Paper Group NAWR 3
Detecting Argumentative Discourse Acts with Linguistic Alignment. Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation. Graph Agreement Models for Semi-Supervised Learning. DANet: Divergent Activation for Weakly Supervised Object Localization. Human Motion Prediction via Spatio-Temporal Inpainting. Push-pull …
Detecting Argumentative Discourse Acts with Linguistic Alignment
| Title | Detecting Argumentative Discourse Acts with Linguistic Alignment |
| Authors | Timothy Niven, Hung-Yu Kao |
| Abstract | We report the results of preliminary investigations into the relationship between linguistic alignment and dialogical argumentation at the level of discourse acts. We annotated a proof of concept dataset with illocutions and transitions at the comment level based on Inference Anchoring Theory. We estimated linguistic alignment across discourse acts and found significant variation. Alignment features calculated at the dyad level are found to be useful for detecting a range of argumentative discourse acts. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4513/ |
| https://www.aclweb.org/anthology/W19-4513 | |
| PWC | https://paperswithcode.com/paper/detecting-argumentative-discourse-acts-with |
| Repo | https://github.com/IKMLab/argalign1 |
| Framework | none |
Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation
| Title | Submodular Optimization-based Diverse Paraphrasing and its Effectiveness in Data Augmentation |
| Authors | Ashutosh Kumar, Satwik Bhattamishra, Bh, Manik ari, Partha Talukdar |
| Abstract | Inducing diversity in the task of paraphrasing is an important problem in NLP with applications in data augmentation and conversational agents. Previous paraphrasing approaches have mainly focused on the issue of generating semantically similar paraphrases while paying little attention towards diversity. In fact, most of the methods rely solely on top-k beam search sequences to obtain a set of paraphrases. The resulting set, however, contains many structurally similar sentences. In this work, we focus on the task of obtaining highly diverse paraphrases while not compromising on paraphrasing quality. We provide a novel formulation of the problem in terms of monotone submodular function maximization, specifically targeted towards the task of paraphrasing. Additionally, we demonstrate the effectiveness of our method for data augmentation on multiple tasks such as intent classification and paraphrase recognition. In order to drive further research, we have made the source code available. |
| Tasks | Data Augmentation, Intent Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1363/ |
| https://www.aclweb.org/anthology/N19-1363 | |
| PWC | https://paperswithcode.com/paper/submodular-optimization-based-diverse |
| Repo | https://github.com/malllabiisc/DiPS |
| Framework | pytorch |
Graph Agreement Models for Semi-Supervised Learning
| Title | Graph Agreement Models for Semi-Supervised Learning |
| Authors | Otilia Stretcu, Krishnamurthy Viswanathan, Dana Movshovitz-Attias, Emmanouil Platanios, Sujith Ravi, Andrew Tomkins |
| Abstract | Graph-based algorithms are among the most successful paradigms for solving semi-supervised learning tasks. Recent work on graph convolutional networks and neural graph learning methods has successfully combined the expressiveness of neural networks with graph structures. We propose a technique that, when applied to these methods, achieves state-of-the-art results on semi-supervised learning datasets. Traditional graph-based algorithms, such as label propagation, were designed with the underlying assumption that the label of a node can be imputed from that of the neighboring nodes. However, real-world graphs are either noisy or have edges that do not correspond to label agreement. To address this, we propose Graph Agreement Models (GAM), which introduces an auxiliary model that predicts the probability of two nodes sharing the same label as a learned function of their features. The agreement model is used when training a node classification model by encouraging agreement only for the pairs of nodes it deems likely to have the same label, thus guiding its parameters to better local optima. The classification and agreement models are trained jointly in a co-training fashion. Moreover, GAM can also be applied to any semi-supervised classification problem, by inducing a graph whenever one is not provided. We demonstrate that our method achieves a relative improvement of up to 72% for various node classification models, and obtains state-of-the-art results on multiple established datasets. |
| Tasks | Node Classification |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9076-graph-agreement-models-for-semi-supervised-learning |
| http://papers.nips.cc/paper/9076-graph-agreement-models-for-semi-supervised-learning.pdf | |
| PWC | https://paperswithcode.com/paper/graph-agreement-models-for-semi-supervised |
| Repo | https://github.com/tensorflow/neural-structured-learning |
| Framework | tf |
DANet: Divergent Activation for Weakly Supervised Object Localization
| Title | DANet: Divergent Activation for Weakly Supervised Object Localization |
| Authors | Haolan Xue, Chang Liu, Fang Wan, Jianbin Jiao, Xiangyang Ji, Qixiang Ye |
