基于词性特征的明喻识别及要素抽取方法

比喻是一种利用事物之间的相似点建立关系的修辞方式。明喻是比喻中最常见的形式,具有明显的喻词,例如"像",用于关联本体和喻体。近年来高考语文散文类鉴赏题中多有考查明喻句的试题,为了解答此类鉴赏题,需要识别比喻句中的本体和喻体要素。该文提出了基于词性特征的明喻识别及要素抽取方法。首先将句子中词向量化表示与词性特征向量化表示进行融合,将融合后的向量输入到BiLSTM中进行训练,然后利用CRF解码出全局最优标注序列;最后得到明喻识别和要素抽取的结果。公开数据集上的实验结果表明,该方法优于已有的单任务方法;同时也将该文方法应用于北京高考语文鉴赏题中比喻句的识别与要素抽取,验证了方法的可行性。     

Carbonaceous microsphere-based superabsorbent polymer as filler for coating of NPK fertilizer: Fabrication,properties, swelling,and nitrogen release characteristics

Recently, the use of controlled release fertilizers in agriculture has resulted in huge benefits in plant growth and cultivation. Superabsorbent polymer (SAP)-coated fertilizers have the added advantage in retaining water in soil after irrigation and also reduce the nutrient release rate from soil in a controlled manner. This study aimed to produce a nitrogen–phosphorus–potassium (NPK) fertilizer coated with superabsorbent carbonaceous microspheres polymer (SPC) by inverse suspension polymerization method with water-retention and controlled release properties. Two sets of experiments were conducted: (1) three different weight percentages and (2) different materials. NPK coated with SPC showed increasing water-retention ability with respect to carbon microsphere percentages and retains >80% water at the 30th day of experiment compared with pure NPK and NPK coated with SAP. The slow release behavior of all samples was investigated by induced coupled plasma mass spectrometry spectrometry and results showed that NPK coated with SAP and SPC has a low release rate with <50% nutrient release compared with uncoated NPK at the 30th day. The release mechanism kinetics of NPK coated with SAP and SPC were studied based on the Kosmeyer–Peppas model. The mechanisms approached Fickian diffusion-controlled release as the n value for both samples was less than 0.5. © 2019 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2020 , 137, 48396.     

Understand Students Feedback Using Bi-Integrated CRF Model Based Target Extraction

Educational institutions showing interest to find the opinion of the students about their course and the instructors to enhance the teaching-learning process. For this, most research uses sentiment analysis to track students’ behavior. Traditional sentence-level sentiment analysis focuses on the whole sentence sentiment. Previous studies show that the sentiments alone are not enough to observe the feeling of the students because different words express different sentiments in a sentence. There is a need to extract the targets in a given sentence which helps to find the sentiment towards those targets. Target extraction is the subtask of targeted sentiment analysis. In this paper, we proposed the innovative model to find the targets of the given sentence using Bi-Integrated Conditional Random Fields (CRF). A Parallel fusion neural network model is designed to perform this task. We evaluate the model using the Michigan dataset and we build a dataset for target extraction from student reviews. The experimental results show that our proposed fusion model achieves better results compared to baseline models.     

临床试验逻辑核查的分类及应用

临床试验数据的清理是临床试验过程中非常重要的环节,完整、清洁的数据才能用于统计分析。本文旨在讨论临床试验数据清理过程中数据核查计划的撰写及逻辑核查的分类等,并进一步讨论近年来临床试验数字化趋势对数据的采集及清理可能带来的影响。     

平面交叉口交通控制与管理不安全因素分析

在现场调查分析交通标志、标线、信号设置存在问题,视距不良、交叉路口交通组织和渠化不当等的基础上,总结了公路平面交叉口在交通控制与管理方面常见的9个不安全因素。运用事故折减系数(CRF)统计数据分析了不安全因素引起事故的可能性,采用汽车碰撞理论分析与专家调查结合的方法,进行各事故类型的严重性分析,进一步确定了各不安全因素的危险性指数,得到其危险性排序,为交叉口安全诊断和安全保障研究提供了依据。     

