Knowledge selection is a challenging task that often deals with semantic drift issues when knowledge is retrieved based on semantic similarity between a fact and a question. In addition, weak correlations embedded in ...Knowledge selection is a challenging task that often deals with semantic drift issues when knowledge is retrieved based on semantic similarity between a fact and a question. In addition, weak correlations embedded in pairs of facts and questions and gigantic knowledge bases available for knowledge search are also unavoidable issues. This paper presents a scalable approach to address these issues. A sparse encoder and a dense encoder are coupled iteratively to retrieve fact candidates from a large-scale knowledge base. A pre-trained language model with two rounds of fine-tuning using results of the sparse and dense encoders is then used to re-rank fact candidates. Top-k facts are selected by a specific re-ranker. The scalable approach is applied on two textual inference datasets and one knowledge-grounded question answering dataset. Experimental results demonstrate that (1) the proposed approach can improve the performance of knowledge selection by reducing the semantic drift;(2) the proposed approach produces outstanding results on the benchmark datasets. The code is available at https://github.com/hhhhzs666/KSIHER.展开更多
The paper deals with ontology modelling for the purpose of design and creating of knowledge ontology for thematic cartography.The prepared ontology represents a database of selected declarative cartographical knowledg...The paper deals with ontology modelling for the purpose of design and creating of knowledge ontology for thematic cartography.The prepared ontology represents a database of selected declarative cartographical knowledge subsequently employed in the intelligent system for interactive support of thematic map design.The knowledge system pilot project under development is intended for users without necessary cartographical knowledge to whom such system will enable interactive creation of a thematic map and will provide them with support to this aim.The paper brings up information on possibilities of a domain expert(cartographer)in the endeavour to seize domain knowledge of thematic cartography and to express them in a formalized way.OWL ontology concentrates,formalizes and organizes declarative knowledge of thematic cartography domain.The result is the database containing taxonomy of terms hierarchically arranged into categories as well as description of their mutual relations.展开更多
The strategy of expert system for high performance liquid chromatography was discussed, the attentions are mainly placed on the knowledge base for selection of column system, separation modes and detection modes in th...The strategy of expert system for high performance liquid chromatography was discussed, the attentions are mainly placed on the knowledge base for selection of column system, separation modes and detection modes in the analysis of amino acids, peptides and proteins.展开更多
The reasonable calculation of ground appropriateness index in permafrost region is the precondition of highway route design in permafrost region. The theory of knowledge base and fuzzy mathematics are applied, and the...The reasonable calculation of ground appropriateness index in permafrost region is the precondition of highway route design in permafrost region. The theory of knowledge base and fuzzy mathematics are applied, and the damage effect of permafrost is considered in the paper. Based on the idea of protecting permafrost the calculation method of ground appro- priateness index is put forward. Firstly, based on the actual environment conditions, the paper determines the factors affecting the road layout in permafrost areas by qualitative and quantitative analysis, including the annual slope, the average annual ground temperature of permafrost, the amount of ice in frozen soil, and the interference engineering. Secondly, based on the knowledge base theory and the use of Delphi method, the paper establishes the knowledge base, the rule base of the permafrost region and inference mechanism. The method of selecting the road in permafrost region is completed and realized by using the software platform. Thirdly, taking the Tuotuo River to Kaixin Mountain section of permafrost region as an example, the application of the method is studied by using an ArcGIS platform. Results show that the route plan determined by the method of selecting the road in perma-frost region can avoid the high temperature and high ice content area, conform the terrain changes and evade the heat disturbance among the existing projects. A reasonable route plan can be achieved, and it can provide the basis for the next engineering construction.展开更多
基金supported by the Wuyi University-Hong Kong-Macao Joint Funding Scheme(No.2022WGALH17)the Research Platform and Project of Universities of Education Department of Guangdong Province,China 2023(No.2023ZDZX1030).
文摘Knowledge selection is a challenging task that often deals with semantic drift issues when knowledge is retrieved based on semantic similarity between a fact and a question. In addition, weak correlations embedded in pairs of facts and questions and gigantic knowledge bases available for knowledge search are also unavoidable issues. This paper presents a scalable approach to address these issues. A sparse encoder and a dense encoder are coupled iteratively to retrieve fact candidates from a large-scale knowledge base. A pre-trained language model with two rounds of fine-tuning using results of the sparse and dense encoders is then used to re-rank fact candidates. Top-k facts are selected by a specific re-ranker. The scalable approach is applied on two textual inference datasets and one knowledge-grounded question answering dataset. Experimental results demonstrate that (1) the proposed approach can improve the performance of knowledge selection by reducing the semantic drift;(2) the proposed approach produces outstanding results on the benchmark datasets. The code is available at https://github.com/hhhhzs666/KSIHER.
基金supported by the Czech Science Foundation under Grant No.205/09/1159.Support of the Czech Science Foundation is gratefully acknowledged.
文摘The paper deals with ontology modelling for the purpose of design and creating of knowledge ontology for thematic cartography.The prepared ontology represents a database of selected declarative cartographical knowledge subsequently employed in the intelligent system for interactive support of thematic map design.The knowledge system pilot project under development is intended for users without necessary cartographical knowledge to whom such system will enable interactive creation of a thematic map and will provide them with support to this aim.The paper brings up information on possibilities of a domain expert(cartographer)in the endeavour to seize domain knowledge of thematic cartography and to express them in a formalized way.OWL ontology concentrates,formalizes and organizes declarative knowledge of thematic cartography domain.The result is the database containing taxonomy of terms hierarchically arranged into categories as well as description of their mutual relations.
基金Project supported by the National Natural Science Foundation of China.
文摘The strategy of expert system for high performance liquid chromatography was discussed, the attentions are mainly placed on the knowledge base for selection of column system, separation modes and detection modes in the analysis of amino acids, peptides and proteins.
基金support provide by Special Fund for Basic Scientific Research of Central Col leges, Changan University (310821172002)Postdoctoral Science Foundation of China (2016M590915)+2 种基金Basic Research Func of Ministry of Transportation (2014319812170)National Sci Tech Support Plan (2014BAG05B01)Basic Research Program of Natural Science in Shaanxi Province (S2017-ZRJJ-MS0603)
文摘The reasonable calculation of ground appropriateness index in permafrost region is the precondition of highway route design in permafrost region. The theory of knowledge base and fuzzy mathematics are applied, and the damage effect of permafrost is considered in the paper. Based on the idea of protecting permafrost the calculation method of ground appro- priateness index is put forward. Firstly, based on the actual environment conditions, the paper determines the factors affecting the road layout in permafrost areas by qualitative and quantitative analysis, including the annual slope, the average annual ground temperature of permafrost, the amount of ice in frozen soil, and the interference engineering. Secondly, based on the knowledge base theory and the use of Delphi method, the paper establishes the knowledge base, the rule base of the permafrost region and inference mechanism. The method of selecting the road in permafrost region is completed and realized by using the software platform. Thirdly, taking the Tuotuo River to Kaixin Mountain section of permafrost region as an example, the application of the method is studied by using an ArcGIS platform. Results show that the route plan determined by the method of selecting the road in perma-frost region can avoid the high temperature and high ice content area, conform the terrain changes and evade the heat disturbance among the existing projects. A reasonable route plan can be achieved, and it can provide the basis for the next engineering construction.