| Abstract | Weakly supervised object localization remains a challenge when learning object localization models from image category labels. Optimizing image classification tends to activate object parts and ignore the full object extent, while expanding object parts into full object extent could deteriorate the performance of image classification. In this paper, we propose a divergent activation (DA) approach, and target at learning complementary and discriminative visual patterns for image classification and weakly supervised object localization from the perspective of discrepancy. To this end, we design hierarchical divergent activation (HDA), which leverages the semantic discrepancy to spread feature activation, implicitly. We also propose discrepant divergent activation (DDA), which pursues object extent by learning mutually exclusive visual patterns, explicitly. Deep networks implemented with HDA and DDA, referred to as DANets, diverge and fuse discrepant yet discriminative features for image classification and object localization in an end-to-end manner. Experiments validate that DANets advance the performance of object localization while maintaining high performance of image classification on CUB-200 and ILSVRC datasets |
| Tasks | Image Classification, Object Localization, Weakly-Supervised Object Localization |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Xue_DANet_Divergent_Activation_for_Weakly_Supervised_Object_Localization_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Xue_DANet_Divergent_Activation_for_Weakly_Supervised_Object_Localization_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/danet-divergent-activation-for-weakly |
| Repo | https://github.com/xuehaolan/DANet |
| Framework | pytorch |
Human Motion Prediction via Spatio-Temporal Inpainting
| Title | Human Motion Prediction via Spatio-Temporal Inpainting |
| Authors | Alejandro Hernandez, Jurgen Gall, Francesc Moreno-Noguer |
| Abstract | We propose a Generative Adversarial Network (GAN) to forecast 3D human motion given a sequence of past 3D skeleton poses. While recent GANs have shown promising results, they can only forecast plausible motion over relatively short periods of time (few hundred milliseconds) and typically ignore the absolute position of the skeleton w.r.t. the camera. Our scheme provides long term predictions (two seconds or more) for both the body pose and its absolute position. Our approach builds upon three main contributions. First, we represent the data using a spatio-temporal tensor of 3D skeleton coordinates which allows formulating the prediction problem as an inpainting one, for which GANs work particularly well. Secondly, we design an architecture to learn the joint distribution of body poses and global motion, capable to hypothesize large chunks of the input 3D tensor with missing data. And finally, we argue that the L2 metric, considered so far by most approaches, fails to capture the actual distribution of long-term human motion. We propose two alternative metrics, based on the distribution of frequencies, that are able to capture more realistic motion patterns. Extensive experiments demonstrate our approach to significantly improve the state of the art, while also handling situations in which past observations are corrupted by occlusions, noise and missing frames. |
| Tasks | motion prediction |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Hernandez_Human_Motion_Prediction_via_Spatio-Temporal_Inpainting_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Hernandez_Human_Motion_Prediction_via_Spatio-Temporal_Inpainting_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/human-motion-prediction-via-spatio-temporal-1 |
| Repo | https://github.com/magnux/MotionGAN |
| Framework | tf |
Push-pull Feedback Implements Hierarchical Information Retrieval Efficiently
| Title | Push-pull Feedback Implements Hierarchical Information Retrieval Efficiently |
| Authors | Xiao Liu, Xiaolong Zou, Zilong Ji, Gengshuo Tian, Yuanyuan Mi, Tiejun Huang, K. Y. Michael Wong, Si Wu |
| Abstract | Experimental data has revealed that in addition to feedforward connections, there exist abundant feedback connections in a neural pathway. Although the importance of feedback in neural information processing has been widely recognized in the field, the detailed mechanism of how it works remains largely unknown. Here, we investigate the role of feedback in hierarchical information retrieval. Specifically, we consider a hierarchical network storing the hierarchical categorical information of objects, and information retrieval goes from rough to fine, aided by dynamical push-pull feedback from higher to lower layers. We elucidate that the push (positive) and pull (negative) feedbacks suppress the interferences due to neural correlations between different and the same categories, respectively, and their joint effect improves retrieval performance significantly. Our model agrees with the push-pull phenomenon observed in neural data and sheds light on our understanding of the role of feedback in neural information processing. |
| Tasks | Information Retrieval |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8807-push-pull-feedback-implements-hierarchical-information-retrieval-efficiently |
| http://papers.nips.cc/paper/8807-push-pull-feedback-implements-hierarchical-information-retrieval-efficiently.pdf | |
| PWC | https://paperswithcode.com/paper/push-pull-feedback-implements-hierarchical |
