Paper Group NANR 17
Team Kermit-the-frog at SemEval-2019 Task 4: Bias Detection Through Sentiment Analysis and Simple Linguistic Features. Neural Lemmatization of Multiword Expressions. Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images. Integrating Bayesian and Discriminative Sparse Kernel Machines for Multi-class Active Lear …
Team Kermit-the-frog at SemEval-2019 Task 4: Bias Detection Through Sentiment Analysis and Simple Linguistic Features
| Title | Team Kermit-the-frog at SemEval-2019 Task 4: Bias Detection Through Sentiment Analysis and Simple Linguistic Features |
| Authors | Talita Anthonio, Lennart Kloppenburg |
| Abstract | In this paper we describe our participation in the SemEval 2019 shared task on hyperpartisan news detection. We present the system that we submitted for final evaluation and the three approaches that we used: sentiment, bias-laden words and filtered n-gram features. Our submitted model is a Linear SVM that solely relies on the negative sentiment of a document. We achieved an accuracy of 0.621 and a f1 score of 0.694 in the competition, revealing the predictive power of negative sentiment for this task. There was no major improvement by adding or substituting the features of the other two approaches that we tried. |
| Tasks | Sentiment Analysis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2177/ |
| https://www.aclweb.org/anthology/S19-2177 | |
| PWC | https://paperswithcode.com/paper/team-kermit-the-frog-at-semeval-2019-task-4 |
| Repo | |
| Framework | |
Neural Lemmatization of Multiword Expressions
| Title | Neural Lemmatization of Multiword Expressions |
| Authors | Marine Schmitt, Mathieu Constant |
| Abstract | This article focuses on the lemmatization of multiword expressions (MWEs). We propose a deep encoder-decoder architecture generating for every MWE word its corresponding part in the lemma, based on the internal context of the MWE. The encoder relies on recurrent networks based on (1) the character sequence of the individual words to capture their morphological properties, and (2) the word sequence of the MWE to capture lexical and syntactic properties. The decoder in charge of generating the corresponding part of the lemma for each word of the MWE is based on a classical character-level attention-based recurrent model. Our model is evaluated for Italian, French, Polish and Portuguese and shows good performances except for Polish. |
| Tasks | Lemmatization |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5117/ |
| https://www.aclweb.org/anthology/W19-5117 | |
| PWC | https://paperswithcode.com/paper/neural-lemmatization-of-multiword-expressions |
| Repo | |
| Framework | |
Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images
| Title | Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images |
| Authors | Yi Zhou, Xiaodong He, Lei Huang, Li Liu, Fan Zhu, Shanshan Cui, Ling Shao |
| Abstract | Medical image analysis has two important research areas: disease grading and fine-grained lesion segmentation. Although the former problem often relies on the latter, the two are usually studied separately. Disease severity grading can be treated as a classification problem, which only requires image-level annotations, while the lesion segmentation requires stronger pixel-level annotations. However, pixel-wise data annotation for medical images is highly time-consuming and requires domain experts. In this paper, we propose a collaborative learning method to jointly improve the performance of disease grading and lesion segmentation by semi-supervised learning with an attention mechanism. Given a small set of pixel-level annotated data, a multi-lesion mask generation model first performs the traditional semantic segmentation task. Then, based on initially predicted lesion maps for large quantities of image-level annotated data, a lesion attentive disease grading model is designed to improve the severity classification accuracy. Meanwhile, the lesion attention model can refine the lesion maps using class-specific information to fine-tune the segmentation model in a semi-supervised manner. An adversarial architecture is also integrated for training. With extensive experiments on a representative medical problem called diabetic retinopathy (DR), we validate the effectiveness of our method and achieve consistent improvements over state-of-the-art methods on three public datasets. |
| Tasks | Lesion Segmentation, Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhou_Collaborative_Learning_of_Semi-Supervised_Segmentation_and_Classification_for_Medical_Images_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhou_Collaborative_Learning_of_Semi-Supervised_Segmentation_and_Classification_for_Medical_Images_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-learning-of-semi-supervised |
