Speech recognition is becoming prevalent in daily life. However, due to the similar semantic context of the entities and the overlap of Chinese pronunciation, the pronoun homophone, especially "他/她/它 (he/she/i...
详细信息
Entity linking refers to linking a string in a text to corresponding entities in a knowledge base through candidate entity generation and candidate entity *** is of great significance to some NLP(natural language proc...
详细信息
Entity linking refers to linking a string in a text to corresponding entities in a knowledge base through candidate entity generation and candidate entity *** is of great significance to some NLP(natural language processing)tasks,such as question *** English entity linking,Chinese entity linking requires more consideration due to the lack of spacing and capitalization in text sequences and the ambiguity of characters and words,which is more evident in certain *** Chinese domains,such as industry,the generated candidate entities are usually composed of long strings and are heavily *** addition,the meanings of the words that make up industrial entities are sometimes *** semantic space is a subspace of the general word embedding space,and thus each entity word needs to get its exact ***,we propose two schemes to achieve better Chinese entity ***,we implement an ngram based candidate entity generation method to increase the recall rate and reduce the nesting ***,we enhance the corresponding candidate entity ranking mechanism by introducing sense *** the contradiction between the ambiguity of word vectors and the single sense of the industrial domain,we design a sense embedding model based on graph clustering,which adopts an unsupervised approach for word sense induction and learns sense representation in conjunction with *** test the embedding quality of our approach on classical datasets and demonstrate its disambiguation ability in general *** confirm that our method can better learn candidate entities’fundamental laws in the industrial domain and achieve better performance on entity linking through experiments.
Many systems have been built to employ the delta-based iterative execution model to support iterative algorithms on distributed platforms by exploiting the sparse computational dependencies between data items of these...
详细信息
Many systems have been built to employ the delta-based iterative execution model to support iterative algorithms on distributed platforms by exploiting the sparse computational dependencies between data items of these iterative algorithms in a synchronous or asynchronous approach. However, for large-scale iterative algorithms, existing synchronous solutions suffer from slow convergence speed and load imbalance, because of the strict barrier between iterations;while existing asynchronous approaches induce excessive redundant communication and computation cost as a result of being barrier-free. In view of the performance trade-off between these two approaches, this paper designs an efficient execution manager, called Aiter-R, which can be integrated into existing delta-based iterative processing systems to efficiently support the execution of delta-based iterative algorithms, by using our proposed group-based iterative execution approach. It can efficiently and correctly explore the middle ground of the two extremes. A heuristic scheduling algorithm is further proposed to allow an iterative algorithm to adaptively choose its trade-off point so as to achieve the maximum efficiency. Experimental results show that Aiter-R strikes a good balance between the synchronous and asynchronous policies and outperforms state-of-the-art solutions. It reduces the execution time by up to 54.1% and 84.6% in comparison with existing asynchronous and the synchronous models, respectively.
Real-world networks,such as social networks,cryptocurrency networks,and e-commerce networks,always have occurrence time of interactions between *** networks are typically modeled as temporal *** cohesive subgraphs fro...
详细信息
Real-world networks,such as social networks,cryptocurrency networks,and e-commerce networks,always have occurrence time of interactions between *** networks are typically modeled as temporal *** cohesive subgraphs from temporal graphs is practical and essential in numerous data mining applications,since mining cohesive subgraphs gets insights into the time-varying nature of temporal ***,existing studies on mining cohesive subgraphs,such as Densest-Exact and k-truss,are mainly tailored for static graphs(whose edges have no temporal information).Therefore,those cohesive subgraph models cannot indicate both the temporal and the structural characteristics of *** this end,we explore the model of cohesive temporal subgraphs by incorporating both the evolving and the structural characteristics of temporal ***,the volume of time intervals in a temporal network is *** a result,the time complexity of mining temporal cohesive subgraphs is *** efficiently address the problem,we first mine the temporal density distribution of temporal *** by the distribution,we can safely prune many unqualified time intervals with the linear time ***,the remaining time intervals where cohesive temporal subgraphs fall in are examined using the greedy *** results of the experiments on nine real-world temporal graphs indicate that our model outperforms state-of-the-art solutions in efficiency and ***,our model only takes less than two minutes on a million-vertex DBLP and has the highest overall average ranking in EDB and TC metrics.
Out-of-distribution (OOD) detection is crucial for developing trustworthy and reliable machine learning systems. Recent advances in training with auxiliary OOD data demonstrate efficacy in enhancing detection capabili...
详细信息
Accurate load forecasting of data centers is an important supporting means for them to participate in demand response or power market. In view of the problems such as large errors and poor stability existing in curren...
详细信息
ISBN:
(数字)9798350373479
ISBN:
(纸本)9798350373486
Accurate load forecasting of data centers is an important supporting means for them to participate in demand response or power market. In view of the problems such as large errors and poor stability existing in current load forecasting methods of data centers, and considering the differences of cooling loads in different seasons, in this paper, a LSTM-Attention fusion neural network model based on Attention mechanism is proposed for the net load prediction of data centers. LSTM neural network is used to extract the time series characteristics of data center loads, and then the Attention mechanism is added to capture the fluctuation characteristics to improve the prediction accuracy. Based on the data set provided by the National Renewable Energy laboratory (NREL), seasonal forecasting is carried out in this paper. The results show that the introduction of the Attention mechanism in the model can effectively improve the accuracy of data center load forecasting, and the model has transferability.
In recent years, Neural Architecture Search (NAS) has emerged as a promising approach for automatically discovering superior model architectures for deep Graph Neural Networks (GNNs). Different methods have paid atten...
详细信息
Evaluating and enhancing the general capabilities of large language models (LLMs) has been an important research topic. Graph is a common data structure in the real world, and understanding graph data is a crucial par...
详细信息
Recently, the bias-related issues in GNN-based link prediction have raised widely spread concerns. In this paper, we emphasize the bias on links across different node clusters, which we call cross-links, after conside...
Recently, the bias-related issues in GNN-based link prediction have raised widely spread concerns. In this paper, we emphasize the bias on links across different node clusters, which we call cross-links, after considering its significance in both easing information cocoons and preserving graph connectivity. Instead of following the objective-oriented mechanism in prior works with compromised utility, we empirically find that existing GNN models face severe data bias between internal-links (links within the same cluster) and cross-links, and this inspires us to rethink the bias issue on cross-links from a data perspective. Specifically, we design a simple yet effective twin-structure framework, which can be easily applied to most GNNs to mitigate the bias as well as boost their utility in an end-to-end manner. The basic idea is to generate debiased node embeddings as demonstrations and fuse them into the embeddings of original GNNs. In particular, we learn debiased node embeddings with the help of augmented supervision signals, and a novel dynamic training strategy is designed to effectively fuse debiased node embeddings with the original node embeddings. Experiments on three datasets with six common GNNs show that our framework can not only alleviate the bias between internal-links and cross-links but also boost the overall accuracy. Comparisons with other state-of-the-art methods also verify the superiority of our method.
The rapid adoption of power Internet of Things (PIoT) systems has made security a critical concern, particularly as existing certificateless authentication and key agreement (CL-AKA) protocols face three fundamental l...
详细信息
暂无评论