基于多级规约CRF 模型景点评论观点分析方法

针对旅游发展趋势及旅游景点评论观点抽取的难题,提出一种基于机器学习的多级规约条件随机场 (conditional random field,CRF)模型的旅游景点评论观点分析方法。分析常见观点分析方法,利用CRF 算法从数据 集中提取评价观点,基于评论者关系特征构建景点虚假评论者自动识别模型对其评论观点进行过滤,并对评论观点 的相关性进行观点合并。实验结果表明：该方法较其他常见方法在准确率、召回率方面有明显提高,且查准率-召回 率曲线(precision and recall,PR)及接受者操作特征(receiver operating characteristic,ROC)曲线效果良好,对游客选 择旅游目标具有很好的决策作用。     

Enhancing TRU burning and Am transmutation in Advanced Recycling Reactor

This paper presents about conceptual designs of Advanced Recycling Reactor (ARR) focusing on enhancement in transuranics (TRU) burning and americium (Am) transmutation. The design has been conducted in the context of the Global Nuclear Energy Partnership (GNEP) seeking to close nuclear fuel cycle in ways that reduce proliferation risks, reduce the nuclear waste in the US and further improve global energy security. This study strives to enhance the TRU burning and the Am transmutation, assuming the development of related technologies in this study, while the ARR based on mature technologies was designed in the previous study. It has followed that the provided TRU burning core is designed to burn TRU at 28 kg/TW_thh, by adding moderator pins of B₄C (Enriched B-11) and the Am transmutation core will be able to transmute Am at 34 kg/TW_thh, by locating Am blanket of AmN around the TRU burning core. It indicates that these concepts improve TRU burning by 40-50% than the previous core and can transmute Am effectively, keeping the void reactivity acceptable.     

Towards subject independent continuous sign language recognition: A segment and merge approach

This paper presents a segment-based probabilistic approach to robustly recognize continuous sign language sentences. The recognition strategy is based on a two-layer conditional random field (CRF) model, where the lower layer processes the component channels and provides outputs to the upper layer for sign recognition. The continuously signed sentences are first segmented, and the sub-segments are labeled SIGN or ME (movement epenthesis) by a Bayesian network (BN) which fuses the outputs of independent CRF and support vector machine (SVM) classifiers. The sub-segments labeled as ME are discarded and the remaining SIGN sub-segments are merged and recognized by the two-layer CRF classifier; for this we have proposed a new algorithm based on the semi-Markov CRF decoding scheme. With eight signers, we obtained a recall rate of 95.7% and a precision of 96.6% for unseen samples from seen signers, and a recall rate of 86.6% and a precision of 89.9% for unseen signers.     

基于条件随机场的中医临床病历命名实体抽取

中医临床病历是中医重要的科研数据资源,但目前临床病历仍以文本为主要表达形式,对病历数据深入分析的前提是进行结构化信息抽取,而命名实体抽取是其基础性步骤。针对中医临床病历的命名实体,如症状、疾病和诱因等的抽取问题,通过手工标注的413份病历数据(以中文字为特征)与4类特征模版,将条件随机场(CRF)、隐马尔科夫模型(HMM)和最大熵马尔科夫模型(MEMM)用于中医病历命名实体抽取的实验,并进行比较分析。结果表明,结合合适的特征模版,CRF命名实体抽取方法取得了较好的性能,F1值的症状达到0.80,疾病名称达到0.74,诱因0.74。与HMM和MEMM相比,CRF有最高的准确率和召回率,是一种较为适用的中医临床病历命名实体抽取方法。     

基于半CRF模型的百科全书文本段落划分

介绍了基于半条件随机域(semi-Markov conditional random fields,简称semi-CRFs)模型的百科全书文本段落划分方法.为了克服单纯的HMM模型和CRF模型的段落类型重复问题,以经过整理的HMM模型状态的后验分布为基本依据,使用了基于词汇语义本体知识库的段落开始特征以及针对特定段落类型的提示性特征来进一步适应目标文本的特点.实验结果表明,该划分方法可以综合利用各种不同类型的信息,比较适合百科全书文本的段落结构,可以取得比单纯的HMM模型和CRF模型更好的性能.