| Repo | |
| Framework | |
Integrating Bayesian and Discriminative Sparse Kernel Machines for Multi-class Active Learning
| Title | Integrating Bayesian and Discriminative Sparse Kernel Machines for Multi-class Active Learning |
| Authors | Weishi Shi, Qi Yu |
| Abstract | We propose a novel active learning (AL) model that integrates Bayesian and discriminative kernel machines for fast and accurate multi-class data sampling. By joining a sparse Bayesian model and a maximum margin machine under a unified kernel machine committee (KMC), the proposed model is able to identify a small number of data samples that best represent the overall data space while accurately capturing the decision boundaries. The integration is conducted using the maximum entropy discrimination framework, resulting in a joint objective function that contains generalized entropy as a regularizer. Such a property allows the proposed AL model to choose data samples that more effectively handle non-separable classification problems. Parameter learning is achieved through a principled optimization framework that leverages convex duality and sparse structure of KMC to efficiently optimize the joint objective function. Key model parameters are used to design a novel sampling function to choose data samples that can simultaneously improve multiple decision boundaries, making it an effective sampler for problems with a large number of classes. Experiments conducted over both synthetic and real data and comparison with competitive AL methods demonstrate the effectiveness of the proposed model. |
| Tasks | Active Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8500-integrating-bayesian-and-discriminative-sparse-kernel-machines-for-multi-class-active-learning |
| http://papers.nips.cc/paper/8500-integrating-bayesian-and-discriminative-sparse-kernel-machines-for-multi-class-active-learning.pdf | |
| PWC | https://paperswithcode.com/paper/integrating-bayesian-and-discriminative |
| Repo | |
| Framework | |
Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning
| Title | Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-2000/ |
| https://www.aclweb.org/anthology/K19-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-shared-task-on-cross |
| Repo | |
| Framework | |
EEG Signal Dimensionality Reduction and Classification using Tensor Decomposition and Deep Convolutional Neural Networks
| Title | EEG Signal Dimensionality Reduction and Classification using Tensor Decomposition and Deep Convolutional Neural Networks |
| Authors | Mojtaba Taherisadr, Mohsen Joneidi, Nazanin Rahnavard |
| Abstract | A new deep learning-based electroencephalography (EEG) signal analysis framework is proposed. While deep neural networks, specifically convolutional neural networks (CNNs), have gained remarkable attention recently, they still suffer from high dimensionality of the training data. Two-dimensional input images of CNNs are more vulnerable to be redundant versus one-dimensional input time-series of conventional neural networks. In this study, we propose a new dimensionality reduction framework for reducing the dimension of CNN inputs based on the tensor decomposition of the time-frequency representation of EEG signals. The proposed tensor decomposition-based dimensionality reduction algorithm transforms a large set of slices of the input tensor to a concise set of slices which are called super-slices. Employing super-slices not only handles the artifacts and redundancies of the EEG data but also reduces the dimension of the CNNs training inputs. We also consider different time-frequency representation methods for EEG image generation and provide a comprehensive comparison among them. We test our proposed framework on HCB-MIT data and as results show our approach outperforms other previous studies. |
| Tasks | Dimensionality Reduction, EEG, Image Generation, Seizure Detection, Time Series |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10432 |
| https://arxiv.org/pdf/1908.10432 | |
| PWC | https://paperswithcode.com/paper/eeg-signal-dimensionality-reduction-and |
| Repo | |
| Framework | |
Sequential Attention with Keyword Mask Model for Community-based Question Answering
| Title | Sequential Attention with Keyword Mask Model for Community-based Question Answering |
| Authors | Jianxin Yang, Wenge Rong, Libin Shi, Zhang Xiong |
