Micro-nano Earth Observation Satellite(MEOS)constellation has the advantages of low construction cost,short revisit cycle,and high functional density,which is considered a promising solution for serving rapidly growin...Micro-nano Earth Observation Satellite(MEOS)constellation has the advantages of low construction cost,short revisit cycle,and high functional density,which is considered a promising solution for serving rapidly growing observation demands.The observation Scheduling Problem in the MEOS constellation(MEOSSP)is a challenging issue due to the large number of satellites and tasks,as well as complex observation constraints.To address the large-scale and complicated MEOSSP,we develop a Two-Stage Scheduling Algorithm based on the Pointer Network with Attention mechanism(TSSA-PNA).In TSSA-PNA,the MEOS observation scheduling is decomposed into a task allocation stage and a single-MEOS scheduling stage.In the task allocation stage,an adaptive task allocation algorithm with four problem-specific allocation operators is proposed to reallocate the unscheduled tasks to new MEOSs.Regarding the single-MEOS scheduling stage,we design a pointer network based on the encoder-decoder architecture to learn the optimal singleMEOS scheduling solution and introduce the attention mechanism into the encoder to improve the learning efficiency.The Pointer Network with Attention mechanism(PNA)can generate the single-MEOS scheduling solution quickly in an end-to-end manner.These two decomposed stages are performed iteratively to search for the solution with high profit.A greedy local search algorithm is developed to improve the profits further.The performance of the PNA and TSSA-PNA on singleMEOS and multi-MEOS scheduling problems are evaluated in the experiments.The experimental results demonstrate that PNA can obtain the approximate solution for the single-MEOS scheduling problem in a short time.Besides,the TSSA-PNA can achieve higher observation profits than the existing scheduling algorithms within the acceptable computational time for the large-scale MEOS scheduling problem.展开更多
The Heterogeneous Capacitated Vehicle Routing Problem(HCVRP),which involves efficiently routing vehicles with diverse capacities to fulfill various customer demands at minimal cost,poses an NP-hard challenge in combin...The Heterogeneous Capacitated Vehicle Routing Problem(HCVRP),which involves efficiently routing vehicles with diverse capacities to fulfill various customer demands at minimal cost,poses an NP-hard challenge in combinatorial optimization.Recently,reinforcement learning approaches such as 2D Array Pointer Networks(2D-Ptr)have demonstrated remarkable speed in decision-making by modeling multiple agents’concurrent choices as a sequence of consecutive actions.However,these learning-based models often struggle with generalization,meaning they cannot seamlessly adapt to new scenarios with varying numbers of vehicles or customers without retraining.Inspired by the potential of multi-teacher knowledge distillation to harness diverse knowledge from multiple sources and craft a comprehensive student model,we propose to enhance the generalization capability of 2D-Ptr through Multiple Teacher-forcing Knowledge Distillation(MTKD).We initially train 12 unique 2D-Ptr models under various settings to serve as teacher models.Subsequently,we randomly sample a teacher model and a batch of problem instances,focusing on those where the chosen teacher performed best.This teacher model then solves these instances,generating high-reward action sequences to guide knowledge transfer to the student model.We conduct rigorous evaluations across four distinct datasets,each comprising four HCVRP instances of varying scales.Our empirical findings underscore the proposed method superiority over existing learning-based methods in terms of both computational efficiency and solution quality.展开更多
