To exploit the domain knowledge to guarantee the correctness of generated text has been a hot topic in recent years, especially for high professional domains such as medical. However, most of recent works only consider the information of unstructured text rather than structured information of the knowledge graph. In this paper, we focus on the medical topic-to-text generation task and adapt a knowledge-aware text generation model to the medical domain, named MedWriter, which not only introduces the specific knowledge from the external MKG but also is capable of learning graph-level representation. We conduct experiments on a medical literature dataset collected from medical journals, each of which has a set of topic words, an abstract of medical literature and a corresponding knowledge graph from CMeKG. Experimental results demonstrate incorporating knowledge graph into generation model can improve the quality of the generated text and has robust superiority over the competitor methods.
Electronic medical records (EMRs) are usually stored in relational databases that require SQL queries to retrieve information of interest. Effectively completing such queries can be a challenging task for medical experts due to the barriers in expertise. Existing text-to-SQL generation studies have not been fully embraced in the medical domain.
The objective of this study was to propose a neural generation model that can jointly consider the characteristics of medical text and the SQL structure to automatically transform medical texts to SQL queries for EMRs.
We proposed a medical text–to-SQL model (MedTS), which employed a pretrained Bidirectional Encoder Representations From Transformers model as the encoder and leveraged a grammar-based long short-term memory network as the decoder to predict the intermediate representation that can easily be transformed into the final SQL query. We adopted the syntax tree as the intermediate representation rather than directly regarding the SQL query as an ordinary word sequence, which is more in line with the tree-structure nature of SQL and can also effectively reduce the search space during generation. Experiments were conducted on the MIMICSQL dataset, and 5 competitor methods were compared.
Experimental results demonstrated that MedTS achieved the accuracy of 0.784 and 0.899 on the test set in terms of logic form and execution, respectively, which significantly outperformed the existing state-of-the-art methods. Further analyses proved that the performance on each component of the generated SQL was relatively balanced and offered substantial improvements.
The proposed MedTS was effective and robust for improving the performance of medical text–to-SQL generation, indicating strong potential to be applied in the real medical scenario.
In order to restrain electric-stress impacts of water micro-droplets in insulation defects under alternating current (AC) electric fields in crosslinked polyethylene (XLPE) material, the present study represents chemical graft modifications of introducing chloroacetic acid allyl ester (CAAE) and maleic anhydride (MAH) individually as two specific polar-group molecules into XLPE material with peroxide melting approach. The accelerated water-tree aging experiments are implemented by means of a water-blade electrode to measure the improved water resistance and the affording mechanism of the graft-modified XLPE material in reference to benchmark XLPE. Melting–crystallization process, dynamic viscoelasticity and stress-strain characteristics are tested utilizing differential scanning calorimeter (DSC), dynamic thermomechanical analyzer (DMA) and electronic tension machine, respectively. Water-tree morphology is observed for various aging times to evaluate dimension characteristics in water-tree developing processes. Monte Carlo molecular simulations are performed to calculate free-energy, thermodynamic phase diagram, interaction parameter and mixing energy of binary mixing systems consisting of CAAE or MAH and water molecules to evaluate their thermodynamic miscibility. Water-tree experiments indicate that water-tree resistance to XLPE can be significantly improved by grafting CAAE or MAH, as indicated by reducing the characteristic length of water-trees from 120 to 80 μm. Heterogeneous nucleation centers of polyethylene crystallization are rendered by the grafted polar-group molecules to ameliorate crystalline microstructures, as manifested by crystallinity increment from 33.5 to 36.2, which favors improving water-tree resistance and mechanical performances. The highly hydrophilic nature of CAAE can evidently inhibit water molecules from aggregating into water micro-droplets in amorphous regions between crystal lamellae, thus acquiring a significant promotion in water-tree resistance of CAAE-modified XLPE. In contrast, the grafted MAH molecules can enhance van der Waals forces between polyethylene molecular chains in amorphous regions much greater than the grafted CAAE and simultaneously act as more efficient crystallization nucleation centers to ameliorate crystalline microstructures of XLPE, resulting in a greater improvement (relaxation peak magnitude increases by >10%) of mechanical toughness in amorphous phase, which primarily accounts for water-tree resistance promotion.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.