| Abstract | In Community-based Question Answering system(CQA), Answer Selection(AS) is a critical task, which focuses on finding a suitable answer within a list of candidate answers. For neural network models, the key issue is how to model the representations of QA text pairs and calculate the interactions between them. We propose a Sequential Attention with Keyword Mask model(SAKM) for CQA to imitate human reading behavior. Question and answer text regard each other as context within keyword-mask attention when encoding the representations, and repeat multiple times(hops) in a sequential style. So the QA pairs capture features and information from both question text and answer text, interacting and improving vector representations iteratively through hops. The flexibility of the model allows to extract meaningful keywords from the sentences and enhance diverse mutual information. We perform on answer selection tasks and multi-level answer ranking tasks. Experiment results demonstrate the superiority of our proposed model on community-based QA datasets. |
| Tasks | Answer Selection, Question Answering |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1228/ |
| https://www.aclweb.org/anthology/N19-1228 | |
| PWC | https://paperswithcode.com/paper/sequential-attention-with-keyword-mask-model |
| Repo | |
| Framework | |
On Tighter Generalization Bounds for Deep Neural Networks: CNNs, ResNets, and Beyond
| Title | On Tighter Generalization Bounds for Deep Neural Networks: CNNs, ResNets, and Beyond |
| Authors | Xingguo Li, Junwei Lu, Zhaoran Wang, Jarvis Haupt, Tuo Zhao |
| Abstract | We propose a generalization error bound for a general family of deep neural networks based on the depth and width of the networks, as well as the spectral norm of weight matrices. Through introducing a novel characterization of the Lipschitz properties of neural network family, we achieve a tighter generalization error bound. We further obtain a result that is free of linear dependence on norms for bounded losses. Besides the general deep neural networks, our results can be applied to derive new bounds for several popular architectures, including convolutional neural networks (CNNs), residual networks (ResNets), and hyperspherical networks (SphereNets). When achieving same generalization errors with previous arts, our bounds allow for the choice of much larger parameter spaces of weight matrices, inducing potentially stronger expressive ability for neural networks. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SJzwvoCqF7 |
| https://openreview.net/pdf?id=SJzwvoCqF7 | |
| PWC | https://paperswithcode.com/paper/on-tighter-generalization-bounds-for-deep |
| Repo | |
| Framework | |
Automatic Taxonomy Induction and Expansion
| Title | Automatic Taxonomy Induction and Expansion |
| Authors | Nicolas Rodolfo Fauceglia, Alfio Gliozzo, Sarthak Dash, Md. Faisal Mahbub Chowdhury, N Mihindukulasooriya, ana |
| Abstract | The Knowledge Graph Induction Service (KGIS) is an end-to-end knowledge induction system. One of its main capabilities is to automatically induce taxonomies from input documents using a hybrid approach that takes advantage of linguistic patterns, semantic web and neural networks. KGIS allows the user to semi-automatically curate and expand the induced taxonomy through a component called Smart SpreadSheet by exploiting distributional semantics. In this paper, we describe these taxonomy induction and expansion features of KGIS. A screencast video demonstrating the system is available in https://ibm.box.com/v/emnlp-2019-demo . |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3005/ |
| https://www.aclweb.org/anthology/D19-3005 | |
| PWC | https://paperswithcode.com/paper/automatic-taxonomy-induction-and-expansion |
| Repo | |
| Framework | |
Learning from Bad Data via Generation
| Title | Learning from Bad Data via Generation |
| Authors | Tianyu Guo, Chang Xu, Boxin Shi, Chao Xu, Dacheng Tao |
| Abstract | Bad training data would challenge the learning model from understanding the underlying data-generating scheme, which then increases the difficulty in achieving satisfactory performance on unseen test data. We suppose the real data distribution lies in a distribution set supported by the empirical distribution of bad data. A worst-case formulation can be developed over this distribution set, and then be interpreted as a generation task in an adversarial manner. The connections and differences between GANs and our framework have been thoroughly discussed. We further theoretically show the influence of this generation task on learning from bad data and reveal its connection with a data-dependent regularization. Given different distance measures (\eg, Wasserstein distance or JS divergence) of distributions, we can derive different objective functions for the problem. Experimental results on different kinds of bad training data demonstrate the necessity and effectiveness of the proposed method. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8837-learning-from-bad-data-via-generation |
