The existing emotion cause pair extraction models do not improve the performance of emotion cause pair extraction by incorporating external knowledge. In this work, we propose an emotion-cause pair extraction model ba...
详细信息
Coreference resolution aims at linking all mentions that refer to the same entity, which are widely adopted in many biomedical and bioinformatics tasks, such as biomedical knowledge graph construction and metabolic pa...
详细信息
ISBN:
(数字)9781665468190
ISBN:
(纸本)9781665468206
Coreference resolution aims at linking all mentions that refer to the same entity, which are widely adopted in many biomedical and bioinformatics tasks, such as biomedical knowledge graph construction and metabolic pathway integration. Many recent studies focus on improving neural model structures. However, we argue that a practical method that integrates commonsense knowledge can further improve coreference resolution performance, because commonsense delivers extra prior knowledge for reasoning and can enhance related representations, rather than naive mention-context occurrence modeling. In this work, we propose an effective method to integrate external commonsense knowledge into a neural coreference resolution model. Specially, a gated attention mechanism is employed in our method to leverage commonsense according to different contexts. By using ConceptNet as the knowledge base in three span-ranking backbone models, the models can yield significant performance gains on used datasets. We also achieve improvements in tasks of long-term mention detection and cross-sentence coreferences after incorporating knowledge.
Precise prediction of stock prices leads to more profits and more effective risk prevention, which is of great significance to both investors and regulators. Recent years, various kinds of information not directly-rel...
详细信息
Precise prediction of stock prices leads to more profits and more effective risk prevention, which is of great significance to both investors and regulators. Recent years, various kinds of information not directly-relevant with stock prices have received more attention, such as texts, images or connections. These external information has the potential of reflecting or influencing fluctuations, and thus, given the utilization of advanced analyzing techniques, the forecasting performance of stock prices could be promoted substantially. For instance, graph neural network models have expanded into many other disciplines including stock price prediction, and exhibited impressive representation learning ability. However, in stock markets, well-defined graphs are rarely seen and how to formulate the graph structures needed remains a challenging problem. Towards this end, this article presents a comprehensive overview of graph construction and graph learning in stock price prediction, by reviewing the existing studies, summarizing its general paradigm, special cases and proposing possible prospects. Our research not only systematically reveals the feasible ways of constructing graphs in financial markets, but also provides insights for further implementations of graph learning models into stock prediction tasks.
Biomedical relation extraction seeks to automatically extract biomedical relations from biomedical text, which plays an important role in biomedical studies. However, constructing high-quality biomedical annotation da...
详细信息
ISBN:
(数字)9781665468190
ISBN:
(纸本)9781665468206
Biomedical relation extraction seeks to automatically extract biomedical relations from biomedical text, which plays an important role in biomedical studies. However, constructing high-quality biomedical annotation data is not only time-consuming but also requires a high level of knowledge in the biomedical field. To alleviate this problem, Semi-supervised Biomedical Relation Extraction aims to extract relation facts from the limited labeled data and the more readily available unlabeled samples. Existing works can be roughly categorized as self-training methods and self-ensembling methods. The former aims to generate pseudo labels, which may lead to the gradual drift problem. The latter aims to encourage the output of one model to be consistent with the other model, where the acquisition of the model is tedious. To alleviate these issues, we propose a novel Uncertainty-Guided Mutual Consistency Training framework(UG-MCT) for semi-supervised Biomedical relation extraction. Specifically, our framework consists of two models with the same structure, which differ only when updating their weights, and then an intersecting pseudo-label mechanism is designed to convert the prediction discrepancies of the two models into mutual consistency training loss, thus promoting the consistency of model predictions. In addition, we utilize uncertainty as guided information to assist the model in focusing on the confident pseudo labels and mitigate the noise of inaccurate pseudo labeling during training. Thus, our model is very simple and efficient while mitigating the noise introduced by pseudo-labels. UG-MCT is evaluated on multiple datasets in different settings and the experimental results demonstrate that our method is highly effective in semi-supervised biomedical relation extraction compared to the state-of-the-art.
Visual question answering requires a system to provide an accurate natural language answer given an image and a natural language question. However, it is widely recognized that previous generic VQA methods often tend ...
详细信息
In this work, we address the challenging task of Generalized Referring Expression Comprehension (GREC). Compared to the classic Referring Expression Comprehension (REC) that focuses on single-target expressions, GREC ...
详细信息
Graph Neural Networks (GNNs) have been widely employed for semi-supervised node classification tasks on graphs. However, the performance of GNNs is significantly affected by label noise, that is, a small amount of inc...
详细信息
In this work, we address the challenging task of Generalized Referring Expression Comprehension (GREC). Compared to the classic Referring Expression Comprehension (REC) that focuses on single-target expressions, GREC ...
详细信息
The minimum weighted connected dominating set problem is a classical NP-hard problem with wide applications in practice. In this paper, an efficient local search algorithm is proposed to solve this problem. In this al...
详细信息
Convolutional Neural Networks (CNNs) have significantly advanced computer vision tasks, but their increasing complexity poses challenges for efficient inference, particularly on resource-constrained devices. We presen...
详细信息
ISBN:
(数字)9798331506209
ISBN:
(纸本)9798331506216
Convolutional Neural Networks (CNNs) have significantly advanced computer vision tasks, but their increasing complexity poses challenges for efficient inference, particularly on resource-constrained devices. We present DualConvNet, a novel CNN architecture that enhances inference efficiency through two key innovations: compressed convolutions and reparameterization. Compressed convolutions reduce computational complexity by selectively processing input channel subsets during both training and inference. For inference, we introduce a reparameterization technique that merges the multi-branch structure into a single, efficient operation, significantly improving speed. Experiments on CIFAR-10, CIFAR-100, and ImageNet-1k demonstrate DualConvNet’s effectiveness, consistently outperforming state-of-the-art models in both accuracy and inference speed. On the COCO dataset, DualConvNet shows competitive accuracy in object detection and instance segmentation tasks while substantially reducing GPU latency. Ablation studies validate the impact of our dual-strategy approach, revealing significant improvements in both accuracy and computational efficiency compared to alternative designs. These results demonstrate DualConvNet’s effectiveness in improving inference efficiency while maintaining high accuracy across various tasks and datasets, making it particularly suitable for real-time applications in resource-constrained scenarios.
暂无评论