基于ERNIE-BiGRU模型的摘要语步自动识别研究

学术文献的摘要是对文献主要内容的浓缩,摘要不同部分的语步具有不同的信息,语步的自动识别和抽取对于学术摘要的后续研究有着重要的应用价值,而目前语步识别的研究相对较少,并且相关算法的效果还需要提高。针对上述问题,该文提出了一种基于ERNIE-BiGRU模型的语步识别算法。该算法首先结合中文句法分析理论提出基于句法依存关系的多语步结构拆分法,对学术文献摘要多语步结构进行自动拆分,获得多个单语步结构;然后构建用于训练的单语步结构语料库,并利用知识增强语义表示预训练模型,训练出句子级词向量;最后将训练出的单语步结构词向量信息输入双向门限循环单元(BiGRU)进行摘要语步自动化识别,取得了良好的效果。实验结果表明,该算法具有较好的鲁棒性和较高的识别精度,在结构化和非结构化摘要上的识别准确率分别达到了96.57%和93.75%。     

基于Bert预训练模型的虚假新闻文本检测

虚假新闻剥夺了人们获取真相的权利,也给社会和国家带来了许多危害。文中以虚假新闻文本为例,分析和验证了多种预训练语言模型在虚假新闻文本分类上的分类效果。经实验证明,相较于其他语言模型,Bert预训练语言模型取得了较好的结果,预测准确率为86.97%,召回率为88.12%,F1值为87.54%。     

A Case Report of Germline Compound Heterozygous Mutations in the BRCA1 Gene of an Ovarian and Breast Cancer Patient

The germline carrier of the BRCA1 pathogenic mutation has been well proven to confer an increased risk of breast and ovarian cancer. Despite BRCA1 biallelic pathogenic mutations being extremely rare, they have been reported to be embryonically lethal or to cause Fanconi anemia (FA). Here we describe a patient who was a 48-year-old female identified with biallelic pathogenic mutations of the BRCA1 gene, with no or very subtle FA-features. She was diagnosed with ovarian cancer and breast cancer at the ages of 43 and 44 and had a strong family history of breast and gynecological cancers.     

A hybrid knowledge and ensemble classification approach for prediction of venous thromboembolism

Clinical narratives such as progress summaries, lab reports, surgical reports, and other narrative texts contain key biomarkers about a patient's health. Evidence-based preventive medicine needs accurate semantic and sentiment analysis to extract and classify medical features as the input to appropriate machine learning classifiers. However, the traditional approach of using single classifiers is limited by the need for dimensionality reduction techniques, statistical feature correlation, a faster learning rate, and the lack of consideration of the semantic relations among features. Hence, extracting semantic and sentiment-based features from clinical text and combining multiple classifiers to create an ensemble intelligent system overcomes many limitations and provides a more robust prediction outcome. The selection of an appropriate approach and its interparameter dependency becomes key for the success of the ensemble method. This paper proposes a hybrid knowledge and ensemble learning framework for prediction of venous thromboembolism (VTE) diagnosis consisting of the following components: a VTE ontology, semantic extraction and sentiment assessment of risk factor framework, and an ensemble classifier. Therefore, a component-based analysis approach was adopted for evaluation using a data set of 250 clinical narratives where knowledge and ensemble achieved the following results with and without semantic extraction and sentiment assessment of risk factor, respectively: a precision of 81.8% and 62.9%, a recall of 81.8% and 57.6%, an F measure of 81.8% and 53.8%, and a receiving operating characteristic of 80.1% and 58.5% in identifying cases of VTE.     

中医学视角下城市物质空间的生命要素探析

通过借鉴中医学整体观和生命观的相关理论,从认识城市有机体的生命属性入手,发现并提炼能够产生和传递城市运营所需各种能量的生命要素:廊道和功能体。阐释了其多层级、多性质和多形态的特点,提出了功能体有动力、廊道成系统、敏感点有活力的疏通策略,旨在促进城市各种能量的有机循环,从而维护城市的健康与安全,提高城市生活的效率与质量。     

Indoor solid fuel use for heating and cooking with blood pressure and hypertension: A cross-sectional study among middle-aged and older adults in China

A cross-sectional study was conducted to investigate the impact of solid fuel use for heating and cooking on blood pressure (BP) and hypertension, using data from the China Health and Retirement Longitudinal Study (CHARLS). The primary fuels used for indoor heating and cooking were collected by questionnaires, respectively. Hypertension was defined based on self-report of physician's diagnosis, and/or measured BP, and/or anti-hypertensive medication use. Multivariate logistic regression models were constructed to assess the associations. Among 10 450 eligible participants, 68.2% and 57.2% used indoor solid fuel for heating and cooking, respectively. Compared with none/clean fuel users, solid fuel for heating was associated with elevated BP (adjusted β: 2.02, 95% CI: 1.04–3.01 for systolic BP; adjusted β: 1.36, 95% CI: 0.78–1.94 for diastolic BP) and increased risk of hypertension (adjusted odds ratio: 1.15, 95% CI: 1.03–1.29). The impact of indoor solid fuel for heating on BP was more evident in rural and north residents, and hypertensive patients. We did not detect any significant associations between solid fuel use for cooking and BP/hypertension. Indoor solid fuel use is prevalent in China, especially in the rural areas. Its negative impact on BP suggested that modernization of household fuel use may help to reduce the burden of hypertension in China.     