| Repo | https://github.com/XiaoLiu-git/Push-Pull-feedback-for-NIPS2019 |
| Framework | none |
Deepsleep: Fast and Accurate Delineation of Sleep Arousals at Millisecond Resolution by Deep Learning
| Title | Deepsleep: Fast and Accurate Delineation of Sleep Arousals at Millisecond Resolution by Deep Learning |
| Authors | Hongyang Li, Yuanfang Guan |
| Abstract | Background: Sleep arousals are transient periods of wakefulness punctuated into sleep. Excessive sleep arousals are associated with many negative effects including daytime sleepiness and sleep disorders. High-quality annotation of polysomnographic recordings is crucial for the diagnosis of sleep arousal disorders. Currently, sleep arousals are mainly annotated by human experts through looking at millions of data points manually, which requires considerable time and effort. Methods: We used the polysomnograms of 2,994 individuals from two independent datasets (i) PhysioNet Challenge dataset (n=994), and (ii) Sleep Heart Health Study dataset (n=2000) for model training (60%), validation (15%), and testing (25%). We developed a deep convolutional neural network approach, DeepSleep, to automatically segment sleep arousal events. Our method captured the long-range and short-range interactions among physiological signals at multiple time scales to empower the detection of sleep arousals. A novel augmentation strategy by randomly swapping similar physiological channels was further applied to improve the prediction accuracy. Findings: Compared with other computational methods in sleep study, DeepSleep features accurate (area under receiver operating characteristic curve of 0.93 and area under the precision recall curve of 0.55), high-resolution (5-millisecond resolution), and fast (10 seconds per sleep record) delineation of sleep arousals. This method ranked first in segmenting non-apenic arousals when evaluated on a large held-out dataset (n=989) in the 2018 PhysioNet Challenge. We found that DeepSleep provided more detailed delineations than humans, especially at the low-confident boundary regions between arousal and non-arousal events. This indicates that in silico annotations is a complement to human annotations and potentially advances the current binary label system and scoring criteria for sleep arousals. Interpretation: The proposed deep learning model achieved state-of-the-art performance in detection of sleep arousals. By introducing the probability of annotation confidence, this model would provide more accurate information for the diagnosis of sleep disorders and the evaluation of sleep quality. |
| Tasks | Sleep Arousal Detection, Sleep Micro-event detection, Sleep Quality |
| Published | 2019-09-07 |
| URL | https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3445559 |
| https://papers.ssrn.com/sol3/Delivery.cfm/TLDIGITALHEALTH-S-19-00424.pdf?abstractid=3445559&mirid=1 | |
| PWC | https://paperswithcode.com/paper/deepsleep-fast-and-accurate-delineation-of |
| Repo | https://github.com/GuanLab/DeepSleep |
| Framework | tf |
Equitable Stable Matchings in Quadratic Time
| Title | Equitable Stable Matchings in Quadratic Time |
| Authors | Nikolaos Tziavelis, Ioannis Giannakopoulos, Katerina Doka, Nectarios Koziris, Panagiotis Karras |
| Abstract | Can a stable matching that achieves high equity among the two sides of a market be reached in quadratic time? The Deferred Acceptance (DA) algorithm finds a stable matching that is biased in favor of one side; optimizing apt equity measures is strongly NP-hard. A proposed approximation algorithm offers a guarantee only with respect to the DA solutions. Recent work introduced Deferred Acceptance with Compensation Chains (DACC), a class of algorithms that can reach any stable matching in O(n^4) time, but did not propose a way to achieve good equity. In this paper, we propose an alternative that is computationally simpler and achieves high equity too. We introduce Monotonic Deferred Acceptance (MDA), a class of algorithms that progresses monotonically towards a stable matching; we couple MDA with a mechanism we call Strongly Deferred Acceptance (SDA), to build an algorithm that reaches an equitable stable matching in quadratic time; we amend this algorithm with a few low-cost local search steps to what we call Deferred Local Search (DLS), and demonstrate experimentally that it outperforms previous solutions in terms of equity measures and matches the most efficient ones in runtime. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8337-equitable-stable-matchings-in-quadratic-time |
| http://papers.nips.cc/paper/8337-equitable-stable-matchings-in-quadratic-time.pdf | |
| PWC | https://paperswithcode.com/paper/equitable-stable-matchings-in-quadratic-time |
| Repo | https://github.com/ntzia/stable-marriage |
| Framework | none |
Underexposed Photo Enhancement Using Deep Illumination Estimation
| Title | Underexposed Photo Enhancement Using Deep Illumination Estimation |
| Authors | Ruixing Wang, Qing Zhang, Chi-Wing Fu, Xiaoyong Shen, Wei-Shi Zheng, Jiaya Jia |
