Paper Group NANR 7
SyntaxFest 2019 Invited talk - Arguments and adjuncts. Reading Turn by Turn: Hierarchical Attention Architecture for Spoken Dialogue Comprehension. ConlluEditor: a fully graphical editor for Universal dependencies treebank files. Global Feature Guided Local Pooling. Multiclass Performance Metric Elicitation. Do Nuclear Submarines Have Nuclear Capta …
SyntaxFest 2019 Invited talk - Arguments and adjuncts
| Title | SyntaxFest 2019 Invited talk - Arguments and adjuncts |
| Authors | Adam Przepi{'o}rkowski |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-8001/ |
| https://www.aclweb.org/anthology/W19-8001 | |
| PWC | https://paperswithcode.com/paper/syntaxfest-2019-invited-talk-arguments-and |
| Repo | |
| Framework | |
Reading Turn by Turn: Hierarchical Attention Architecture for Spoken Dialogue Comprehension
| Title | Reading Turn by Turn: Hierarchical Attention Architecture for Spoken Dialogue Comprehension |
| Authors | Zhengyuan Liu, Nancy Chen |
| Abstract | Comprehending multi-turn spoken conversations is an emerging research area, presenting challenges different from reading comprehension of passages due to the interactive nature of information exchange from at least two speakers. Unlike passages, where sentences are often the default semantic modeling unit, in multi-turn conversations, a turn is a topically coherent unit embodied with immediately relevant context, making it a linguistically intuitive segment for computationally modeling verbal interactions. Therefore, in this work, we propose a hierarchical attention neural network architecture, combining turn-level and word-level attention mechanisms, to improve spoken dialogue comprehension performance. Experiments are conducted on a multi-turn conversation dataset, where nurses inquire and discuss symptom information with patients. We empirically show that the proposed approach outperforms standard attention baselines, achieves more efficient learning outcomes, and is more robust to lengthy and out-of-distribution test samples. |
| Tasks | Reading Comprehension |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1543/ |
| https://www.aclweb.org/anthology/P19-1543 | |
| PWC | https://paperswithcode.com/paper/reading-turn-by-turn-hierarchical-attention |
| Repo | |
| Framework | |
ConlluEditor: a fully graphical editor for Universal dependencies treebank files
| Title | ConlluEditor: a fully graphical editor for Universal dependencies treebank files |
| Authors | Johannes Heinecke |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-8010/ |
| https://www.aclweb.org/anthology/W19-8010 | |
| PWC | https://paperswithcode.com/paper/conllueditor-a-fully-graphical-editor-for |
| Repo | |
| Framework | |
Global Feature Guided Local Pooling
| Title | Global Feature Guided Local Pooling |
| Authors | Takumi Kobayashi |
| Abstract | In deep convolutional neural networks (CNNs), local pooling operation is a key building block to effectively downsize feature maps for reducing computation cost as well as increasing robustness against input variation. There are several types of pooling operation, such as average/max-pooling, from which one has to be manually selected for building CNNs. The optimal pooling type would be dependent on characteristics of features in CNNs and classification tasks, making it hard to find out the proper pooling module in advance. In this paper, we propose a flexible pooling method which adaptively tunes the pooling functionality based on input features without manually fixing it beforehand. In the proposed method, the parameterized pooling form is derived from a probabilistic perspective to flexibly represent various types of pooling and then the parameters are estimated by means of global statistics in the input feature map. Thus, the proposed local pooling guided by global features effectively works in the CNNs trained in an end-to-end manner. The experimental results on image classification tasks demonstrate the effectiveness of the proposed pooling method in various deep CNNs. |
| Tasks | Image Classification |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Kobayashi_Global_Feature_Guided_Local_Pooling_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Kobayashi_Global_Feature_Guided_Local_Pooling_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/global-feature-guided-local-pooling |
| Repo | |
| Framework | |
Multiclass Performance Metric Elicitation
| Title | Multiclass Performance Metric Elicitation |
| Authors | Gaurush Hiranandani, Shant Boodaghians, Ruta Mehta, Oluwasanmi O. Koyejo |
| Abstract | Metric Elicitation is a principled framework for selecting the performance metric that best reflects implicit user preferences. However, available strategies have so far been limited to binary classification. In this paper, we propose novel strategies for eliciting multiclass classification performance metrics using only relative preference feedback. We also show that the strategies are robust to both finite sample and feedback noise. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9133-multiclass-performance-metric-elicitation |
| http://papers.nips.cc/paper/9133-multiclass-performance-metric-elicitation.pdf | |
| PWC | https://paperswithcode.com/paper/multiclass-performance-metric-elicitation |
