Paper Group ANR 1711
Self-Supervised Dialogue Learning. Verification of Non-Linear Specifications for Neural Networks. Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA. Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation. CURE: Curvature Regularization For Missing Data Recovery. Are we asking the right questions in MovieQA?. LPa …
Self-Supervised Dialogue Learning
| Title | Self-Supervised Dialogue Learning |
| Authors | Jiawei Wu, Xin Wang, William Yang Wang |
| Abstract | The sequential order of utterances is often meaningful in coherent dialogues, and the order changes of utterances could lead to low-quality and incoherent conversations. We consider the order information as a crucial supervised signal for dialogue learning, which, however, has been neglected by many previous dialogue systems. Therefore, in this paper, we introduce a self-supervised learning task, inconsistent order detection, to explicitly capture the flow of conversation in dialogues. Given a sampled utterance pair triple, the task is to predict whether it is ordered or misordered. Then we propose a sampling-based self-supervised network SSN to perform the prediction with sampled triple references from previous dialogue history. Furthermore, we design a joint learning framework where SSN can guide the dialogue systems towards more coherent and relevant dialogue learning through adversarial training. We demonstrate that the proposed methods can be applied to both open-domain and task-oriented dialogue scenarios, and achieve the new state-of-the-art performance on the OpenSubtitiles and Movie-Ticket Booking datasets. |
| Tasks | |
| Published | 2019-06-30 |
| URL | https://arxiv.org/abs/1907.00448v1 |
| https://arxiv.org/pdf/1907.00448v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-dialogue-learning |
| Repo | |
| Framework | |
Verification of Non-Linear Specifications for Neural Networks
| Title | Verification of Non-Linear Specifications for Neural Networks |
| Authors | Chongli Qin, Krishnamurthy, Dvijotham, Brendan O’Donoghue, Rudy Bunel, Robert Stanforth, Sven Gowal, Jonathan Uesato, Grzegorz Swirszcz, Pushmeet Kohli |
| Abstract | Prior work on neural network verification has focused on specifications that are linear functions of the output of the network, e.g., invariance of the classifier output under adversarial perturbations of the input. In this paper, we extend verification algorithms to be able to certify richer properties of neural networks. To do this we introduce the class of convex-relaxable specifications, which constitute nonlinear specifications that can be verified using a convex relaxation. We show that a number of important properties of interest can be modeled within this class, including conservation of energy in a learned dynamics model of a physical system; semantic consistency of a classifier’s output labels under adversarial perturbations and bounding errors in a system that predicts the summation of handwritten digits. Our experimental evaluation shows that our method is able to effectively verify these specifications. Moreover, our evaluation exposes the failure modes in models which cannot be verified to satisfy these specifications. Thus, emphasizing the importance of training models not just to fit training data but also to be consistent with specifications. |
| Tasks | |
| Published | 2019-02-25 |
| URL | http://arxiv.org/abs/1902.09592v1 |
| http://arxiv.org/pdf/1902.09592v1.pdf | |
| PWC | https://paperswithcode.com/paper/verification-of-non-linear-specifications-for |
| Repo | |
| Framework | |
Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA
| Title | Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA |
| Authors | Badri N. Patro, Anupriy, Vinay P. Namboodiri |
| Abstract | In this paper, we aim to obtain improved attention for a visual question answering (VQA) task. It is challenging to provide supervision for attention. An observation we make is that visual explanations as obtained through class activation mappings (specifically Grad-CAM) that are meant to explain the performance of various networks could form a means of supervision. However, as the distributions of attention maps and that of Grad-CAMs differ, it would not be suitable to directly use these as a form of supervision. Rather, we propose the use of a discriminator that aims to distinguish samples of visual explanation and attention maps. The use of adversarial training of the attention regions as a two-player game between attention and explanation serves to bring the distributions of attention maps and visual explanations closer. Significantly, we observe that providing such a means of supervision also results in attention maps that are more closely related to human attention resulting in a substantial improvement over baseline stacked attention network (SAN) models. It also results in a good improvement in rank correlation metric on the VQA task. This method can also be combined with recent MCB based methods and results in consistent improvement. We also provide comparisons with other means for learning distributions such as based on Correlation Alignment (Coral), Maximum Mean Discrepancy (MMD) and Mean Square Error (MSE) losses and observe that the adversarial loss outperforms the other forms of learning the attention maps. Visualization of the results also confirms our hypothesis that attention maps improve using this form of supervision. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08618v1 |
| https://arxiv.org/pdf/1911.08618v1.pdf | |
| PWC | https://paperswithcode.com/paper/explanation-vs-attention-a-two-player-game-to |
| Repo | |
| Framework | |
Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation
| Title | Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation |
