Paper Group NANR 31
Adaptive GNN for Image Analysis and Editing. Leveraging Non-Conversational Tasks for Low Resource Slot Filling: Does it help?. Multi-Task Learning of System Dialogue Act Selection for Supervised Pretraining of Goal-Oriented Dialogue Policies. Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge Bases. Atlas of …
Adaptive GNN for Image Analysis and Editing
| Title | Adaptive GNN for Image Analysis and Editing |
| Authors | Lingyu Liang, Lianwen Jin, Yong Xu |
| Abstract | Graph neural network (GNN) has powerful representation ability, but optimal configurations of GNN are non-trivial to obtain due to diversity of graph structure and cascaded nonlinearities. This paper aims to understand some properties of GNN from a computer vision (CV) perspective. In mathematical analysis, we propose an adaptive GNN model by recursive definition, and derive its relation with two basic operations in CV: filtering and propagation operations. The proposed GNN model is formulated as a label propagation system with guided map, graph Laplacian and node weight. It reveals that 1) the guided map and node weight determine whether a GNN leads to filtering or propagation diffusion, and 2) the kernel of graph Laplacian controls diffusion pattern. In practical verification, we design a new regularization structure with guided feature to produce GNN-based filtering and propagation diffusion to tackle the ill-posed inverse problems of quotient image analysis (QIA), which recovers the reflectance ratio as a signature for image analysis or adjustment. A flexible QIA-GNN framework is constructed to achieve various image-based editing tasks, like face illumination synthesis and low-light image enhancement. Experiments show the effectiveness of the QIA-GNN, and provide new insights of GNN for image analysis and editing. |
| Tasks | Image Enhancement, Low-Light Image Enhancement |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8622-adaptive-gnn-for-image-analysis-and-editing |
| http://papers.nips.cc/paper/8622-adaptive-gnn-for-image-analysis-and-editing.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-gnn-for-image-analysis-and-editing |
| Repo | |
| Framework | |
Leveraging Non-Conversational Tasks for Low Resource Slot Filling: Does it help?
| Title | Leveraging Non-Conversational Tasks for Low Resource Slot Filling: Does it help? |
| Authors | Samuel Louvan, Bernardo Magnini |
| Abstract | Slot filling is a core operation for utterance understanding in task-oriented dialogue systems. Slots are typically domain-specific, and adding new domains to a dialogue system involves data and time-intensive processes. A popular technique to address the problem is transfer learning, where it is assumed the availability of a large slot filling dataset for the source domain, to be used to help slot filling on the target domain, with fewer data. In this work, instead, we propose to leverage source tasks based on semantically related non-conversational resources (e.g., semantic sequence tagging datasets), as they are both cheaper to obtain and reusable to several slot filling domains. We show that using auxiliary non-conversational tasks in a multi-task learning setup consistently improves low resource slot filling performance. |
| Tasks | Multi-Task Learning, Slot Filling, Task-Oriented Dialogue Systems, Transfer Learning |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5911/ |
| https://www.aclweb.org/anthology/W19-5911 | |
| PWC | https://paperswithcode.com/paper/leveraging-non-conversational-tasks-for-low |
| Repo | |
| Framework | |
Multi-Task Learning of System Dialogue Act Selection for Supervised Pretraining of Goal-Oriented Dialogue Policies
| Title | Multi-Task Learning of System Dialogue Act Selection for Supervised Pretraining of Goal-Oriented Dialogue Policies |
| Authors | Sarah McLeod, Ivana Kruijff-Korbayova, Bernd Kiefer |
| Abstract | This paper describes the use of Multi-Task Neural Networks (NNs) for system dialogue act selection. These models leverage the representations learned by the Natural Language Understanding (NLU) unit to enable robust initialization/bootstrapping of dialogue policies from medium sized initial data sets. We evaluate the models on two goal-oriented dialogue corpora in the travel booking domain. Results show the proposed models improve over models trained without knowledge of NLU tasks. |
| Tasks | Multi-Task Learning |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5947/ |
| https://www.aclweb.org/anthology/W19-5947 | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-of-system-dialogue-act |
| Repo | |
| Framework | |
Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge Bases
