Datasets that boosted state-of-the-art solutions for Question Answering (QA) systems prove that it is possible to ask questions in natural language manner. However, users are still used to query-like systems where they type in keywords to search for answer. In this study we validate which parts of questions are essential for obtaining valid answer. In order to conclude that, we take advantage of LIME - a framework that explains prediction by local approximation. We find that grammar and natural language is disregarded by QA. State-of-the-art model can answer properly even if 'asked' only with a few words with high coefficients calculated with LIME. According to our knowledge, it is the first time that QA model is being explained by LIME.
In this paper we introduce vSTS, a new dataset for measuring textual similarity of sentences using multimodal information. The dataset is comprised by images along with its respectively textual captions. We describe the dataset both quantitatively and qualitatively, and claim that it is a valid gold standard for measuring automatic multimodal textual similarity systems. We also describe the initial experiments combining the multimodal information.
In resource-constrained environments, one can employ spatial multiplexing cameras to acquire a small number of measurements of a scene, and perform effective reconstruction or high-level inference using purely data-driven neural networks. However, once trained, the measurement matrix and the network are valid only for a single measurement rate (MR) chosen at training time. To overcome this drawback, we answer the following question: How can we jointly design the measurement operator and the reconstruction/inference network so that the system can operate over a \textit{range} of MRs? To this end, we present a novel training algorithm, for learning \textbf{\textit{rate-adaptive}} networks. Using standard datasets, we demonstrate that, when tested over a range of MRs, a rate-adaptive network can provide high quality reconstruction over a the entire range, resulting in up to about 15 dB improvement over previous methods, where the network is valid for only one MR. We demonstrate the effectiveness of our approach for sample-efficient object tracking where video frames are acquired at dynamically varying MRs. We also extend this algorithm to learn the measurement operator in conjunction with image recognition networks. Experiments on MNIST and CIFAR-10 confirm the applicability of our algorithm to different tasks.
Molecular optimization aims to discover novel molecules with desirable properties. Two fundamental challenges are: (i) it is not trivial to generate valid molecules in a controllable way due to hard chemical constraints such as the valency conditions, and (ii) it is often costly to evaluate a property of a novel molecule, and therefore, the number of property evaluations is limited. These challenges are to some extent alleviated by a combination of a variational autoencoder (VAE) and Bayesian optimization (BO). VAE converts a molecule into/from its latent continuous vector, and BO optimizes a latent continuous vector (and its corresponding molecule) within a limited number of property evaluations. While the most recent work, for the first time, achieved 100% validity, its architecture is rather complex due to auxiliary neural networks other than VAE, making it difficult to train. This paper presents a molecular hypergraph grammar variational autoencoder (MHG-VAE), which uses a single VAE to achieve 100% validity. Our idea is to develop a graph grammar encoding the hard chemical constraints, called molecular hypergraph grammar (MHG), which guides VAE to always generate valid molecules. We also present an algorithm to construct MHG from a set of molecules.
Deep generative models have achieved remarkable success in various data domains, including images, time series, and natural languages. There remain, however, substantial challenges for combinatorial structures, including graphs. One of the key challenges lies in the difficulty of ensuring semantic validity in context. For examples, in molecular graphs, the number of bonding-electron pairs must not exceed the valence of an atom; whereas in protein interaction networks, two proteins may be connected only when they belong to the same or correlated gene ontology terms. These constraints are not easy to be incorporated into a generative model. In this work, we propose a regularization framework for variational autoencoders as a step toward semantic validity. We focus on the matrix representation of graphs and formulate penalty terms that regularize the output distribution of the decoder to encourage the satisfaction of validity constraints. Experimental results confirm a much higher likelihood of sampling valid graphs in our approach, compared with others reported in the literature.