| Repo | |
| Framework | |
Do Nuclear Submarines Have Nuclear Captains? A Challenge Dataset for Commonsense Reasoning over Adjectives and Objects
| Title | Do Nuclear Submarines Have Nuclear Captains? A Challenge Dataset for Commonsense Reasoning over Adjectives and Objects |
| Authors | James Mullenbach, Jonathan Gordon, Nanyun Peng, Jonathan May |
| Abstract | How do adjectives project from a noun to its parts? If a motorcycle is red, are its wheels red? Is a nuclear submarine{'}s captain nuclear? These questions are easy for humans to judge using our commonsense understanding of the world, but are difficult for computers. To attack this challenge, we crowdsource a set of human judgments that answer the English-language question {``}Given a whole described by an adjective, does the adjective also describe a given part?{''} We build strong baselines for this task with a classification approach. Our findings indicate that, despite the recent successes of large language models on tasks aimed to assess commonsense knowledge, these models do not greatly outperform simple word-level models based on pre-trained word embeddings. This provides evidence that the amount of commonsense knowledge encoded in these language models does not extend far beyond that already baked into the word embeddings. Our dataset will serve as a useful testbed for future research in commonsense reasoning, especially as it relates to adjectives and objects | |
| Tasks | Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1625/ |
| https://www.aclweb.org/anthology/D19-1625 | |
| PWC | https://paperswithcode.com/paper/do-nuclear-submarines-have-nuclear-captains-a |
| Repo | |
| Framework | |
Evaluation of Morphological Embeddings for English and Russian Languages
| Title | Evaluation of Morphological Embeddings for English and Russian Languages |
| Authors | Vitaly Romanov, Albina Khusainova |
| Abstract | This paper evaluates morphology-based embeddings for English and Russian languages. Despite the interest and introduction of several morphology based word embedding models in the past and acclaimed performance improvements on word similarity and language modeling tasks, in our experiments, we did not observe any stable preference over two of our baseline models - SkipGram and FastText. The performance exhibited by morphological embeddings is the average of the two baselines mentioned above. |
| Tasks | Language Modelling |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2010/ |
| https://www.aclweb.org/anthology/W19-2010 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-morphological-embeddings-for |
| Repo | |
| Framework | |
Align, Attend and Locate: Chest X-Ray Diagnosis via Contrast Induced Attention Network With Limited Supervision
| Title | Align, Attend and Locate: Chest X-Ray Diagnosis via Contrast Induced Attention Network With Limited Supervision |
| Authors | Jingyu Liu, Gangming Zhao, Yu Fei, Ming Zhang, Yizhou Wang, Yizhou Yu |
| Abstract | Obstacles facing accurate identification and localization of diseases in chest X-ray images lie in the lack of high-quality images and annotations. In this paper, we propose a Contrast Induced Attention Network (CIA-Net), which exploits the highly structured property of chest X-ray images and localizes diseases via contrastive learning on the aligned positive and negative samples. To force the attention module to focus only on sites of abnormalities, we also introduce a learnable alignment module to adjust all the input images, which eliminates variations of scales, angles, and displacements of X-ray images generated under bad scan conditions. We show that the use of contrastive attention and alignment module allows the model to learn rich identification and localization information using only a small amount of location annotations, resulting in state-of-the-art performance in NIH chest X-ray dataset. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Align_Attend_and_Locate_Chest_X-Ray_Diagnosis_via_Contrast_Induced_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Align_Attend_and_Locate_Chest_X-Ray_Diagnosis_via_Contrast_Induced_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/align-attend-and-locate-chest-x-ray-diagnosis |
| Repo | |
| Framework | |
Complex Program Induction for Querying Knowledge Bases in the Absence of Gold Programs
| Title | Complex Program Induction for Querying Knowledge Bases in the Absence of Gold Programs |
| Authors | Amrita Saha, Ghulam Ahmed Ansari, Abhishek Laddha, Karthik Sankaranarayanan, Soumen Chakrabarti |