| Title | Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge Bases |
| Authors | V Thejas, Abhijeet Gupta, Sebastian Pad{'o} |
| Abstract | Collaboratively constructed knowledge bases play an important role in information systems, but are essentially always incomplete. Thus, a large number of models has been developed for Knowledge Base Completion, the task of predicting new attributes of entities given partial descriptions of these entities. Virtually all of these models either concentrate on numeric attributes ({\textless}Italy,GDP,2T{$}{\textgreater}) or they concentrate on categorical attributes ({\textless}Tim Cook,chairman,Apple{\textgreater}). In this paper, we propose a simple feed-forward neural architecture to jointly predict numeric and categorical attributes based on embeddings learned from textual occurrences of the entities in question. Following insights from multi-task learning, our hypothesis is that due to the correlations among attributes of different kinds, joint prediction improves over separate prediction. Our experiments on seven FreeBase domains show that this hypothesis is true of the two attribute types: we find substantial improvements for numeric attributes in the joint model, while performance remains largely unchanged for categorical attributes. Our analysis indicates that this is the case because categorical attributes, many of which describe membership in various classes, provide useful {`}background knowledge{'} for numeric prediction, while this is true to a lesser degree in the inverse direction. | |
| Tasks | Knowledge Base Completion, Multi-Task Learning |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1137/ |
| https://www.aclweb.org/anthology/R19-1137 | |
| PWC | https://paperswithcode.com/paper/text-based-joint-prediction-of-numeric-and |
| Repo | |
| Framework | |
Atlas of Digital Pathology: A Generalized Hierarchical Histological Tissue Type-Annotated Database for Deep Learning
| Title | Atlas of Digital Pathology: A Generalized Hierarchical Histological Tissue Type-Annotated Database for Deep Learning |
| Authors | Mahdi S. Hosseini, Lyndon Chan, Gabriel Tse, Michael Tang, Jun Deng, Sajad Norouzi, Corwyn Rowsell, Konstantinos N. Plataniotis, Savvas Damaskinos |
| Abstract | In recent years, computer vision techniques have made large advances in image recognition and been applied to aid radiological diagnosis. Computational pathology aims to develop similar tools for aiding pathologists in diagnosing digitized histopathological slides, which would improve diagnostic accuracy and productivity amidst increasing workloads. However, there is a lack of publicly-available databases of (1) localized patch-level images annotated with (2) a large range of Histological Tissue Type (HTT). As a result, computational pathology research is constrained to diagnosing specific diseases or classifying tissues from specific organs, and cannot be readily generalized to handle unexpected diseases and organs. In this paper, we propose a new digital pathology database, the “Atlas of Digital Pathology” (or ADP), which comprises of 17,668 patch images extracted from 100 slides annotated with up to 57 hierarchical HTTs. Our data is generalized to different tissue types across different organs and aims to provide training data for supervised multi-label learning of patch-level HTT in a digitized whole slide image. We demonstrate the quality of our image labels through pathologist consultation and by training three state-of-the-art neural networks on tissue type classification. Quantitative results support the visually consistency of our data and we demonstrate a tissue type-based visual attention aid as a sample tool that could be developed from our database. |
| Tasks | Multi-Label Learning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Hosseini_Atlas_of_Digital_Pathology_A_Generalized_Hierarchical_Histological_Tissue_Type-Annotated_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Hosseini_Atlas_of_Digital_Pathology_A_Generalized_Hierarchical_Histological_Tissue_Type-Annotated_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/atlas-of-digital-pathology-a-generalized |
| Repo | |
| Framework | |
Progressive Teacher-Student Learning for Early Action Prediction
| Title | Progressive Teacher-Student Learning for Early Action Prediction |
| Authors | Xionghui Wang, Jian-Fang Hu, Jian-Huang Lai, Jianguo Zhang, Wei-Shi Zheng |