Collaborative reasoning for understanding image-question pairs is a very critical but underexplored topic in interpretable visual question answering systems. Although very recent studies have attempted to use explicit compositional processes to assemble multiple subtasks embedded in questions, their models heavily rely on annotations or handcrafted rules to obtain valid reasoning processes, which leads to either heavy workloads or poor performance on compositional reasoning. In this paper, to better align image and language domains in diverse and unrestricted cases, we propose a novel neural network model that performs global reasoning on a dependency tree parsed from the question; thus, our model is called a parse-tree-guided reasoning network (PTGRN). This network consists of three collaborative modules: i) an attention module that exploits the local visual evidence of each word parsed from the question, ii) a gated residual composition module that composes the previously mined evidence, and iii) a parse-tree-guided propagation module that passes the mined evidence along the parse tree. Thus, PTGRN is capable of building an interpretable visual question answering (VQA) system that gradually derives image cues following question-driven parse-tree reasoning. Experiments on relational datasets demonstrate the superiority of PTGRN over current state-of-the-art VQA methods, and the visualization results highlight the explainable capability of our reasoning system.
Attention mechanisms are often used in deep neural networks for distantly supervised relation extraction (DS-RE) to distinguish valid from noisy instances. However, traditional 1-D vector attention models are insufficient for the learning of different contexts in the selection of valid instances to predict the relationship for an entity pair. To alleviate this issue, we propose a novel multi-level structured (2-D matrix) self-attention mechanism for DS-RE in a multi-instance learning (MIL) framework using bidirectional recurrent neural networks. In the proposed method, a structured word-level self-attention mechanism learns a 2-D matrix where each row vector represents a weight distribution for different aspects of an instance regarding two entities. Targeting the MIL issue, the structured sentence-level attention learns a 2-D matrix where each row vector represents a weight distribution on selection of different valid in-stances. Experiments conducted on two publicly available DS-RE datasets show that the proposed framework with a multi-level structured self-attention mechanism significantly outperform state-of-the-art baselines in terms of PR curves, P@N and F1 measures.
Well-known corner or local extrema feature based detectors such as FAST and DoG have achieved noticeable successes. However, detecting keypoints in the presence of blur has remained to be an unresolved issue. As a matter of fact, various kinds of blur (e.g., motion blur, out-of-focus, and space-variant) remarkably increase challenges for keypoint detection. As a result, those methods have limited performance. To settle this issue, we propose a blur-countering method for detecting valid keypoints for various types and degrees of blurred images. Specifically, we first present a distance metric for derivative distributions, which preserves the distinctiveness of patch pairs well under blur. We then model the asymmetry by utilizing the difference of squared eigenvalues based on the distance metric. To make it scale-robust, we also extend it to scale space. The proposed detector is efficient as the main computational cost is the square of derivatives at each pixel. Extensive visual and quantitative results show that our method outperforms current approaches under different types and degrees of blur. Without any parallelization, our implementation\footnote{We will make our code publicly available upon the acceptance.} achieves real-time performance for low-resolution images (e.g., $320\times240$ pixel).
Statistical significance testing plays an important role when drawing conclusions from experimental results in NLP papers. Particularly, it is a valuable tool when one would like to establish the superiority of one algorithm over another. This appendix complements the guide for testing statistical significance in NLP presented in \cite{dror2018hitchhiker} by proposing valid statistical tests for the common tasks and evaluation measures in the field.
In a dialog, there can be multiple valid next utterances at any point. The present end-to-end neural methods for dialog do not take this into account. They learn with the assumption that at any time there is only one correct next utterance. In this work, we focus on this problem in the goal-oriented dialog setting where there are different paths to reach a goal. We propose a new method, that uses a combination of supervised learning and reinforcement learning approaches to address this issue. We also propose a new and more effective testbed, permuted-bAbI dialog tasks, by introducing multiple valid next utterances to the original-bAbI dialog tasks, which allows evaluation of goal-oriented dialog systems in a more realistic setting. We show that there is a significant drop in performance of existing end-to-end neural methods from 81.5% per-dialog accuracy on original-bAbI dialog tasks to 30.3% on permuted-bAbI dialog tasks. We also show that our proposed method improves the performance and achieves 47.3% per-dialog accuracy on permuted-bAbI dialog tasks.
