Enhancing Relational Triple Extraction in Specific Domains:Semantic Enhancement and Synergy of Large Language Models and Small Pre-Trained Language Models

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.

Fetal bovine serum versus Chinese herbal formula Naoluoxintong serum supplementation for proliferation and differentiation of rat embryonic neural stem cells

BACKGROUND： How to induce endogenous neural stem cells （NSCs） to differentiate into needed neural cell types is a hot spot of current researches. OBJECTIVE： To compare differences between fetal bovine serum and Chinese herbal formula Naoluoxintong serum supplementation for inducing proliferation and differentiation in rat embryonic NSCs. DESIGN, TIME AND SETTING： An in vitro, serum pharmacology, comparative, observation study was performed from March to September in 2008 at the Laboratory of Neurodegenerative Diseases, College of Life Science in University of Science and Technology of China, the Key Laboratory Breeding Base of Acupuncture Foundation and Technology in Anhui University of Traditional Chinese Medicine, the Anhui Province Key Laboratory of R ＆ D of Chinese Medicine, and at the Level 3 Laboratory of Molecular Biology of the State Administration of Traditional Chinese Medicine. MATERIALS： The Chinese herbal formula Naoluoxintong was produced by Radix Astragali, Radix Notoginseng, Rhizoma Chuanxiong, Scolopendra at Anhui University of Traditional Chinese Medicine. Mouse anti-rat nestin, gliat fibrillary acidic protein, and galactocerebroside monoclonal antibodies, as well as rabbit anti-neuron-specific enolase polyclonal antibody were produced by Chemicon, Billerica, MA, USA. METHODS： Wistar rats aged 3 months were intragastrically infused with Naoluoxintong. Wistar rat embryonic NSCs （passage 8） were induced to proliferate and differentiate using 10% fetal bovine serum, 10% Naoluoxintong serum, and 10% rat serum. MAIN OUTCOME MEASURES： Phenotypic changes in cultured cells were detected using phase contrast microscopy, and cell proliferation and differentiation were observed using immunofluorescence staining. RESULTS： Proliferation and differentiation of embryonic NSCs was induced by three different types of blood serum. Although the differentiation time course with Nao/uoxintongserum was later than with the other two methods, the differentiated cells were morphologically similar to mature neurons to a greater extent. CONCLUSION： Nao/uoxintong serum supplementation induced differentiation of NSCs into neuronal-like cells and stimulated neuronal maturation.

Characteristics and achievements of the Xin'an Medical School

The Xin'an Medical School began in the Jin Dynasty(266-420),developed in the Song Dynasty(960-1279),prospered in theMing and Qing dynasties(1368-1911),and has been passed down to the modern era.As a school of medicine with distinct regional characteristics,it has contributed to the development of traditional Chinese medicine and exerted farreaching influence,mainly in literature resources,medical theory,clinical application,and spiritual culture.This paper intends to discuss its academic characteristics and contribution to the development of traditional Chinese medicine,focusing on its formation,academic inheritance and innovation,overseas popularization,and integration of Confucianism,Taoism,and Buddhism in medicine.

Research on the modern clinical herbal administration rules in TCM treatment of ovarian cysts based on data mining

Objective:To explore the recent 20 years' herbal administration rules in TCM treatments of ovarian cysts (OCs) based on data mining.Methods:A prescription database for ovarian cysts was established by ACCESS 2007.Importing the database into SPSS17.0 and SPSS Modeler14.1.SPSS17.0 was used for descriptive and cluster analyses,while SPSS Modeler14.1 was used for association rules analysis.Results:After screening,363 prescriptions were obtained.The 10 most frequently-used Chinese herbal medicines are Zedoaria (Rhizoma Curcumae),Poria cocos (Poria),Common buried rubber (Rhizoma Sparganii),Red peony root (Radix Paeoniae Rubra),Peach seed (Semen Persicae),Danggui (Radix Angelicae Sinensis),Chinese angelica (Ramulus Cinnamomi),Liquorice root (Radix Glycyrrhizae),Pangolin scales (Squama Manis) and Moutan cortex (Cortex Moutan Radicis);the 5 most common syndromes of OCs are qi stagnation and blood stasis,phlegm and blood stasis,uterine blood stasis,stagnation of liver qi and retention of phlegm and dampness,nearly to 54.26%;In association rules analysis,5 sets of two-herbs association rules were obtained,17 sets of three-herbs association rules were obtained,22 sets of four-herbs association rules were obtained and 4 sets of five-herbs association rules were obtained;By clustering,13 sets of core couplet medicinals were obtained.Conclusion:Medicinal herbs for promoting blood circulation to remove blood stasis,resolve hard lumps,for strengthening the spleen,eliminating phlegm,and relieving liver qi stagnation were highly used in the treatment of OCs;Herbs attributed to the Liver Meridian,the Spleen Meridian and the Heart Meridian were highly used in OCs;The compatibility of herbs for promoting blood circulation to remove blood stasis and resolve hard lumps were highly used;Guizhi Fuling Wan (GFW) was often used and combined with other herbs in the treatment of OCs.