| Abstract | The goal of early action prediction is to recognize actions from partially observed videos with incomplete action executions, which is quite different from action recognition. Predicting early actions is very challenging since the partially observed videos do not contain enough action information for recognition. In this paper, we aim at improving early action prediction by proposing a novel teacher-student learning framework. Our framework involves a teacher model for recognizing actions from full videos, a student model for predicting early actions from partial videos, and a teacher-student learning block for distilling progressive knowledge from teacher to student, crossing different tasks. Extensive experiments on three public action datasets show that the proposed progressive teacher-student learning framework can consistently improve performance of early action prediction model. We have also reported the state-of-the-art performances for early action prediction on all of these sets. |
| Tasks | Temporal Action Localization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Progressive_Teacher-Student_Learning_for_Early_Action_Prediction_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Progressive_Teacher-Student_Learning_for_Early_Action_Prediction_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/progressive-teacher-student-learning-for |
| Repo | |
| Framework | |
Dynamic Scene Deblurring With Parameter Selective Sharing and Nested Skip Connections
| Title | Dynamic Scene Deblurring With Parameter Selective Sharing and Nested Skip Connections |
| Authors | Hongyun Gao, Xin Tao, Xiaoyong Shen, Jiaya Jia |
| Abstract | Dynamic Scene deblurring is a challenging low-level vision task where spatially variant blur is caused by many factors, e.g., camera shake and object motion. Recent study has made significant progress. Compared with the parameter independence scheme [19] and parameter sharing scheme [33], we develop the general principle for constraining the deblurring network structure by proposing the generic and effective selective sharing scheme. Inside the subnetwork of each scale, we propose a nested skip connection structure for the nonlinear transformation modules to replace stacked convolution layers or residual blocks. Besides, we build a new large dataset of blurred/sharp image pairs towards better restoration quality. Comprehensive experimental results show that our parameter selective sharing scheme, nested skip connection structure, and the new dataset are all significant to set a new state-of-the-art in dynamic scene deblurring. |
| Tasks | Deblurring |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Gao_Dynamic_Scene_Deblurring_With_Parameter_Selective_Sharing_and_Nested_Skip_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Gao_Dynamic_Scene_Deblurring_With_Parameter_Selective_Sharing_and_Nested_Skip_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-scene-deblurring-with-parameter |
| Repo | |
| Framework | |
Coverage of Information Extraction from Sentences and Paragraphs
| Title | Coverage of Information Extraction from Sentences and Paragraphs |
| Authors | Simon Razniewski, Nitisha Jain, Paramita Mirza, Gerhard Weikum |
| Abstract | Scalar implicatures are language features that imply the negation of stronger statements, e.g., {``}She was married twice{''} typically implicates that she was not married thrice. In this paper we discuss the importance of scalar implicatures in the context of textual information extraction. We investigate how textual features can be used to predict whether a given text segment mentions all objects standing in a certain relationship with a certain subject. Preliminary results on Wikipedia indicate that this prediction is feasible, and yields informative assessments. | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1583/ |
| https://www.aclweb.org/anthology/D19-1583 | |
| PWC | https://paperswithcode.com/paper/coverage-of-information-extraction-from |
| Repo | |
| Framework | |
A biscriptual morphological transducer for Crimean Tatar
| Title | A biscriptual morphological transducer for Crimean Tatar |
| Authors | Francis M. Tyers, Jonathan Washington, Darya Kavitskaya, Memduh G{"o}k{\i}rmak, Nick Howell, Remziye Berberova |
| Abstract | |
| Tasks | |
| Published | 2019-02-01 |
| URL | https://www.aclweb.org/anthology/W19-6010/ |
| https://www.aclweb.org/anthology/W19-6010 | |
| PWC | https://paperswithcode.com/paper/a-biscriptual-morphological-transducer-for |
| Repo | |
| Framework | |
Finding Sami Cognates with a Character-Based NMT Approach
| Title | Finding Sami Cognates with a Character-Based NMT Approach |
| Authors | Mika H{"a}m{"a}l{"a}inen, Jack Rueter |
| Abstract | |
| Tasks | |
| Published | 2019-02-01 |
| URL | https://www.aclweb.org/anthology/W19-6006/ |
| https://www.aclweb.org/anthology/W19-6006 | |
| PWC | https://paperswithcode.com/paper/finding-sami-cognates-with-a-character-based |
| Repo | |
| Framework | |
Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels
| Title | Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels |
| Authors | Felix J.S. Bragman, Ryutaro Tanno, Sebastien Ourselin, Daniel C. Alexander, Jorge Cardoso |
| Abstract | The performance of multi-task learning in Convolutional Neural Networks (CNNs) hinges on the design of feature sharing between tasks within the architecture. The number of possible sharing patterns are combinatorial in the depth of the network and the number of tasks, and thus hand-crafting an architecture, purely based on the human intuitions of task relationships can be time-consuming and suboptimal. In this paper, we present a probabilistic approach to learning task-specific and shared representations in CNNs for multi-task learning. Specifically, we propose “stochastic filter groups” (SFG), a mechanism to assign convolution kernels in each layer to “specialist” and “generalist” groups, which are specific to and shared across different tasks, respectively. The SFG modules determine the connectivity between layers and the structures of task-specific and shared representations in the network. We employ variational inference to learn the posterior distribution over the possible grouping of kernels and network parameters. Experiments demonstrate the proposed method generalises across multiple tasks and shows improved performance over baseline methods. |
| Tasks | Multi-Task Learning |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Bragman_Stochastic_Filter_Groups_for_Multi-Task_CNNs_Learning_Specialist_and_Generalist_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Bragman_Stochastic_Filter_Groups_for_Multi-Task_CNNs_Learning_Specialist_and_Generalist_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-filter-groups-for-multi-task-cnns-1 |
| Repo | |
| Framework | |
Deep Joint-Semantics Reconstructing Hashing for Large-Scale Unsupervised Cross-Modal Retrieval
| Title | Deep Joint-Semantics Reconstructing Hashing for Large-Scale Unsupervised Cross-Modal Retrieval |
| Authors | Shupeng Su, Zhisheng Zhong, Chao Zhang |
| Abstract | Cross-modal hashing encodes the multimedia data into a common binary hash space in which the correlations among the samples from different modalities can be effectively measured. Deep cross-modal hashing further improves the retrieval performance as the deep neural networks can generate more semantic relevant features and hash codes. In this paper, we study the unsupervised deep cross-modal hash coding and propose Deep Joint-Semantics Reconstructing Hashing (DJSRH), which has the following two main advantages. First, to learn binary codes that preserve the neighborhood structure of the original data, DJSRH constructs a novel joint-semantics affinity matrix which elaborately integrates the original neighborhood information from different modalities and accordingly is capable to capture the latent intrinsic semantic affinity for the input multi-modal instances. Second, DJSRH later trains the networks to generate binary codes that maximally reconstruct above joint-semantics relations via the proposed reconstructing framework, which is more competent for the batch-wise training as it reconstructs the specific similarity value unlike the common Laplacian constraint merely preserving the similarity order. Extensive experiments demonstrate the significant improvement by DJSRH in various cross-modal retrieval tasks. |
| Tasks | Cross-Modal Retrieval |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Su_Deep_Joint-Semantics_Reconstructing_Hashing_for_Large-Scale_Unsupervised_Cross-Modal_Retrieval_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Su_Deep_Joint-Semantics_Reconstructing_Hashing_for_Large-Scale_Unsupervised_Cross-Modal_Retrieval_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-joint-semantics-reconstructing-hashing |
| Repo | |
| Framework | |
``Transforming’’ Delete, Retrieve, Generate Approach for Controlled Text Style Transfer
| Title | ``Transforming’’ Delete, Retrieve, Generate Approach for Controlled Text Style Transfer | |
| Authors | Akhilesh Sudhakar, Bhargav Upadhyay, Arjun Maheswaran |
| Abstract | Text style transfer is the task of transferring the style of text having certain stylistic attributes, while preserving non-stylistic or content information. In this work we introduce the Generative Style Transformer (GST) - a new approach to rewriting sentences to a target style in the absence of parallel style corpora. GST leverages the power of both, large unsupervised pre-trained language models as well as the Transformer. GST is a part of a larger {`}Delete Retrieve Generate{'} framework, in which we also propose a novel method of deleting style attributes from the source sentence by exploiting the inner workings of the Transformer. Our models outperform state-of-art systems across 5 datasets on sentiment, gender and political slant transfer. We also propose the use of the GLEU metric as an automatic metric of evaluation of style transfer, which we found to compare better with human ratings than the predominantly used BLEU score. | |