| Authors | Yiming Xu, Lin Chen, Zhongwei Cheng, Lixin Duan, Jiebo Luo |
| Abstract | We study the problem of visual question answering (VQA) in images by exploiting supervised domain adaptation, where there is a large amount of labeled data in the source domain but only limited labeled data in the target domain with the goal to train a good target model. A straightforward solution is to fine-tune a pre-trained source model by using those limited labeled target data, but it usually cannot work well due to the considerable difference between the data distributions of the source and target domains. Moreover, the availability of multiple modalities (i.e., images, questions and answers) in VQA poses further challenges to model the transferability between those different modalities. In this paper, we tackle the above issues by proposing a novel supervised multi-modal domain adaptation method for VQA to learn joint feature embeddings across different domains and modalities. Specifically, we align the data distributions of the source and target domains by considering all modalities together as well as separately for each individual modality. Based on the extensive experiments on the benchmark VQA 2.0 and VizWiz datasets for the realistic open-ended VQA task, we demonstrate that our proposed method outperforms the existing state-of-the-art approaches in this challenging domain adaptation setting for VQA. |
| Tasks | Domain Adaptation, Question Answering, Visual Question Answering |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04058v1 |
| https://arxiv.org/pdf/1911.04058v1.pdf | |
| PWC | https://paperswithcode.com/paper/open-ended-visual-question-answering-by-multi |
| Repo | |
| Framework | |
CURE: Curvature Regularization For Missing Data Recovery
| Title | CURE: Curvature Regularization For Missing Data Recovery |
| Authors | Bin Dong, Haocheng Ju, Yiping Lu, Zuoqiang Shi |
| Abstract | Missing data recovery is an important and yet challenging problem in imaging and data science. Successful models often adopt certain carefully chosen regularization. Recently, the low dimension manifold model (LDMM) was introduced by S.Osher et al. and shown effective in image inpainting. They observed that enforcing low dimensionality on image patch manifold serves as a good image regularizer. In this paper, we observe that having only the low dimension manifold regularization is not enough sometimes, and we need smoothness as well. For that, we introduce a new regularization by combining the low dimension manifold regularization with a higher order Curvature Regularization, and we call this new regularization CURE for short. The key step of solving CURE is to solve a biharmonic equation on a manifold. We further introduce a weighted version of CURE, called WeCURE, in a similar manner as the weighted nonlocal Laplacian (WNLL) method. Numerical experiments for image inpainting and semi-supervised learning show that the proposed CURE and WeCURE significantly outperform LDMM and WNLL respectively. |
| Tasks | Image Inpainting |
| Published | 2019-01-28 |
| URL | https://arxiv.org/abs/1901.09548v3 |
| https://arxiv.org/pdf/1901.09548v3.pdf | |
| PWC | https://paperswithcode.com/paper/cure-curvature-regularization-for-missing |
| Repo | |
| Framework | |
Are we asking the right questions in MovieQA?
| Title | Are we asking the right questions in MovieQA? |
| Authors | Bhavan Jasani, Rohit Girdhar, Deva Ramanan |
| Abstract | Joint vision and language tasks like visual question answering are fascinating because they explore high-level understanding, but at the same time, can be more prone to language biases. In this paper, we explore the biases in the MovieQA dataset and propose a strikingly simple model which can exploit them. We find that using the right word embedding is of utmost importance. By using an appropriately trained word embedding, about half the Question-Answers (QAs) can be answered by looking at the questions and answers alone, completely ignoring narrative context from video clips, subtitles, and movie scripts. Compared to the best published papers on the leaderboard, our simple question + answer only model improves accuracy by 5% for video + subtitle category, 5% for subtitle, 15% for DVS and 6% higher for scripts. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03083v1 |
| https://arxiv.org/pdf/1911.03083v1.pdf | |
| PWC | https://paperswithcode.com/paper/are-we-asking-the-right-questions-in-movieqa |
| Repo | |
| Framework | |
LPaintB: Learning to Paint from Self-Supervision
| Title | LPaintB: Learning to Paint from Self-Supervision |
| Authors | Biao Jia, Jonathan Brandt, Radomir Mech, Byungmoon Kim, Dinesh Manocha |
| Abstract | We present a novel reinforcement learning-based natural media painting algorithm. Our goal is to reproduce a reference image using brush strokes and we encode the objective through observations. Our formulation takes into account that the distribution of the reward in the action space is sparse and training a reinforcement learning algorithm from scratch can be difficult. We present an approach that combines self-supervised learning and reinforcement learning to effectively transfer negative samples into positive ones and change the reward distribution. We demonstrate the benefits of our painting agent to reproduce reference images with brush strokes. The training phase takes about one hour and the runtime algorithm takes about 30 seconds on a GTX1080 GPU reproducing a 1000x800 image with 20,000 strokes. |
| Tasks | Learning to Paint |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.06841v2 |
| https://arxiv.org/pdf/1906.06841v2.pdf | |
| PWC | https://paperswithcode.com/paper/lpaintb-learning-to-paint-from-self |
