In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple e...In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple extraction models facemultiple challenges when processing domain-specific data,including insufficient utilization of semantic interaction information between entities and relations,difficulties in handling challenging samples,and the scarcity of domain-specific datasets.To address these issues,our study introduces three innovative components:Relation semantic enhancement,data augmentation,and a voting strategy,all designed to significantly improve the model’s performance in tackling domain-specific relational triple extraction tasks.We first propose an innovative attention interaction module.This method significantly enhances the semantic interaction capabilities between entities and relations by integrating semantic information fromrelation labels.Second,we propose a voting strategy that effectively combines the strengths of large languagemodels(LLMs)and fine-tuned small pre-trained language models(SLMs)to reevaluate challenging samples,thereby improving the model’s adaptability in specific domains.Additionally,we explore the use of LLMs for data augmentation,aiming to generate domain-specific datasets to alleviate the scarcity of domain data.Experiments conducted on three domain-specific datasets demonstrate that our model outperforms existing comparative models in several aspects,with F1 scores exceeding the State of the Art models by 2%,1.6%,and 0.6%,respectively,validating the effectiveness and generalizability of our approach.展开更多
The great evolution of the mobile market during the last years caused some fragmentation of the mobile platforms namely through the existence of different programming languages and software development tools for each ...The great evolution of the mobile market during the last years caused some fragmentation of the mobile platforms namely through the existence of different programming languages and software development tools for each platform. This fact can be an obstacle and increases the development complexity and costs when we want to develop mobile applications for multiple platforms. The XIS-Mobile domain specific language (defined as a UML profile) and its MDD-based framework address this problem by proposing platform-independent models to describe mobile applications and from them automatically generate the application’s source code. Many issues arose during an iterative process of evaluation which originated changes and the evolution of XIS-Mobile. This paper presents the results of the evaluation of XIS-Mobile (both the language and the companion framework) obtained through the implementation of a case study and by conducting a user session, and discusses its benefits and challenges.展开更多
在航空航天领域,系统的复杂度快速增长,这对基于模型的系统工程的开展带来巨大的挑战,尤以复杂系统的需求分析为甚。需求分析过程缺乏针对性的支持模型的工具。针对基于模型的系统工程中的这一问题,根据领域建模的思想,引入领域特定语言...在航空航天领域,系统的复杂度快速增长,这对基于模型的系统工程的开展带来巨大的挑战,尤以复杂系统的需求分析为甚。需求分析过程缺乏针对性的支持模型的工具。针对基于模型的系统工程中的这一问题,根据领域建模的思想,引入领域特定语言(domain specific language, DSL)的概念,提出一种构建DSL进行需求分析的方法,并针对基于模型的系统工程(model based system engineering, MBSE)中需求分析的需要构建相应的DSL。首先,从基于模型的系统工程方法论角度,对工程应用中的需求捕获与分解进行了分析;接着,通过扩展后的GOPPRR(graph object property port role relationship)元元模型依据需要,构建了DSL的具体语法与语义;最后,以具体的系统为例与系统建模语言分析方法做出了对比。结果表明,所构建的DSL在进行复杂系统的需求分析与建模时,与实际需要契合,在各个环节都具有针对性强、形式化的优点,有利于保证需求分析与建模工作的正确性。展开更多
说实话，我开始不喜欢DSL这个词了。因为每次没等我把DSL三个字母全部说出来，我的朋友都已经背过耳朵去了。这玩意已经在俺们这个圈子里说烂了。Domain Specific Language，啊？难道我平时写的每行代码不都是和具体的领域相关的嘛。凭...说实话，我开始不喜欢DSL这个词了。因为每次没等我把DSL三个字母全部说出来，我的朋友都已经背过耳朵去了。这玩意已经在俺们这个圈子里说烂了。Domain Specific Language，啊？难道我平时写的每行代码不都是和具体的领域相关的嘛。凭啥你写的是DSL，我写的就是陈旧腐朽的Java代码？我不禁要问了，咋写才算DSL？展开更多
基金Science and Technology Innovation 2030-Major Project of“New Generation Artificial Intelligence”granted by Ministry of Science and Technology,Grant Number 2020AAA0109300.
文摘In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple extraction models facemultiple challenges when processing domain-specific data,including insufficient utilization of semantic interaction information between entities and relations,difficulties in handling challenging samples,and the scarcity of domain-specific datasets.To address these issues,our study introduces three innovative components:Relation semantic enhancement,data augmentation,and a voting strategy,all designed to significantly improve the model’s performance in tackling domain-specific relational triple extraction tasks.We first propose an innovative attention interaction module.This method significantly enhances the semantic interaction capabilities between entities and relations by integrating semantic information fromrelation labels.Second,we propose a voting strategy that effectively combines the strengths of large languagemodels(LLMs)and fine-tuned small pre-trained language models(SLMs)to reevaluate challenging samples,thereby improving the model’s adaptability in specific domains.Additionally,we explore the use of LLMs for data augmentation,aiming to generate domain-specific datasets to alleviate the scarcity of domain data.Experiments conducted on three domain-specific datasets demonstrate that our model outperforms existing comparative models in several aspects,with F1 scores exceeding the State of the Art models by 2%,1.6%,and 0.6%,respectively,validating the effectiveness and generalizability of our approach.
文摘The great evolution of the mobile market during the last years caused some fragmentation of the mobile platforms namely through the existence of different programming languages and software development tools for each platform. This fact can be an obstacle and increases the development complexity and costs when we want to develop mobile applications for multiple platforms. The XIS-Mobile domain specific language (defined as a UML profile) and its MDD-based framework address this problem by proposing platform-independent models to describe mobile applications and from them automatically generate the application’s source code. Many issues arose during an iterative process of evaluation which originated changes and the evolution of XIS-Mobile. This paper presents the results of the evaluation of XIS-Mobile (both the language and the companion framework) obtained through the implementation of a case study and by conducting a user session, and discusses its benefits and challenges.
文摘在航空航天领域,系统的复杂度快速增长,这对基于模型的系统工程的开展带来巨大的挑战,尤以复杂系统的需求分析为甚。需求分析过程缺乏针对性的支持模型的工具。针对基于模型的系统工程中的这一问题,根据领域建模的思想,引入领域特定语言(domain specific language, DSL)的概念,提出一种构建DSL进行需求分析的方法,并针对基于模型的系统工程(model based system engineering, MBSE)中需求分析的需要构建相应的DSL。首先,从基于模型的系统工程方法论角度,对工程应用中的需求捕获与分解进行了分析;接着,通过扩展后的GOPPRR(graph object property port role relationship)元元模型依据需要,构建了DSL的具体语法与语义;最后,以具体的系统为例与系统建模语言分析方法做出了对比。结果表明,所构建的DSL在进行复杂系统的需求分析与建模时,与实际需要契合,在各个环节都具有针对性强、形式化的优点,有利于保证需求分析与建模工作的正确性。
文摘说实话，我开始不喜欢DSL这个词了。因为每次没等我把DSL三个字母全部说出来，我的朋友都已经背过耳朵去了。这玩意已经在俺们这个圈子里说烂了。Domain Specific Language，啊？难道我平时写的每行代码不都是和具体的领域相关的嘛。凭啥你写的是DSL，我写的就是陈旧腐朽的Java代码？我不禁要问了，咋写才算DSL？