| Abstract | Recent years have seen increasingly complex question-answering on knowledge bases (KBQA) involving logical, quantitative, and comparative reasoning over KB subgraphs. Neural Program Induction (NPI) is a pragmatic approach toward modularizing the reasoning process by translating a complex natural language query into a multi-step executable program. While NPI has been commonly trained with the {}{}gold{'}{'} program or its sketch, for realistic KBQA applications such gold programs are expensive to obtain. There, practically only natural language queries and the corresponding answers can be provided for training. The resulting combinatorial explosion in program space, along with extremely sparse rewards, makes NPI for KBQA ambitious and challenging. We present Complex Imperative Program Induction from Terminal Rewards (CIPITR), an advanced neural programmer that mitigates reward sparsity with auxiliary rewards, and restricts the program space to semantically correct programs using high-level constraints, KB schema, and inferred answer type. CIPITR solves complex KBQA considerably more accurately than key-value memory networks and neural symbolic machines (NSM). For moderately complex queries requiring 2- to 5-step programs, CIPITR scores at least 3{\mbox{$\times$}} higher F1 than the competing systems. On one of the hardest class of programs (comparative reasoning) with 5{–}10 steps, CIPITR outperforms NSM by a factor of 89 and memory networks by 9 times. |
| Tasks | Question Answering |
| Published | 2019-03-01 |
| URL | https://www.aclweb.org/anthology/Q19-1012/ |
| https://www.aclweb.org/anthology/Q19-1012 | |
| PWC | https://paperswithcode.com/paper/complex-program-induction-for-querying |
| Repo | |
| Framework | |
DeepSentiPeer: Harnessing Sentiment in Review Texts to Recommend Peer Review Decisions
| Title | DeepSentiPeer: Harnessing Sentiment in Review Texts to Recommend Peer Review Decisions |
| Authors | Tirthankar Ghosal, Rajeev Verma, Asif Ekbal, Pushpak Bhattacharyya |
| Abstract | Automatically validating a research artefact is one of the frontiers in Artificial Intelligence (AI) that directly brings it close to competing with human intellect and intuition. Although criticised sometimes, the existing peer review system still stands as the benchmark of research validation. The present-day peer review process is not straightforward and demands profound domain knowledge, expertise, and intelligence of human reviewer(s), which is somewhat elusive with the current state of AI. However, the peer review texts, which contains rich sentiment information of the reviewer, reflecting his/her overall attitude towards the research in the paper, could be a valuable entity to predict the acceptance or rejection of the manuscript under consideration. Here in this work, we investigate the role of reviewer sentiment embedded within peer review texts to predict the peer review outcome. Our proposed deep neural architecture takes into account three channels of information: the paper, the corresponding reviews, and review{'}s polarity to predict the overall recommendation score as well as the final decision. We achieve significant performance improvement over the baselines (∼ 29{%} error reduction) proposed in a recently released dataset of peer reviews. An AI of this kind could assist the editors/program chairs as an additional layer of confidence, especially when non-responding/missing reviewers are frequent in present day peer review. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1106/ |
| https://www.aclweb.org/anthology/P19-1106 | |
| PWC | https://paperswithcode.com/paper/deepsentipeer-harnessing-sentiment-in-review |
| Repo | |
| Framework | |
SME-Net: Sparse Motion Estimation for Parametric Video Prediction Through Reinforcement Learning
| Title | SME-Net: Sparse Motion Estimation for Parametric Video Prediction Through Reinforcement Learning |
| Authors | Yung-Han Ho, Chuan-Yuan Cho, Wen-Hsiao Peng, Guo-Lun Jin |
| Abstract | This paper leverages a classic prediction technique, known as parametric overlapped block motion compensation (POBMC), in a reinforcement learning framework for video prediction. Learning-based prediction methods with explicit motion models often suffer from having to estimate large numbers of motion parameters with artificial regularization. Inspired by the success of sparse motion-based prediction for video compression, we propose a parametric video prediction on a sparse motion field composed of few critical pixels and their motion vectors. The prediction is achieved by gradually refining the estimate of a future frame in iterative, discrete steps. Along the way, the identification of critical pixels and their motion estimation are addressed by two neural networks trained under a reinforcement learning setting. Our model achieves the state-of-the-art performance on CaltchPed, UCF101 and CIF datasets in one-step and multi-step prediction tests. It shows good generalization results and is able to learn well on small training data. |
| Tasks | Motion Compensation, Motion Estimation, Video Compression, Video Prediction |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Ho_SME-Net_Sparse_Motion_Estimation_for_Parametric_Video_Prediction_Through_Reinforcement_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Ho_SME-Net_Sparse_Motion_Estimation_for_Parametric_Video_Prediction_Through_Reinforcement_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sme-net-sparse-motion-estimation-for |
| Repo | |
| Framework | |
Proceedings of the Third Workshop on Structured Prediction for NLP
| Title | Proceedings of the Third Workshop on Structured Prediction for NLP |
| Authors | |
| Abstract | |
| Tasks | Structured Prediction |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1500/ |
| https://www.aclweb.org/anthology/W19-1500 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-third-workshop-on-5 |