基于微博用户兴趣话题的相似用户挖掘

相似用户挖掘是提高社交网络服务质量的重要途径，在面向大数据的社交网络时代，准确的相似用户挖掘对于用户和互联网企业等都有重要的意义，而根据用户自己的兴趣话题挖掘的相似用户更符合相似用户的要求。提出了一种基于用户兴趣话题进行相似用户挖掘的方法。该方法首先使用TextRank话题提取方法对用户进行兴趣话题提取，再对用户发表内容进行训练，计算出所有词之间的相似度。提出CP（Corresponding Position similarity）、CPW（Corresponding Position Weighted similarity）、AP（All Position similarity）、APW（All Position Weighted similarity）四种用户兴趣话题词相似度计算方法，通过用户和相似用户间关注、粉丝重合率验证相似用户挖掘效果，APW similarity的相似用户的关注/粉丝重合百分比为1.687%，优于提出的其他三种算法，分别提高了26.3%、2.8%、12.4%，并且比传统的文本相似度方法Jaccard相似度、编辑距离算法、余弦相似度分别提高了20.4%、21.2%、45.0%。因此APW方法可以更加有效地挖掘出用户的相似用户。     

基于查询的新闻多文档自动摘要技术研究

针对新闻文本领域,该文提出一种基于查询的自动文本摘要技术,更加有针对性地满足用户信息需求。根据句子的TF-IDF、与查询句的相似度等要素,计算句子权重,并根据句子指示的时间给定不同的时序权重系数,使得最近发生的新闻内容具有更高的权重,最后使用最大边界相关的方法选择摘要句。通过与基于TF-IDF、Text-Rank、LDA等六种方法的对比,该摘要方法ROUGE评测指标上优于其他方法。从结合评测结果及摘要示例可以看出,该文提出的方法可以有效地从新闻文档集中摘取核心信息,满足用户查询内容的信息需求。     

M-estimator based Chinese Remainder Theorem with few remainders using a Kroenecker product based mapping vector

The Chinese Remainder Theorem (CRT) explains how to estimate an integer-valued number from the knowledge of the remainders obtained by dividing such unknown integer by co-prime integers. As an algebraic theorem, CRT is the basis for several techniques concerning data processing. For instance, considering a single-tone signal whose frequency value is above the sampling rate, the respective peak in the DFT informs the impinging frequency value modulo the sampling rate. CRT is nevertheless sensitive to errors in the remainders, and many efforts have been developed in order to improve its robustness. In this paper, we propose a technique to estimate real-valued numbers by means of CRT, employing for this goal a Kroenecker based M-Estimation (ME), specially suitable for CRT systems with low number of remainders. Since ME schemes are in general computationally expensive, we propose a mapping vector obtained via Kroenecker products which considerably reduces the computational complexity. Furthermore, our proposed technique enhances the probability of estimating an unknown number accurately even when the errors in the remainders surpass 1/4 of the greatest common divisor of all moduli. We also provide a version of the mapping vectors based on tensorial n-mode products, delivering in the end the same information of the original method. Our approach outperforms the state-of-the-art CRT methods not only in terms of percentage of successful estimations but also in terms of smaller average error.     

基于多元神经网络融合的分布式资源空间文本分类研究

针对实体产业对科技资源的服务需求,以服务效应作为资源文本分类标准,提出一种基于多元神经网络融合的分布式资源空间文本分类模型。设计了包含词嵌入层、卷积层、双向门控循环单元层、注意力机制层和softmax层的多元神经网络通路;在此基础上采用基于需求—效应—资源分类策略,完成了从定性科技资源需求到定量资源服务效应求解,再到定性科技资源输出的映射变换,重点解决了分布式科技资源局部和全局语义特征形式多样、文本长距离依赖特征显著、重要资源信息难以准确识别的问题,进而从分布式科技资源空间中快速准确地获取效应知识,提升实体产业产品研发效率和创新能力;通过万方专利科技资源数据集验证了所提方法的可行性和有效性,为更加全面地挖掘资源文本特征和按需服务实体产业提供了一种新的思路和手段。