminative low-rank tensor recovery (DLTR) model to characterize the structure prior adaptively in each dimension. By integrating the structure prior in DLTR with the system imaging process, we develop an optimization framework for HSI reconstruction, which is finally solved via the alternating minimization algorithm. Extensive experiments implemented with both synthetic and real data demonstrate that our method outperforms state-of-the-art methods. |
| Tasks | Image Reconstruction |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhang_Computational_Hyperspectral_Imaging_Based_on_Dimension-Discriminative_Low-Rank_Tensor_Recovery_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Computational_Hyperspectral_Imaging_Based_on_Dimension-Discriminative_Low-Rank_Tensor_Recovery_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/computational-hyperspectral-imaging-based-on |
| Repo | |
| Framework | |
Downsampling leads to Image Memorization in Convolutional Autoencoders
| Title | Downsampling leads to Image Memorization in Convolutional Autoencoders |
| Authors | Adityanarayanan Radhakrishnan, Caroline Uhler, Mikhail Belkin |
| Abstract | Memorization of data in deep neural networks has become a subject of significant research interest. In this paper, we link memorization of images in deep convolutional autoencoders to downsampling through strided convolution. To analyze this mechanism in a simpler setting, we train linear convolutional autoencoders and show that linear combinations of training data are stored as eigenvectors in the linear operator corresponding to the network when downsampling is used. On the other hand, networks without downsampling do not memorize training data. We provide further evidence that the same effect happens in nonlinear networks. Moreover, downsampling in nonlinear networks causes the model to not only memorize just linear combinations of images, but individual training images. Since convolutional autoencoder components are building blocks of deep convolutional networks, we envision that our findings will shed light on the important phenomenon of memorization in over-parameterized deep networks. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ByGUFsAqYm |
| https://openreview.net/pdf?id=ByGUFsAqYm | |
| PWC | https://paperswithcode.com/paper/downsampling-leads-to-image-memorization-in |
| Repo | |
| Framework | |
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
| Title | Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1000/ |
| https://www.aclweb.org/anthology/P19-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-57th-conference-of-the |
| Repo | |
| Framework | |
Writing Styles of Salwa and Al-Qarni
| Title | Writing Styles of Salwa and Al-Qarni |
| Authors | Ahmed Omer, Michael Oakes |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5603/ |
| https://www.aclweb.org/anthology/W19-5603 | |
| PWC | https://paperswithcode.com/paper/writing-styles-of-salwa-and-al-qarni |
| Repo | |
| Framework | |