Shuttle tankers scheduling is an important task in offshore oil and gas transportation process,which involves operating time window fulfillment,optimal transportation planning,and proper inventory management.However,c...Shuttle tankers scheduling is an important task in offshore oil and gas transportation process,which involves operating time window fulfillment,optimal transportation planning,and proper inventory management.However,conventional approaches like Mixed lnteger Linear Programming(MlLP)or meta heuristic algorithms often fail in long running time.In this paper,a Graph Pointer Network(GPN)based Hierarchical Curriculum Reinforcement Learning(HCRl)method is proposed to solve Shuttle Tankers Scheduling Problem(STSP)The model is trained to divide STSP into voyage and operation stages and generate routing and inventory management decisions sequentially.An asynchronous training strategy is developed to address the coupling between stages.Comparison experiments demonstrate that the proposed HCRL method achieves 12%shortel tour lengths on average compared to heuristic algorithms.Additional experiments validate its generalizability to unseen instances and scalability to larger instances.展开更多
在汉越低资源翻译任务中,句子中的实体词准确翻译是一大难点。针对实体词在训练语料中出现的频率较低,模型无法构建双语实体词之间的映射关系等问题,构建一种融入实体翻译的汉越神经机器翻译模型。首先,通过汉越实体双语词典预先获取源...在汉越低资源翻译任务中,句子中的实体词准确翻译是一大难点。针对实体词在训练语料中出现的频率较低,模型无法构建双语实体词之间的映射关系等问题,构建一种融入实体翻译的汉越神经机器翻译模型。首先,通过汉越实体双语词典预先获取源句中实体词的翻译结果;其次,将结果拼接在源句末端作为模型的输入,同时在编码端引入“约束提示信息”增强表征;最后,在解码端融入指针网络机制,以确保模型能复制输出源端句的词汇。实验结果表明,该模型相较于跨语言模型XLM-R(Cross-lingual Language Model-RoBERTa)的双语评估替补(BLEU)值在汉越方向提升了1.37,越汉方向提升了0.21,时间性能上相较于Transformer该模型在汉越方向和越汉方向分别缩短3.19%和3.50%,可有效地提升句子中实体词翻译的综合性能。展开更多
A mobile ad hoc network (MANET) is a kind of wireless ad hoc network. It is a self-configuring network of mobile routers connected by wireless links. Since MANETs do not have a fixed infrastructure, it is a chal-lenge...A mobile ad hoc network (MANET) is a kind of wireless ad hoc network. It is a self-configuring network of mobile routers connected by wireless links. Since MANETs do not have a fixed infrastructure, it is a chal-lenge to design a location management scheme that is both scalable and cost-efficient. In this paper, we propose a cooperative location management scheme, called CooLMS, for MANETs. CooLMS combines the strength of grid based location management and pointer forwarding strategy to achieve high scalability and low signaling cost. An indepth formal analysis of the location management cost of CooLMS is presented. In particular, the total location management cost of mobile nodes moving at variable velocity is estimated using the Gauss_Markov mobility model for the correlation of mobility velocities. Simulation results show CooLMS performs better than other schemes under certain circumstances.展开更多
为了解决自动文本摘要任务存在的文本语义信息不能充分编码、生成的摘要语义冗余、原始语义信息丢失等语义问题,提出了一种融合知识和文本语义信息的双编码器自动摘要模型(dual-encoder automatic summarization model incorporating kn...为了解决自动文本摘要任务存在的文本语义信息不能充分编码、生成的摘要语义冗余、原始语义信息丢失等语义问题,提出了一种融合知识和文本语义信息的双编码器自动摘要模型(dual-encoder automatic summarization model incorporating knowledge and semantic information,KSDASum)。该方法采用双编码器对原文语义信息进行充分编码,文本编码器获取全文的语义信息,图结构编码器维护全文上下文结构信息。解码器部分采用基于Transformer结构和指针网络,更好地捕捉文本和结构信息进行交互,并利用指针网络的优势提高生成摘要的准确性。同时,训练过程中采用强化学习中自我批判的策略梯度优化模型能力。该方法在CNN/Daily Mail和XSum公开数据集上与GSUM生成式摘要方法相比,在评价指标上均获得最优的结果,证明了所提模型能够有效地利用知识和语义信息,提升了生成文本摘要的能力。展开更多