| Repo | |
| Framework | |
A Novel Deep Arrhythmia-Diagnosis Network for Atrial Fibrillation Classification Using Electrocardiogram Signals
| Title | A Novel Deep Arrhythmia-Diagnosis Network for Atrial Fibrillation Classification Using Electrocardiogram Signals |
| Authors | Hao Dang, Muyi Sun, Guanhong Zhang, Xingqun Qi, Xiaoguang Zhou, Qing Chang |
| Abstract | Atrial fibrillation (AF), a common abnormal heartbeat rhythm, is a life-threatening recurrent disease that affects older adults. Automatic classification is one of the most valuable topics in medical sciences and bioinformatics, especially the detection of atrial fibrillation. However, it is difficult to accurately explain the local characteristics of electrocardiogram (ECG) signals by manual analysis, due to their small amplitude and short duration, coupled with the complexity and non-linearity. Hence, in this paper, we propose a novel deep arrhythmia-diagnosis method, named deep CNN-BLSTM network model, to automatically detect the AF heartbeats using the ECG signals. The model mainly consists of four convolution layers: two BLSTM layers and two fully connected layers. The datasets of RR intervals (called set A) and heartbeat sequences (P-QRS-T waves, called set B) are fed into the above-mentioned model. Most importantly, our proposed approach achieved favorable performances with an accuracy of 99.94% and 98.63% in the training and validation set of set A, respectively. In the testing set (unseen data sets), we obtained an accuracy of 96.59%, a sensitivity of 99.93%, and a specificity of 97.03%. To the best of our knowledge, the algorithm we proposed has shown excellent results compared to many state-of-art researches, which provides a new solution for the AF automatic detection. |
| Tasks | Arrhythmia Detection, Atrial Fibrillation Detection, Electrocardiography (ECG) |
| Published | 2019-05-24 |
| URL | https://doi.org/10.1109/ACCESS.2019.2918792 |
| https://ieeexplore.ieee.org/ielx7/6287639/8600701/08721643.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-deep-arrhythmia-diagnosis-network-for |
| Repo | |
| Framework | |
Variational Sparse Coding
| Title | Variational Sparse Coding |
| Authors | Francesco Tonolini, Bjorn Sand Jensen, Roderick Murray-Smith |
| Abstract | Variational auto-encoders (VAEs) offer a tractable approach when performing approximate inference in otherwise intractable generative models. However, standard VAEs often produce latent codes that are disperse and lack interpretability, thus making the resulting representations unsuitable for auxiliary tasks (e.g. classification) and human interpretation. We address these issues by merging ideas from variational auto-encoders and sparse coding, and propose to explicitly model sparsity in the latent space of a VAE with a Spike and Slab prior distribution. We derive the evidence lower bound using a discrete mixture recognition function thereby making approximate posterior inference as computational efficient as in the standard VAE case. With the new approach, we are able to infer truly sparse representations with generally intractable non-linear probabilistic models. We show that these sparse representations are advantageous over standard VAE representations on two benchmark classification tasks (MNIST and Fashion-MNIST) by demonstrating improved classification accuracy and significantly increased robustness to the number of latent dimensions. Furthermore, we demonstrate qualitatively that the sparse elements capture subjectively understandable sources of variation. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SkeJ6iR9Km |
| https://openreview.net/pdf?id=SkeJ6iR9Km | |
| PWC | https://paperswithcode.com/paper/variational-sparse-coding |
| Repo | |
| Framework | |
On the Margin Theory of Feedforward Neural Networks
| Title | On the Margin Theory of Feedforward Neural Networks |
| Authors | Colin Wei, Jason Lee, Qiang Liu, Tengyu Ma |
| Abstract | Past works have shown that, somewhat surprisingly, over-parametrization can help generalization in neural networks. Towards explaining this phenomenon, we adopt a margin-based perspective. We establish: 1) for multi-layer feedforward relu networks, the global minimizer of a weakly-regularized cross-entropy loss has the maximum normalized margin among all networks, 2) as a result, increasing the over-parametrization improves the normalized margin and generalization error bounds for deep networks. In the case of two-layer networks, an infinite-width neural network enjoys the best generalization guarantees. The typical infinite feature methods are kernel methods; we compare the neural net margin with that of kernel methods and construct natural instances where kernel methods have much weaker generalization guarantees. We validate this gap between the two approaches empirically. Finally, this infinite-neuron viewpoint is also fruitful for analyzing optimization. We show that a perturbed gradient flow on infinite-size networks finds a global optimizer in polynomial time. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJGtFoC5Fm |
| https://openreview.net/pdf?id=HJGtFoC5Fm | |
| PWC | https://paperswithcode.com/paper/on-the-margin-theory-of-feedforward-neural-1 |
| Repo | |
| Framework | |
