Data curation is vital for selecting effective demonstration examples in graph-to-text generation.However,evaluating the quality ofKnowledgeGraphs(KGs)remains challenging.Prior research exhibits a narrowfocus on struc...Data curation is vital for selecting effective demonstration examples in graph-to-text generation.However,evaluating the quality ofKnowledgeGraphs(KGs)remains challenging.Prior research exhibits a narrowfocus on structural statistics,such as the shortest path length,while the correctness of graphs in representing the associated text is rarely explored.To address this gap,we introduce a dual-perspective evaluation framework for KG-text data,based on the computation of structural adequacy and semantic alignment.Froma structural perspective,we propose the Weighted Incremental EdgeMethod(WIEM)to quantify graph completeness by leveraging agreement between relation models to predict possible edges between entities.WIEM targets to find increments from models on“unseen links”,whose presence is inversely proportional to the structural adequacy of the original KG in representing the text.From a semantic perspective,we evaluate how well a KG aligns with the text in capturing the intended meaning.To do so,we instruct a large language model to convert KGs into natural language andmeasure the similarity between generated and reference texts.Based on these computations,we apply a Top-K union method,integrating the structural and semantic modules,to rank and select high-quality KGs.We evaluate our framework against various approaches for selecting few-shot examples in graph-to-text generation.Experiments on theAssociation for Computational LinguisticsAbstract Graph Dataset(ACL-AGD)and Automatic Content Extraction 05(ACE05)dataset demonstrate the effectiveness of our approach in distinguishing KG-text data of different qualities,evidenced by the largest performance gap between top-and bottom-ranked examples.We also find that the top examples selected through our dual-perspective framework consistently yield better performance than those selected by traditional measures.These results highlight the importance of data curation in improving graph-to-text generation.展开更多
Current design rationale （DR） systems have not demonstrated the value of the approach in practice since little attention is put to the evaluation method of DR knowledge. To systematize knowledge management process f...Current design rationale （DR） systems have not demonstrated the value of the approach in practice since little attention is put to the evaluation method of DR knowledge. To systematize knowledge management process for future computer-aided DR applications, a prerequisite is to provide the measure for the DR knowledge. In this paper, a new knowledge network evaluation method for DR management is presented. The method characterizes the DR knowledge value from four perspectives, namely, the design rationale structure scale, association knowledge and reasoning ability, degree of design justification support and degree of knowledge representation conciseness. The DR knowledge comprehensive value is also measured by the proposed method. To validate the proposed method, different style of DR knowledge network and the performance of the proposed measure are discussed. The evaluation method has been applied in two realistic design cases and compared with the structural measures. The research proposes the DR knowledge evaluation method which can provide object metric and selection basis for the DR knowledge reuse during the product design process. In addition, the method is proved to be more effective guidance and support for the application and management of DR knowledge.展开更多
文摘Data curation is vital for selecting effective demonstration examples in graph-to-text generation.However,evaluating the quality ofKnowledgeGraphs(KGs)remains challenging.Prior research exhibits a narrowfocus on structural statistics,such as the shortest path length,while the correctness of graphs in representing the associated text is rarely explored.To address this gap,we introduce a dual-perspective evaluation framework for KG-text data,based on the computation of structural adequacy and semantic alignment.Froma structural perspective,we propose the Weighted Incremental EdgeMethod(WIEM)to quantify graph completeness by leveraging agreement between relation models to predict possible edges between entities.WIEM targets to find increments from models on“unseen links”,whose presence is inversely proportional to the structural adequacy of the original KG in representing the text.From a semantic perspective,we evaluate how well a KG aligns with the text in capturing the intended meaning.To do so,we instruct a large language model to convert KGs into natural language andmeasure the similarity between generated and reference texts.Based on these computations,we apply a Top-K union method,integrating the structural and semantic modules,to rank and select high-quality KGs.We evaluate our framework against various approaches for selecting few-shot examples in graph-to-text generation.Experiments on theAssociation for Computational LinguisticsAbstract Graph Dataset(ACL-AGD)and Automatic Content Extraction 05(ACE05)dataset demonstrate the effectiveness of our approach in distinguishing KG-text data of different qualities,evidenced by the largest performance gap between top-and bottom-ranked examples.We also find that the top examples selected through our dual-perspective framework consistently yield better performance than those selected by traditional measures.These results highlight the importance of data curation in improving graph-to-text generation.
基金Supported by National Natural Science Foundation of China(Grant Nos.51175019,61104169,51205321)
文摘Current design rationale （DR） systems have not demonstrated the value of the approach in practice since little attention is put to the evaluation method of DR knowledge. To systematize knowledge management process for future computer-aided DR applications, a prerequisite is to provide the measure for the DR knowledge. In this paper, a new knowledge network evaluation method for DR management is presented. The method characterizes the DR knowledge value from four perspectives, namely, the design rationale structure scale, association knowledge and reasoning ability, degree of design justification support and degree of knowledge representation conciseness. The DR knowledge comprehensive value is also measured by the proposed method. To validate the proposed method, different style of DR knowledge network and the performance of the proposed measure are discussed. The evaluation method has been applied in two realistic design cases and compared with the structural measures. The research proposes the DR knowledge evaluation method which can provide object metric and selection basis for the DR knowledge reuse during the product design process. In addition, the method is proved to be more effective guidance and support for the application and management of DR knowledge.