Question categorization and expert retrieval methods have been crucial for information organization and accessibility in community question & answering (CQA) platforms. Research in this area, however, has dealt with only the text modality. With the increasing multimodal nature of web content, we focus on extending these methods for CQA questions accompanied by images. Specifically, we leverage the success of representation learning for text and images in the visual question answering (VQA) domain, and adapt the underlying concept and architecture for automated category classification and expert retrieval on image-based questions posted on Yahoo! Chiebukuro, the Japanese counterpart of Yahoo! Answers. To the best of our knowledge, this is the first work to tackle the multimodality challenge in CQA, and to adapt VQA models for tasks on a more ecologically valid source of visual questions. Our analysis of the differences between visual QA and community QA data drives our proposal of novel augmentations of an attention method tailored for CQA, and use of auxiliary tasks for learning better grounding features. Our final model markedly outperforms the text-only and VQA model baselines for both tasks of classification and expert retrieval on real-world multimodal CQA data.
This paper focuses on semantic task planning, i.e., predicting a sequence of actions toward accomplishing a specific task under a certain scene, which is a new problem in computer vision research. The primary challenges are how to model task-specific knowledge and how to integrate this knowledge into the learning procedure. In this work, we propose training a recurrent long short-term memory (LSTM) network to address this problem, i.e., taking a scene image (including pre-located objects) and the specified task as input and recurrently predicting action sequences. However, training such a network generally requires large numbers of annotated samples to cover the semantic space (e.g., diverse action decomposition and ordering). To overcome this issue, we introduce a knowledge and-or graph (AOG) for task description, which hierarchically represents a task as atomic actions. With this AOG representation, we can produce many valid samples (i.e., action sequences according to common sense) by training another auxiliary LSTM network with a small set of annotated samples. Furthermore, these generated samples (i.e., task-oriented action sequences) effectively facilitate training of the model for semantic task planning. In our experiments, we create a new dataset that contains diverse daily tasks and extensively evaluate the effectiveness of our approach.
This paper introduces a quantitative evaluation of filters that seek to separate an image into its large-scale variations, the base layer, and its fine-scale variations, the detail layer. Such methods have proliferated with the development of HDR imaging and the proposition of many new tone-mapping operators. We argue that an objective quality measurement for all methods can be based on their artifacts. To this aim, the four main recurrent artifacts are described and mathematically characterized. Among them two are classic, the luminance halo and the staircase effect, but we show the relevance of two more, the contrast halo and the compartmentalization effect. For each of these artifacts we design a test-pattern and its attached measurement formula. Then we fuse these measurements into a single quality mark, and obtain in that way a ranking method valid for all filters performing a base+detail decomposition. This synthetic ranking is applied to seven filters representative of the literature and shown to agree with expert artifact rejection criteria.
In social network analysis, the observed data is usually some social behavior, such as the formation of groups, rather than an explicit network structure. Zhao and Weko (2017) propose a model-based approach called the hub model to infer implicit networks from grouped observations. The hub model assumes independence between groups, which sometimes is not valid in practice. In this article, we generalize the idea of the hub model into the case of grouped observations with temporal dependence. As in the hub model, we assume that the group at each time point is gathered by one leader. Unlike in the hub model, the group leaders are not sampled independently but follow a Markov chain, and other members in adjacent groups can also be correlated. An expectation-maximization (EM) algorithm is developed for this model and a polynomial-time algorithm is proposed for the E-step. The performance of the new model is evaluated under different simulation settings. We apply this model to a data set of the Kibale Chimpanzee Project.
This paper proposes an original problem of \emph{stereo computation from a single mixture image}-- a challenging problem that had not been researched before. The goal is to separate (\ie, unmix) a single mixture image into two constitute image layers, such that the two layers form a left-right stereo image pair, from which a valid disparity map can be recovered. This is a severely illposed problem, from one input image one effectively aims to recover three (\ie, left image, right image and a disparity map). In this work we give a novel deep-learning based solution, by jointly solving the two subtasks of image layer separation as well as stereo matching. Training our deep net is a simple task, as it does not need to have disparity maps. Extensive experiments demonstrate the efficacy of our method.