| Abstract | This paper presents a new neural network for enhancing underexposed photos. Instead of directly learning an image-to-image mapping as previous work, we introduce intermediate illumination in our network to associate the input with expected enhancement result, which augments the network’s capability to learn complex photographic adjustment from expert-retouched input/output image pairs. Based on this model, we formulate a loss function that adopts constraints and priors on the illumination, prepare a new dataset of 3,000 underexposed image pairs, and train the network to effectively learn a rich variety of adjustment for diverse lighting conditions. By these means, our network is able to recover clear details, distinct contrast, and natural color in the enhancement results. We perform extensive experiments on the benchmark MIT-Adobe FiveK dataset and our new dataset, and show that our network is effective to deal with previously challenging images. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Underexposed_Photo_Enhancement_Using_Deep_Illumination_Estimation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Underexposed_Photo_Enhancement_Using_Deep_Illumination_Estimation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/underexposed-photo-enhancement-using-deep |
| Repo | https://github.com/wangruixing/DeepUPE |
| Framework | tf |
HMEAE: Hierarchical Modular Event Argument Extraction
| Title | HMEAE: Hierarchical Modular Event Argument Extraction |
| Authors | Xiaozhi Wang, Ziqi Wang, Xu Han, Zhiyuan Liu, Juanzi Li, Peng Li, Maosong Sun, Jie Zhou, Xiang Ren |
| Abstract | Existing event extraction methods classify each argument role independently, ignoring the conceptual correlations between different argument roles. In this paper, we propose a Hierarchical Modular Event Argument Extraction (HMEAE) model, to provide effective inductive bias from the concept hierarchy of event argument roles. Specifically, we design a neural module network for each basic unit of the concept hierarchy, and then hierarchically compose relevant unit modules with logical operations into a role-oriented modular network to classify a specific argument role. As many argument roles share the same high-level unit module, their correlation can be utilized to extract specific event arguments better. Experiments on real-world datasets show that HMEAE can effectively leverage useful knowledge from the concept hierarchy and significantly outperform the state-of-the-art baselines. The source code can be obtained from https://github.com/thunlp/HMEAE. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1584/ |
| https://www.aclweb.org/anthology/D19-1584 | |
| PWC | https://paperswithcode.com/paper/hmeae-hierarchical-modular-event-argument |
| Repo | https://github.com/thunlp/HMEAE |
| Framework | tf |
Skeleton-Based Action Recognition With Directed Graph Neural Networks
| Title | Skeleton-Based Action Recognition With Directed Graph Neural Networks |
| Authors | Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu |
| Abstract | The skeleton data have been widely used for the action recognition tasks since they can robustly accommodate dynamic circumstances and complex backgrounds. In existing methods, both the joint and bone information in skeleton data have been proved to be of great help for action recognition tasks. However, how to incorporate these two types of data to best take advantage of the relationship between joints and bones remains a problem to be solved. In this work, we represent the skeleton data as a directed acyclic graph based on the kinematic dependency between the joints and bones in the natural human body. A novel directed graph neural network is designed specially to extract the information of joints, bones and their relations and make prediction based on the extracted features. In addition, to better fit the action recognition task, the topological structure of the graph is made adaptive based on the training process, which brings notable improvement. Moreover, the motion information of the skeleton sequence is exploited and combined with the spatial information to further enhance the performance in a two-stream framework. Our final model is tested on two large-scale datasets, NTU-RGBD and Skeleton-Kinetics, and exceeds state-of-the-art performance on both of them. |
| Tasks | Skeleton Based Action Recognition, Temporal Action Localization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Shi_Skeleton-Based_Action_Recognition_With_Directed_Graph_Neural_Networks_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Shi_Skeleton-Based_Action_Recognition_With_Directed_Graph_Neural_Networks_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/skeleton-based-action-recognition-with-4 |
| Repo | https://github.com/kenziyuliu/DGNN-PyTorch |
| Framework | pytorch |
A Discourse Signal Annotation System for RST Trees
| Title | A Discourse Signal Annotation System for RST Trees |
| Authors | Luke Gessler, Yang Liu, Amir Zeldes |
| Abstract | This paper presents a new system for open-ended discourse relation signal annotation in the framework of Rhetorical Structure Theory (RST), implemented on top of an online tool for RST annotation. We discuss existing projects annotating textual signals of discourse relations, which have so far not allowed simultaneously structuring and annotating words signaling hierarchical discourse trees, and demonstrate the design and applications of our interface by extending existing RST annotations in the freely available GUM corpus. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2708/ |