电力变压器缺陷文本蕴含大量与设备可靠性密切相关的信息,可为变压器的智能化运维及寿命周期管理提供重要支撑。依托基于Transformer的双向编码器表示(bidirectional encoder representation from transformers,BERT)模型,文章提出一种...电力变压器缺陷文本蕴含大量与设备可靠性密切相关的信息,可为变压器的智能化运维及寿命周期管理提供重要支撑。依托基于Transformer的双向编码器表示(bidirectional encoder representation from transformers,BERT)模型,文章提出一种融合乱序语言模型预训练BERT(pre-training BERT with permuted language model,PERT)与高效全局指针(efficient global pointer,EGP)网络的电力变压器缺陷文本实体识别方法。首先,在大规模中文语料库上利用乱序语言模型进行预训练以形成PERT模型。其次,PERT作为语义编码层,以深入挖掘实体内部的语义依赖关系,并捕捉复杂文本中的语言特征;EGP作为信息解码层,专注于精确定位关键信息并提取实体在缺陷文本中的分布特征,进而准确识别缺陷实体。最后,运用PERT-EGP模型识别缺陷文本中包含的缺陷设备、缺陷部件、缺陷部位、缺陷现象和缺陷程度5类实体。算例结果表明,相较于现有方法,该方法不仅在成分复杂的复合实体和长文本上效果提升显著,而且大幅缩短模型训练时间,具有更好的文本识别性能。展开更多
基于“预训练+微调”范式的实体关系联合抽取方法依赖大规模标注数据,在数据标注难度大、成本高的中文古籍小样本场景下微调效率低,抽取性能不佳;中文古籍中普遍存在实体嵌套和关系重叠的问题,限制了实体关系联合抽取的效果;管道式抽取...基于“预训练+微调”范式的实体关系联合抽取方法依赖大规模标注数据,在数据标注难度大、成本高的中文古籍小样本场景下微调效率低,抽取性能不佳;中文古籍中普遍存在实体嵌套和关系重叠的问题,限制了实体关系联合抽取的效果;管道式抽取方法存在错误传播问题,影响抽取效果。针对以上问题,提出一种基于提示学习和全局指针网络的中文古籍实体关系联合抽取方法。首先,利用区间抽取式阅读理解的提示学习方法对预训练语言模型(PLM)注入领域知识以统一预训练和微调的优化目标,并对输入句子进行编码表示;其次,使用全局指针网络分别对主、客实体边界和不同关系下的主、客实体边界进行预测和联合解码,对齐成实体关系三元组,并构建了PTBG(Prompt Tuned BERT with Global pointer)模型,解决实体嵌套和关系重叠问题,同时避免了管道式解码的错误传播问题;最后,在上述工作基础上分析了不同提示模板对抽取性能的影响。在《史记》数据集上进行实验的结果表明,相较于注入领域知识前后的OneRel模型,PTBG模型所取得的F1值分别提升了1.64和1.97个百分点。可见,PTBG模型能更好地对中文古籍实体关系进行联合抽取,为低资源的小样本深度学习场景提供了新的研究思路与方法。展开更多
中文医疗文本的实体识别是自然语言处理领域的重点研究方向,文本的内在复杂性,包括术语的歧义性、实体的层级性以及对上下文信息的高度依赖,均有可能对实体识别任务的结果产生显著影响。为此,提出一种基于RBIEGP模型的中文实体识别方法...中文医疗文本的实体识别是自然语言处理领域的重点研究方向,文本的内在复杂性,包括术语的歧义性、实体的层级性以及对上下文信息的高度依赖,均有可能对实体识别任务的结果产生显著影响。为此,提出一种基于RBIEGP模型的中文实体识别方法。该方法首先利用RoBERTa-wwm-ext预训练模型对输入的中文医疗文本进行编码处理,以生成包含丰富语义信息的词向量序列;然后,将这些词向量序列送入BiGRU网络和集成了注意力机制的迭代扩张卷积神经网络,以捕获输入文本的上下文信息以及扩展感受野;最后,将这些融合了语法语义特征、上下文信息以及扩展感受野的特征一起输入到全局指针网络(Efficient Global Pointer,EGP),以进行实体类别的判定,并输出具有高准确度的实体类别序列。实验结果表明,RBIEGP模型在CMeEE/Yidu-S4k数据集上的F 1分数分别达到了70.47%和83.02%,相较于一些现有的主流模型,分别提升了2.72百分点和1.99百分点。展开更多
基金supported by the National Natural Science Foundation of China(No.62101587)the National Funded Postdoctoral Researcher Program of China(No.GZC20233578)。
文摘Micro-nano Earth Observation Satellite(MEOS)constellation has the advantages of low construction cost,short revisit cycle,and high functional density,which is considered a promising solution for serving rapidly growing observation demands.The observation Scheduling Problem in the MEOS constellation(MEOSSP)is a challenging issue due to the large number of satellites and tasks,as well as complex observation constraints.To address the large-scale and complicated MEOSSP,we develop a Two-Stage Scheduling Algorithm based on the Pointer Network with Attention mechanism(TSSA-PNA).In TSSA-PNA,the MEOS observation scheduling is decomposed into a task allocation stage and a single-MEOS scheduling stage.In the task allocation stage,an adaptive task allocation algorithm with four problem-specific allocation operators is proposed to reallocate the unscheduled tasks to new MEOSs.Regarding the single-MEOS scheduling stage,we design a pointer network based on the encoder-decoder architecture to learn the optimal singleMEOS scheduling solution and introduce the attention mechanism into the encoder to improve the learning efficiency.The Pointer Network with Attention mechanism(PNA)can generate the single-MEOS scheduling solution quickly in an end-to-end manner.These two decomposed stages are performed iteratively to search for the solution with high profit.A greedy local search algorithm is developed to improve the profits further.The performance of the PNA and TSSA-PNA on singleMEOS and multi-MEOS scheduling problems are evaluated in the experiments.The experimental results demonstrate that PNA can obtain the approximate solution for the single-MEOS scheduling problem in a short time.Besides,the TSSA-PNA can achieve higher observation profits than the existing scheduling algorithms within the acceptable computational time for the large-scale MEOS scheduling problem.