| Repo | |
| Framework | |
Neural Temporal-Difference Learning Converges to Global Optima
| Title | Neural Temporal-Difference Learning Converges to Global Optima |
| Authors | Qi Cai, Zhuoran Yang, Jason D. Lee, Zhaoran Wang |
| Abstract | Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coupling leads to nonconvexity and even divergence in optimization. As a result, the global convergence of neural TD remains unclear. In this paper, we prove for the first time that neural TD converges at a sublinear rate to the global optimum of the mean-squared projected Bellman error for policy evaluation. In particular, we show how such global convergence is enabled by the overparametrization of neural networks, which also plays a vital role in the empirical success of neural TD. Beyond policy evaluation, we establish the global convergence of neural (soft) Q-learning, which is further connected to that of policy gradient algorithms. |
| Tasks | Q-Learning |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10027v1 |
| https://arxiv.org/pdf/1905.10027v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-temporal-difference-learning-converges |
| Repo | |
| Framework | |
Global Planar Convolutions for improved context aggregation in Brain Tumor Segmentation
| Title | Global Planar Convolutions for improved context aggregation in Brain Tumor Segmentation |
| Authors | Santi Puch, Irina Sánchez, Aura Hernández, Gemma Piella, Vesna Prchkovska |
| Abstract | In this work, we introduce the Global Planar Convolution module as a building-block for fully-convolutional networks that aggregates global information and, therefore, enhances the context perception capabilities of segmentation networks in the context of brain tumor segmentation. We implement two baseline architectures (3D UNet and a residual version of 3D UNet, ResUNet) and present a novel architecture based on these two architectures, ContextNet, that includes the proposed Global Planar Convolution module. We show that the addition of such module eliminates the need of building networks with several representation levels, which tend to be over-parametrized and to showcase slow rates of convergence. Furthermore, we provide a visual demonstration of the behavior of GPC modules via visualization of intermediate representations. We finally participate in the 2018 edition of the BraTS challenge with our best performing models, that are based on ContextNet, and report the evaluation scores on the validation and the test sets of the challenge. |
| Tasks | Brain Tumor Segmentation |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10281v1 |
| https://arxiv.org/pdf/1908.10281v1.pdf | |
| PWC | https://paperswithcode.com/paper/global-planar-convolutions-for-improved |
| Repo | |
| Framework | |
This Email Could Save Your Life: Introducing the Task of Email Subject Line Generation
| Title | This Email Could Save Your Life: Introducing the Task of Email Subject Line Generation |
| Authors | Rui Zhang, Joel Tetreault |
| Abstract | Given the overwhelming number of emails, an effective subject line becomes essential to better inform the recipient of the email’s content. In this paper, we propose and study the task of email subject line generation: automatically generating an email subject line from the email body. We create the first dataset for this task and find that email subject line generation favor extremely abstractive summary which differentiates it from news headline generation or news single document summarization. We then develop a novel deep learning method and compare it to several baselines as well as recent state-of-the-art text summarization systems. We also investigate the efficacy of several automatic metrics based on correlations with human judgments and propose a new automatic evaluation metric. Our system outperforms competitive baselines given both automatic and human evaluations. To our knowledge, this is the first work to tackle the problem of effective email subject line generation. |
| Tasks | Document Summarization, Text Summarization |
| Published | 2019-06-08 |
| URL | https://arxiv.org/abs/1906.03497v1 |
| https://arxiv.org/pdf/1906.03497v1.pdf | |
| PWC | https://paperswithcode.com/paper/this-email-could-save-your-life-introducing |
| Repo | |
| Framework | |
Meta-Model Framework for Surrogate-Based Parameter Estimation in Dynamical Systems
| Title | Meta-Model Framework for Surrogate-Based Parameter Estimation in Dynamical Systems |
| Authors | Žiga Lukšič, Jovan Tanevski, Sašo Džeroski, Ljupčo Todorovski |
| Abstract | The central task in modeling complex dynamical systems is parameter estimation. This task involves numerous evaluations of a computationally expensive objective function. Surrogate-based optimization introduces a computationally efficient predictive model that approximates the value of the objective function. The standard approach involves learning a surrogate from training examples that correspond to past evaluations of the objective function. Current surrogate-based optimization methods use static, predefined substitution strategies that decide when to use the surrogate and when the true objective. We introduce a meta-model framework where the substitution strategy is dynamically adapted to the solution space of the given optimization problem. The meta model encapsulates the objective function, the surrogate model and the model of the substitution strategy, as well as components for learning them. The framework can be seamlessly coupled with an arbitrary optimization algorithm without any modification: it replaces the objective function and autonomously decides how to evaluate a given candidate solution. We test the utility of the framework on three tasks of estimating parameters of real-world models of dynamical systems. The results show that the meta model significantly improves the efficiency of optimization, reducing the total number of evaluations of the objective function up to an average of 77%. |