| https://www.aclweb.org/anthology/W19-2708 | |
| PWC | https://paperswithcode.com/paper/a-discourse-signal-annotation-system-for-rst |
| Repo | https://github.com/amir-zeldes/rstweb |
| Framework | none |
Non-Local Graph Convolutional Networks for Skeleton-Based Action Recognition
| Title | Non-Local Graph Convolutional Networks for Skeleton-Based Action Recognition |
| Authors | Lei Shi, Yifan Zhang, Jian Cheng, Hanqing Lu |
| Abstract | Traditional deep methods for skeleton-based action recognition usually structure the skeleton as a coordinates sequence or a pseudo-image to feed to RNNs or CNNs, which cannot explicitly exploit the natural connectivity among the joints. Recently, graph convolutional networks (GCNs), which generalize CNNs to more generic non-Euclidean structures, obtains remarkable performance for skeleton-based action recognition. However, the topology of the graph is set by hand and fixed over all layers, which may be not optimal for the action recognition task and the hierarchical CNN structures. Besides, the first-order information (the coordinate of joints) is mainly used in former GCNs, while the second-order information (the length and direction of bones) is less exploited. In this work, a novel two-stream nonlocal graph convolutional network is proposed to solve these problems. The topology of the graph in each layer of the model can be either uniformly or individually learned by BP algorithm, which brings more flexibility and generality. Meanwhile, a two-stream framework is proposed to model both of the joints and bones information simultaneously, which further boost the recognition performance. Extensive experiments on two large-scale datasets, NTU-RGB+D and Kinetics, demonstrate the performance of our model exceeds the state-of-the-art by a significant margin. |
| Tasks | Skeleton Based Action Recognition |
| Published | 2019-07-04 |
| URL | https://arxiv.org/abs/1805.07694v2 |
| https://arxiv.org/pdf/1805.07694v2.pdf | |
| PWC | https://paperswithcode.com/paper/non-local-graph-convolutional-networks-for-1 |
| Repo | https://github.com/lshiwjx/2s-AGCN |
| Framework | pytorch |
Twin Auxilary Classifiers GAN
| Title | Twin Auxilary Classifiers GAN |
| Authors | Mingming Gong, Yanwu Xu, Chunyuan Li, Kun Zhang, Kayhan Batmanghelich |
| Abstract | Conditional generative models enjoy significant progress over the past few years. One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN) that generates highly discriminative images by extending the loss function of GAN with an auxiliary classifier. However, the diversity of the generated samples by AC-GAN tends to decrease as the number of classes increases. In this paper, we identify the source of low diversity issue theoretically and propose a practical solution to the problem. We show that the auxiliary classifier in AC-GAN imposes perfect separability, which is disadvantageous when the supports of the class distributions have significant overlap. To address the issue, we propose Twin Auxiliary Classifiers Generative Adversarial Net (TAC-GAN) that adds a new player that interacts with other players (the generator and the discriminator) in GAN. Theoretically, we demonstrate that our TAC-GAN can effectively minimize the divergence between generated and real data distributions. Extensive experimental results show that our TAC-GAN can successfully replicate the true data distributions on simulated data, and significantly improves the diversity of class-conditional image generation on real datasets. |
| Tasks | Conditional Image Generation, Image Generation |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8414-twin-auxilary-classifiers-gan |
| http://papers.nips.cc/paper/8414-twin-auxilary-classifiers-gan.pdf | |
| PWC | https://paperswithcode.com/paper/twin-auxilary-classifiers-gan |
| Repo | https://github.com/batmanlab/twin_ac |
| Framework | pytorch |
Incorporating Label Dependencies in Multilabel Stance Detection
| Title | Incorporating Label Dependencies in Multilabel Stance Detection |
| Authors | William Ferreira, Andreas Vlachos |
| Abstract | Stance detection in social media is a well-studied task in a variety of domains. Nevertheless, previous work has mostly focused on multiclass versions of the problem, where the labels are mutually exclusive, and typically positive, negative or neutral. In this paper, we address versions of the task in which an utterance can have multiple labels, thus corresponding to multilabel classification. We propose a method that explicitly incorporates label dependencies in the training objective and compare it against a variety of baselines, as well as a reduction of multilabel to multiclass learning. In experiments with three datasets, we find that our proposed method improves upon all baselines on two out of three datasets. We also show that the reduction of multilabel to multiclass classification can be very competitive, especially in cases where the output consists of a small number of labels and one can enumerate over all label combinations. |
| Tasks | Stance Detection |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1665/ |
| https://www.aclweb.org/anthology/D19-1665 | |
| PWC | https://paperswithcode.com/paper/incorporating-label-dependencies-in |
| Repo | https://github.com/willferreira/multilabel-stance-detection |
| Framework | tf |