| Tasks | Style Transfer, Text Style Transfer |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1322/ |
| https://www.aclweb.org/anthology/D19-1322 | |
| PWC | https://paperswithcode.com/paper/transforming-delete-retrieve-generate-1 |
| Repo | |
| Framework | |
Pareto Meets Huber: Efficiently Avoiding Poor Minima in Robust Estimation
| Title | Pareto Meets Huber: Efficiently Avoiding Poor Minima in Robust Estimation |
| Authors | Christopher Zach, Guillaume Bourmaud |
| Abstract | Robust cost optimization is the task of fitting parameters to data points containing outliers. In particular, we focus on large-scale computer vision problems, such as bundle adjustment, where Non-Linear Least Square (NLLS) solvers are the current workhorse. In this context, NLLS-based state of the art algorithms have been designed either to quickly improve the target objective and find a local minimum close to the initial value of the parameters, or to have a strong ability to escape poor local minima. In this paper, we propose a novel algorithm relying on multi-objective optimization which allows to match those two properties. We experimentally demonstrate that our algorithm has an ability to escape poor local minima that is on par with the best performing algorithms with a faster decrease of the target objective. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zach_Pareto_Meets_Huber_Efficiently_Avoiding_Poor_Minima_in_Robust_Estimation_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zach_Pareto_Meets_Huber_Efficiently_Avoiding_Poor_Minima_in_Robust_Estimation_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/pareto-meets-huber-efficiently-avoiding-poor |
| Repo | |
| Framework | |
Deep Bayesian Natural Language Processing
| Title | Deep Bayesian Natural Language Processing |
| Authors | Jen-Tzung Chien |
| Abstract | This introductory tutorial addresses the advances in deep Bayesian learning for natural language with ubiquitous applications ranging from speech recognition to document summarization, text classification, text segmentation, information extraction, image caption generation, sentence generation, dialogue control, sentiment classification, recommendation system, question answering and machine translation, to name a few. Traditionally, {}deep learning{''} is taken to be a learning process where the inference or optimization is based on the real-valued deterministic model. The {}semantic structure{''} in words, sentences, entities, actions and documents drawn from a large vocabulary may not be well expressed or correctly optimized in mathematical logic or computer programs. The {``}distribution function{''} in discrete or continuous latent variable model for natural language may not be properly decomposed or estimated. This tutorial addresses the fundamentals of statistical models and neural networks, and focus on a series of advanced Bayesian models and deep models including hierarchical Dirichlet process, Chinese restaurant process, hierarchical Pitman-Yor process, Indian buffet process, recurrent neural network, long short-term memory, sequence-to-sequence model, variational auto-encoder, generative adversarial network, attention mechanism, memory-augmented neural network, skip neural network, stochastic neural network, predictive state neural network and policy neural network. We present how these models are connected and why they work for a variety of applications on symbolic and complex patterns in natural language. The variational inference and sampling method are formulated to tackle the optimization for complicated models. The word and sentence embeddings, clustering and co-clustering are merged with linguistic and semantic constraints. A series of case studies and domain applications are presented to tackle different issues in deep Bayesian processing, learning and understanding. At last, we will point out a number of directions and outlooks for future studies. | |
| Tasks | Document Summarization, Machine Translation, Question Answering, Sentence Embeddings, Sentiment Analysis, Speech Recognition, Text Classification |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-4006/ |
| https://www.aclweb.org/anthology/P19-4006 | |
| PWC | https://paperswithcode.com/paper/deep-bayesian-natural-language-processing |
| Repo | |
| Framework | |