| Tasks | |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.09088v2 |
| https://arxiv.org/pdf/1906.09088v2.pdf | |
| PWC | https://paperswithcode.com/paper/meta-model-framework-for-surrogate-based |
| Repo | |
| Framework | |
Statistical Method to Model the Quality Inconsistencies of the Welding Process
| Title | Statistical Method to Model the Quality Inconsistencies of the Welding Process |
| Authors | Mohammad Aminisharifabad, Qingyu Yang |
| Abstract | Resistance Spot Welding (RSW) is an important manufacturing process that attracts increasing attention in automotive industry. However, due to the complexity of the manufacturing process, the corresponding product quality shows significant inconsistencies even under the same process setup. This paper develops a statistical method to capture the inconsistence of welding quality measurements (e.g., nugget width) based on process parameters to efficiently monitor product quality. The proposed method provides engineering efficiency and cost saving benefit through reduction of physical testing required for weldability and verification. The developed method is applied to the real-world welding process. |
| Tasks | |
| Published | 2019-02-24 |
| URL | http://arxiv.org/abs/1902.08869v1 |
| http://arxiv.org/pdf/1902.08869v1.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-method-to-model-the-quality |
| Repo | |
| Framework | |
Sparse Regression and Adaptive Feature Generation for the Discovery of Dynamical Systems
| Title | Sparse Regression and Adaptive Feature Generation for the Discovery of Dynamical Systems |
| Authors | Chinmay S. Kulkarni |
| Abstract | We study the performance of sparse regression methods and propose new techniques to distill the governing equations of dynamical systems from data. We first look at the generic methodology of learning interpretable equation forms from data, proposed by Brunton et al., followed by performance of LASSO for this purpose. We then propose a new algorithm that uses the dual of LASSO optimization for higher accuracy and stability. In the second part, we propose a novel algorithm that learns the candidate function library in a completely data-driven manner to distill the governing equations of the dynamical system. This is achieved via sequentially thresholded ridge regression (STRidge) over a orthogonal polynomial space. The performance of the three discussed methods is illustrated by looking the Lorenz 63 system and the quadratic Lorenz system. |
| Tasks | |
| Published | 2019-02-07 |
| URL | http://arxiv.org/abs/1902.02719v2 |
| http://arxiv.org/pdf/1902.02719v2.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-regression-and-adaptive-feature |
| Repo | |
| Framework | |
Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model
| Title | Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model |
| Authors | Alexander R. Fabbri, Irene Li, Tianwei She, Suyi Li, Dragomir R. Radev |
| Abstract | Automatic generation of summaries from multiple news articles is a valuable tool as the number of online publications grows rapidly. Single document summarization (SDS) systems have benefited from advances in neural encoder-decoder model thanks to the availability of large datasets. However, multi-document summarization (MDS) of news articles has been limited to datasets of a couple of hundred examples. In this paper, we introduce Multi-News, the first large-scale MDS news dataset. Additionally, we propose an end-to-end model which incorporates a traditional extractive summarization model with a standard SDS model and achieves competitive results on MDS datasets. We benchmark several methods on Multi-News and release our data and code in hope that this work will promote advances in summarization in the multi-document setting. |
| Tasks | Document Summarization, Multi-Document Summarization |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01749v3 |
| https://arxiv.org/pdf/1906.01749v3.pdf | |
| PWC | https://paperswithcode.com/paper/multi-news-a-large-scale-multi-document |
| Repo | |
| Framework | |
Predicting Different Types of Conversions with Multi-Task Learning in Online Advertising
| Title | Predicting Different Types of Conversions with Multi-Task Learning in Online Advertising |
| Authors | Junwei Pan, Yizhi Mao, Alfonso Lobos Ruiz, Yu Sun, Aaron Flores |
| Abstract | Conversion prediction plays an important role in online advertising since Cost-Per-Action (CPA) has become one of the primary campaign performance objectives in the industry. Unlike click prediction, conversions have different types in nature, and each type may be associated with different decisive factors. In this paper, we formulate conversion prediction as a multi-task learning problem, so that the prediction models for different types of conversions can be learned together. These models share feature representations, but have their specific parameters, providing the benefit of information-sharing across all tasks. We then propose Multi-Task Field-weighted Factorization Machine (MT-FwFM) to solve these tasks jointly. Our experiment results show that, compared with two state-of-the-art models, MT-FwFM improve the AUC by 0.74% and 0.84% on two conversion types, and the weighted AUC across all conversion types is also improved by 0.50%. |
| Tasks | Multi-Task Learning |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10235v2 |
| https://arxiv.org/pdf/1907.10235v2.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-different-types-of-conversions |
| Repo | |
| Framework | |
