While the recent tree-based neural models have demonstrated promising results in generating solution expression for the math word problem (MWP), most of these models do not capture the relationships and order information among the quantities well. This results in poor quantity representations and incorrect solution expressions. In this paper, we propose Graph2Tree, a novel deep learning architecture that combines the merits of the graph-based encoder and tree-based decoder to generate better solution expressions. Included in our Graph2Tree framework are two graphs, namely the Quantity Cell Graph and Quantity Comparison Graph, which are designed to address limitations of existing methods by effectively representing the relationships and order information among the quantities in MWPs. We conduct extensive experiments on two available datasets. Our experiment results show that Graph2Tree outperforms the state-of-the-art baselines on two benchmark datasets significantly. We also discuss case studies and empirically examine Graph2Tree's effectiveness in translating the MWP text into solution expressions 1 .
In this paper, we propose a novel approach to video captioning based on adversarial learning and Long-Short Term Memory (LSTM). With this solution concept we aim at compensating for the deficiencies of LSTM-based video captioning methods that generally show potential to effectively handle temporal nature of video data when generating captions, but that also typically suffer from exponential error accumulation. Specifically, we adopt a standard Generative Adversarial Network (GAN) architecture, characterized by an interplay of two competing processes: a "generator", which generates textual sentences given the visual content of a video, and a "discriminator" which controls the accuracy of the generated sentences. The discriminator acts as an "adversary" towards the generator and with its controlling mechanism helps the generator to become more accurate. For the generator module, we take an existing video captioning concept using LSTM network. For the discriminator, we propose a novel realization specifically tuned for the video captioning problem and taking both the sentences and video features as input. This leads to our proposed LSTM-GAN system architecture, for which we show experimentally to significantly outperform the existing methods on standard public datasets.
Video captioning has been attracting broad research attention in multimedia community. However, most existing approaches either ignore temporal information among video frames or just employ local contextual temporal knowledge. In this work, we propose a novel video captioning framework, termed as Bidirectional Long-Short Term Memory (BiLSTM), which deeply captures bidirectional global temporal structure in video. Specifically, we first devise a joint visual modelling approach to encode video data by combining a forward LSTM pass, a backward LSTM pass, together with visual features from Convolutional Neural Networks (CNNs). Then, we inject the derived video representation into the subsequent language model for initialization. The benefits are in two folds: 1) comprehensively preserving sequential and visual information; and 2) adaptively learning dense visual features and sparse semantic representations for videos and sentences, respectively. We verify the effectiveness of our proposed video captioning framework on a commonlyused benchmark, i.e., Microsoft Video Description (MSVD) corpus, and the experimental results demonstrate that the superiority of the proposed approach as compared to several state-of-the-art methods.
Parkinson's disease (PD) is a progressive neurodegenerative disease characterized by motor and nonmotor signs and symptoms. To date, many studies of PD have focused on its cardinal motor symptoms. To study the nonmotor signs of early PD, we investigated the reactions solicited by heat pain stimuli in early untreated PD patients without pain using fMRI. The activation patterns of contact heat stimuli (51°C) were assessed in 14 patients and 17 age- and sex-matched healthy controls. Patients with PD showed significant decreases in activation of the superior temporal gyrus (STG) and insula compared with controls. In addition, a significant relationship between activation of the insula and STG and the pain scores was observed in healthy controls but not in PD. This study provided further support that the insula and STG are important parts of the somatosensory circuitry recruited during the period of pain. The hypoactivity of the STG and insula in PD implied that functions including affective, cognitive, and sensory-discriminative processes, which are associated with the insula and STG, were disturbed. This finding supports the view that leaving early PD untreated could be tied directly to central nervous system dysfunction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.