基金in part by the National Science Foundation of China under Grant No.62276238in part by the National Science Foundation for Distinguished Young Scholars of China under Grant No.62325602in part by the Natural Science Foundation of Henan,China under Grant No.232300421095.
文摘The Heterogeneous Capacitated Vehicle Routing Problem(HCVRP),which involves efficiently routing vehicles with diverse capacities to fulfill various customer demands at minimal cost,poses an NP-hard challenge in combinatorial optimization.Recently,reinforcement learning approaches such as 2D Array Pointer Networks(2D-Ptr)have demonstrated remarkable speed in decision-making by modeling multiple agents’concurrent choices as a sequence of consecutive actions.However,these learning-based models often struggle with generalization,meaning they cannot seamlessly adapt to new scenarios with varying numbers of vehicles or customers without retraining.Inspired by the potential of multi-teacher knowledge distillation to harness diverse knowledge from multiple sources and craft a comprehensive student model,we propose to enhance the generalization capability of 2D-Ptr through Multiple Teacher-forcing Knowledge Distillation(MTKD).We initially train 12 unique 2D-Ptr models under various settings to serve as teacher models.Subsequently,we randomly sample a teacher model and a batch of problem instances,focusing on those where the chosen teacher performed best.This teacher model then solves these instances,generating high-reward action sequences to guide knowledge transfer to the student model.We conduct rigorous evaluations across four distinct datasets,each comprising four HCVRP instances of varying scales.Our empirical findings underscore the proposed method superiority over existing learning-based methods in terms of both computational efficiency and solution quality.
基金supported by the National Natural Science Foundation of China(Nos.22178383 and 21706282)Beijing Natural Science Foundation(No.2232021)Research Foundation of China University of Petroleum(Beijing)(No.2462020BJRC004).
文摘Shuttle tankers scheduling is an important task in offshore oil and gas transportation process,which involves operating time window fulfillment,optimal transportation planning,and proper inventory management.However,conventional approaches like Mixed lnteger Linear Programming(MlLP)or meta heuristic algorithms often fail in long running time.In this paper,a Graph Pointer Network(GPN)based Hierarchical Curriculum Reinforcement Learning(HCRl)method is proposed to solve Shuttle Tankers Scheduling Problem(STSP)The model is trained to divide STSP into voyage and operation stages and generate routing and inventory management decisions sequentially.An asynchronous training strategy is developed to address the coupling between stages.Comparison experiments demonstrate that the proposed HCRL method achieves 12%shortel tour lengths on average compared to heuristic algorithms.Additional experiments validate its generalizability to unseen instances and scalability to larger instances.
文摘在汉越低资源翻译任务中,句子中的实体词准确翻译是一大难点。针对实体词在训练语料中出现的频率较低,模型无法构建双语实体词之间的映射关系等问题,构建一种融入实体翻译的汉越神经机器翻译模型。首先,通过汉越实体双语词典预先获取源句中实体词的翻译结果;其次,将结果拼接在源句末端作为模型的输入,同时在编码端引入“约束提示信息”增强表征;最后,在解码端融入指针网络机制,以确保模型能复制输出源端句的词汇。实验结果表明,该模型相较于跨语言模型XLM-R(Cross-lingual Language Model-RoBERTa)的双语评估替补(BLEU)值在汉越方向提升了1.37,越汉方向提升了0.21,时间性能上相较于Transformer该模型在汉越方向和越汉方向分别缩短3.19%和3.50%,可有效地提升句子中实体词翻译的综合性能。
文摘A mobile ad hoc network (MANET) is a kind of wireless ad hoc network. It is a self-configuring network of mobile routers connected by wireless links. Since MANETs do not have a fixed infrastructure, it is a chal-lenge to design a location management scheme that is both scalable and cost-efficient. In this paper, we propose a cooperative location management scheme, called CooLMS, for MANETs. CooLMS combines the strength of grid based location management and pointer forwarding strategy to achieve high scalability and low signaling cost. An indepth formal analysis of the location management cost of CooLMS is presented. In particular, the total location management cost of mobile nodes moving at variable velocity is estimated using the Gauss_Markov mobility model for the correlation of mobility velocities. Simulation results show CooLMS performs better than other schemes under certain circumstances.