Unrecognized role of humic acid as a reductant in accelerating fluoroquinolones oxidation by aqueous permanganate

A great concern has been raised regarding the issue of fluoroquinolones(FQs)in the environment.In this work,the transformation of FQs by commonly used oxidant permanganate(Mn(VII))in the absence and presence of humic acid(HA),ubiquitously existing in aquatic environments,was systematically investigated.Here,the catalytic role of in-situ formed MnO;on Mn(VII)oxidation of FQs depending on solution pH and co-existing substrates was firstly reported.It was interestingly found that HA could appreciably accelerate FQs degradation by Mn(VII)at environmentally relevant pH.HA as a reductant in accelerating FQs by Mn(VII)oxidation was distinctly elucidated for the first time,where MnO;in situ formed from the reduction of Mn(VII)by HA served as a catalyst.Similar products were observed in the presence versus absence of HA.Considering that the accelerating role of HA was related to its reducing ability,an activation method based on Mn(VII)and reductant(i.e.,Fe(II),Mn(II)and(bi)sulfite)was proposed,which exhibited considerable potential for application in the treatment of FQs contaminated water.

Proactive planning of bandwidth resource using simulation-based what-if predictions for Web services in the cloud

Resource planning is becoming an increasingly important and timely problem for cloud users.As more Web services are moved to the cloud,minimizing network usage is often a key driver of cost control.Most existing approaches focus on resources such as CPU,memory,and disk I/O.In particular,CPU receives the most attention from researchers,but the bandwidth is somehow neglected.It is challenging to predict the network throughput of modem Web services,due to the factors of diverse and complex response,evolving Web services,and complex network transportation.In this paper,we propose a methodology of what-if analysis,named Log2Sim,to plan the bandwidth resource of Web services.Log2Sim uses a lightweight workload model to describe user behavior,an automated mining approach to obtain characteristics of workloads and responses from massive Web logs,and traffic-aware simulations to predict the impact on the bandwidth consumption and the response time in changing contexts.We use a real-life Web system and a classic benchmark to evaluate Log2Sim in multiple scenarios.The evaluation result shows that Log2Sim has good performance in the prediction of bandwidth consumption.The average relative error is 2%for the benchmark and 8% for the real-life system.As for the response time,Log2Sim cannot produce accurate predictions for every single service request,but the simulation results always show similar trends on average response time with the increase of workloads in different changing contexts.It can provide sufficient information for the system administrator in proactive bandwidth planning.

电磁功能型木塑复合材料研究进展

木塑复合材料是一种具备环境友好性以及良好性能的复合材料。开发具备电磁功能的木塑复合材料有利于提升产品的附加值并进一步拓宽产品的应用范围,具有重要的研究意义和应用价值。文中在概述常用电磁功能助剂的类型、结构、性能及其电磁原理的基础上,总结了导电型、电磁屏蔽型和抗静电型木塑复合材料的研究现状以及目前电磁功能型木塑复合材料的应用领域及行业现状;针对现有研究中存在的助剂分散性差、导电机理不明确、界面结合受影响、产业化难推广等问题,展望电磁功能型木塑复合材料的研究方向,以期为电磁功能型木塑复合材料的进一步开发和利用提供科学依据。