| http://papers.nips.cc/paper/8837-learning-from-bad-data-via-generation.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-bad-data-via-generation |
| Repo | |
| Framework | |
Low Level Linguistic Controls for Style Transfer and Content Preservation
| Title | Low Level Linguistic Controls for Style Transfer and Content Preservation |
| Authors | Katy Gero, Chris Kedzie, Jonathan Reeve, Lydia Chilton |
| Abstract | Despite the success of style transfer in image processing, it has seen limited progress in natural language generation. Part of the problem is that content is not as easily decoupled from style in the text domain. Curiously, in the field of stylometry, content does not figure prominently in practical methods of discriminating stylistic elements, such as authorship and genre. Rather, syntax and function words are the most salient features. Drawing on this work, we model style as a suite of low-level linguistic controls, such as frequency of pronouns, prepositions, and subordinate clause constructions. We train a neural encoder-decoder model to reconstruct reference sentences given only content words and the setting of the controls. We perform style transfer by keeping the content words fixed while adjusting the controls to be indicative of another style. In experiments, we show that the model reliably responds to the linguistic controls and perform both automatic and manual evaluations on style transfer. We find we can fool a style classifier 84{%} of the time, and that our model produces highly diverse and stylistically distinctive outputs. This work introduces a formal, extendable model of style that can add control to any neural text generation system. |
| Tasks | Style Transfer, Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8628/ |
| https://www.aclweb.org/anthology/W19-8628 | |
| PWC | https://paperswithcode.com/paper/low-level-linguistic-controls-for-style-1 |
| Repo | |
| Framework | |
Spatial Residual Layer and Dense Connection Block Enhanced Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
| Title | Spatial Residual Layer and Dense Connection Block Enhanced Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition |
| Authors | Cong Wu, Xiao-Jun Wu, Josef Kittler |
| Abstract | Recent research has shown that modeling the dynamic joint features of the human body by a graph convolutional network (GCN) is a groundbreaking approach for skeleton-based action recognition, especially for the recognition of the body-motion, human-object and human-human interactions. Nevertheless, how to model and utilize coherent skeleton information comprehensively is still an open problem. In order to capture the rich spatiotemporal information and utilize features more effectively, we introduce a spatial residual layer and a dense connection block enhanced spatial temporal graph convolutional network. More specifically, our work introduces three aspects. Firstly, we extend spatial graph convolution to spatial temporal graph convolution of cross-domain residual to extract more precise and informative spatiotemporal feature, and reduce the training complexity by feature fusion in the, so-called, spatial residual layer. Secondly, instead of simply superimposing multiple similar layers, we use dense connection to take full advantage of the global information. Thirdly, we combine the above mentioned two components to create a spatial temporal graph convolutional network (ST-GCN), referred to as SDGCN. The proposed graph representation has a new structure. We perform extensive experiments on two large datasets: Kinetics and NTU-RGB+D. Our method achieves a great improvement in performance compared to the mainstream methods. We evaluate our method quantitatively and qualitatively, thus proving its effectiveness. |
| Tasks | Skeleton Based Action Recognition |
| Published | 2019-10-27 |
| URL | http://openaccess.thecvf.com/content_ICCVW_2019/html/SGRL/Wu_Spatial_Residual_Layer_and_Dense_Connection_Block_Enhanced_Spatial_Temporal_ICCVW_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCVW_2019/papers/SGRL/Wu_Spatial_Residual_Layer_and_Dense_Connection_Block_Enhanced_Spatial_Temporal_ICCVW_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-residual-layer-and-dense-connection |
| Repo | |
| Framework | |
MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding
| Title | MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding |
| Authors | Quan Kong, Ziming Wu, Ziwei Deng, Martin Klinkigt, Bin Tong, Tomokazu Murakami |