文摘为了解决自动文本摘要任务存在的文本语义信息不能充分编码、生成的摘要语义冗余、原始语义信息丢失等语义问题,提出了一种融合知识和文本语义信息的双编码器自动摘要模型(dual-encoder automatic summarization model incorporating knowledge and semantic information,KSDASum)。该方法采用双编码器对原文语义信息进行充分编码,文本编码器获取全文的语义信息,图结构编码器维护全文上下文结构信息。解码器部分采用基于Transformer结构和指针网络,更好地捕捉文本和结构信息进行交互,并利用指针网络的优势提高生成摘要的准确性。同时,训练过程中采用强化学习中自我批判的策略梯度优化模型能力。该方法在CNN/Daily Mail和XSum公开数据集上与GSUM生成式摘要方法相比,在评价指标上均获得最优的结果,证明了所提模型能够有效地利用知识和语义信息,提升了生成文本摘要的能力。
文摘电力变压器缺陷文本蕴含大量与设备可靠性密切相关的信息,可为变压器的智能化运维及寿命周期管理提供重要支撑。依托基于Transformer的双向编码器表示(bidirectional encoder representation from transformers,BERT)模型,文章提出一种融合乱序语言模型预训练BERT(pre-training BERT with permuted language model,PERT)与高效全局指针(efficient global pointer,EGP)网络的电力变压器缺陷文本实体识别方法。首先,在大规模中文语料库上利用乱序语言模型进行预训练以形成PERT模型。其次,PERT作为语义编码层,以深入挖掘实体内部的语义依赖关系,并捕捉复杂文本中的语言特征;EGP作为信息解码层,专注于精确定位关键信息并提取实体在缺陷文本中的分布特征,进而准确识别缺陷实体。最后,运用PERT-EGP模型识别缺陷文本中包含的缺陷设备、缺陷部件、缺陷部位、缺陷现象和缺陷程度5类实体。算例结果表明,相较于现有方法,该方法不仅在成分复杂的复合实体和长文本上效果提升显著,而且大幅缩短模型训练时间,具有更好的文本识别性能。
文摘基于“预训练+微调”范式的实体关系联合抽取方法依赖大规模标注数据,在数据标注难度大、成本高的中文古籍小样本场景下微调效率低,抽取性能不佳;中文古籍中普遍存在实体嵌套和关系重叠的问题,限制了实体关系联合抽取的效果;管道式抽取方法存在错误传播问题,影响抽取效果。针对以上问题,提出一种基于提示学习和全局指针网络的中文古籍实体关系联合抽取方法。首先,利用区间抽取式阅读理解的提示学习方法对预训练语言模型(PLM)注入领域知识以统一预训练和微调的优化目标,并对输入句子进行编码表示;其次,使用全局指针网络分别对主、客实体边界和不同关系下的主、客实体边界进行预测和联合解码,对齐成实体关系三元组,并构建了PTBG(Prompt Tuned BERT with Global pointer)模型,解决实体嵌套和关系重叠问题,同时避免了管道式解码的错误传播问题;最后,在上述工作基础上分析了不同提示模板对抽取性能的影响。在《史记》数据集上进行实验的结果表明,相较于注入领域知识前后的OneRel模型,PTBG模型所取得的F1值分别提升了1.64和1.97个百分点。可见,PTBG模型能更好地对中文古籍实体关系进行联合抽取,为低资源的小样本深度学习场景提供了新的研究思路与方法。
文摘中文医疗文本的实体识别是自然语言处理领域的重点研究方向,文本的内在复杂性,包括术语的歧义性、实体的层级性以及对上下文信息的高度依赖,均有可能对实体识别任务的结果产生显著影响。为此,提出一种基于RBIEGP模型的中文实体识别方法。该方法首先利用RoBERTa-wwm-ext预训练模型对输入的中文医疗文本进行编码处理,以生成包含丰富语义信息的词向量序列;然后,将这些词向量序列送入BiGRU网络和集成了注意力机制的迭代扩张卷积神经网络,以捕获输入文本的上下文信息以及扩展感受野;最后,将这些融合了语法语义特征、上下文信息以及扩展感受野的特征一起输入到全局指针网络(Efficient Global Pointer,EGP),以进行实体类别的判定,并输出具有高准确度的实体类别序列。实验结果表明,RBIEGP模型在CMeEE/Yidu-S4k数据集上的F 1分数分别达到了70.47%和83.02%,相较于一些现有的主流模型,分别提升了2.72百分点和1.99百分点。