Deep learning approaches have been rapidly adopted across a wide range of fields because of their accuracy and flexibility, but require large labeled training datasets. This presents a fundamental problem for applications with limited, expensive, or private data (i.e. small data), such as human pose and behavior estimation/tracking which could be highly personalized. In this paper, we present a semi-supervised data augmentation approach that can synthesize large scale labeled training datasets using 3D graphical engines based on a physically-valid low dimensional pose descriptor. To evaluate the performance of our synthesized datasets in training deep learning-based models, we generated a large synthetic human pose dataset, called ScanAva using 3D scans of only 7 individuals based on our proposed augmentation approach. A state-of-the-art human pose estimation deep learning model then was trained from scratch using our ScanAva dataset and could achieve the pose estimation accuracy of 91.2% at PCK0.5 criteria after applying an efficient domain adaptation on the synthetic images, in which its pose estimation accuracy was comparable to the same model trained on large scale pose data from real humans such as MPII dataset and much higher than the model trained on other synthetic human dataset such as SURREAL.
In data science, determining proximity between observations is critical to many downstream analyses such as clustering, information retrieval and classification. However, when the underlying structure of the data probability space is unclear, the function used to compute similarity between data points is often arbitrarily chosen. Here, we present a novel concept of proximity, Semblance, that uses the empirical distribution across all observations to inform the similarity between each pair. The advantage of Semblance lies in its distribution free formulation and its ability to detect niche features by placing greater emphasis on similarity between observation pairs that fall at the outskirts of the data distribution, as opposed to those that fall towards the center. We prove that Semblance is a valid Mercer kernel, thus allowing its principled use in kernel based learning machines. Semblance can be applied to any data modality, and we demonstrate its consistently improved performance against conventional methods through simulations and three real case studies from very different applications, viz. cell type classification using single cell RNA sequencing, selecting predictors of positive return on real estate investments, and image compression.
We develop the setting of sequential prediction based on shifting experts and on a "smooth" version of the method of specialized experts. To aggregate experts predictions, we use the AdaHedge algorithm, which is a version of the Hedge algorithm with adaptive learning rate, and extend it by the meta-algorithm Fixed Share. Due to this, we combine the advantages of both algorithms: (1) we use the shifting regret which is a more optimal characteristic of the algorithm; (2) regret bounds are valid in the case of signed unbounded losses of the experts. Also, (3) we incorporate in this scheme a "smooth" version of the method of specialized experts which allows us to make more flexible and accurate predictions. All results are obtained in the adversarial setting -- no assumptions are made about the nature of data source. We present results of numerical experiments for short-term forecasting of electricity consumption based on a real data.
Universally valid ground truth is almost impossible to obtain or would come at a very high cost. For supervised learning without universally valid ground truth, a recommended approach is applying crowdsourcing: Gathering a large data set annotated by multiple individuals of varying possibly expertise levels and inferring the ground truth data to be used as labels to train the classifier. Nevertheless, due to the sensitivity of the problem at hand (e.g. mitosis detection in breast cancer histology images), the obtained data needs verification and proper assessment before being used for classifier training. Even in the context of organic computing systems, an indisputable ground truth might not always exist. Therefore, it should be inferred through the aggregation and verification of the local knowledge of each autonomous agent.
Random forests are a powerful method for non-parametric regression, but are limited in their ability to fit smooth signals, and can show poor predictive performance in the presence of strong, smooth effects. Taking the perspective of random forests as an adaptive kernel method, we pair the forest kernel with a local linear regression adjustment to better capture smoothness. The resulting procedure, local linear forests, enables us to improve on asymptotic rates of convergence for random forests with smooth signals, and provides substantial gains in accuracy on both real and simulated data. We prove a central limit theorem valid under regularity conditions on the forest and smoothness constraints, and propose a computationally efficient construction for confidence intervals. Moving to a causal inference application, we discuss the merits of local regression adjustments for heterogeneous treatment effect estimation, and give an example on a dataset exploring the effect word choice has on attitudes to the social safety net. Last, we include simulation results on real and generated data.