| Abstract | Unlike vision modalities, body-worn sensors or passive sensing can avoid the failure of action understanding in vision related challenges, e.g. occlusion and appearance variation. However, a standard large-scale dataset does not exist, in which different types of modalities across vision and sensors are integrated. To address the disadvantage of vision-based modalities and push towards multi/cross modal action understanding, this paper introduces a new large-scale dataset recorded from 20 distinct subjects with seven different types of modalities: RGB videos, keypoints, acceleration, gyroscope, orientation, Wi-Fi and pressure signal. The dataset consists of more than 36k video clips for 37 action classes covering a wide range of daily life activities such as desktop-related and check-in-based ones in four different distinct scenarios. On the basis of our dataset, we propose a novel multi modality distillation model with attention mechanism to realize an adaptive knowledge transfer from sensor-based modalities to vision-based modalities. The proposed model significantly improves performance of action recognition compared to models trained with only RGB information. The experimental results confirm the effectiveness of our model on cross-subject, -view, -scene and -session evaluation criteria. We believe that this new large-scale multimodal dataset will contribute the community of multimodal based action understanding. |
| Tasks | Transfer Learning |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Kong_MMAct_A_Large-Scale_Dataset_for_Cross_Modal_Human_Action_Understanding_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Kong_MMAct_A_Large-Scale_Dataset_for_Cross_Modal_Human_Action_Understanding_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mmact-a-large-scale-dataset-for-cross-modal |
| Repo | |
| Framework | |
Three-Stream Convolutional Neural Network With Multi-Task and Ensemble Learning for 3D Action Recognition
| Title | Three-Stream Convolutional Neural Network With Multi-Task and Ensemble Learning for 3D Action Recognition |
| Authors | Duohan Liang, Guoliang Fan, Guangfeng Lin, Wanjun Chen, Xiaorong Pan, Hong Zhu |
| Abstract | In this paper, we propose a three-stream convolutional neural network (3SCNN) for action recognition from skeleton sequences, which aims to thoroughly and fully exploit the skeleton data by extracting, learning, fusing and inferring multiple motion-related features, including 3D joint positions and joint displacements across adjacent frames as well as oriented bone segments. The proposed 3SCNN involves three sequential stages. The first stage enriches three independently extracted features by co-occurrence feature learning. The second stage involves multi-channel pairwise fusion to take advantage of the complementary and diverse nature among three features. The third stage is a multi-task and ensemble learning network to further improve the generalization ability of 3SCNN. Experimental results on the standard dataset show the effectiveness of our proposed multi-stream feature learning, fusion and inference method for skeleton-based 3D action recognition. |
| Tasks | 3D Human Action Recognition, Skeleton Based Action Recognition |
| Published | 2019-06-16 |
| URL | http://openaccess.thecvf.com/content_CVPRW_2019/html/PBVS/Liang_Three-Stream_Convolutional_Neural_Network_With_Multi-Task_and_Ensemble_Learning_for_CVPRW_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPRW_2019/papers/PBVS/Liang_Three-Stream_Convolutional_Neural_Network_With_Multi-Task_and_Ensemble_Learning_for_CVPRW_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/three-stream-convolutional-neural-network |
| Repo | |
| Framework | |
Machine Translation from an Intercomprehension Perspective
| Title | Machine Translation from an Intercomprehension Perspective |
| Authors | Yu Chen, Tania Avgustinova |
| Abstract | Within the first shared task on machine translation between similar languages, we present our first attempts on Czech to Polish machine translation from an intercomprehension perspective. We propose methods based on the mutual intelligibility of the two languages, taking advantage of their orthographic and phonological similarity, in the hope to improve over our baselines. The translation results are evaluated using BLEU. On this metric, none of our proposals could outperform the baselines on the final test set. The current setups are rather preliminary, and there are several potential improvements we can try in the future. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5425/ |
| https://www.aclweb.org/anthology/W19-5425 | |
| PWC | https://paperswithcode.com/paper/machine-translation-from-an |
| Repo | |
| Framework | |
