基于BERT和LightGBM的文本关键词提取方法

传统的文本关键词提取方法忽略了上下文语义信息,不能解决一词多义问题,提取效果并不理想。基于LDA和BERT模型,文中提出LDA-BERT-LightG BM(LB-LightG BM)模型。该方法选择LDA主题模型获得每个评论的主题及其词分布,根据阈值筛选出候选关键词,将筛选出来的词和原评论文本拼接在一起输入到BERT模型中,进行词向量训练,得到包含文本主题词向量,从而将文本关键词提取问题通过LightG BM算法转化为二分类问题。通过实验对比了textrank算法、LDA算法、LightG BM算法及文中提出的LB-LightG BM模型对文本关键词提取的准确率P、召回率R以及F1。结果表明,当Top N取3～6时,F1的平均值比最优方法提升3.5%,该方法的抽取效果整体上优于实验中所选取的对比方法,能够更准确地发现文本关键词。     

Thermosensitive Gels for the Topical Administration of Diltiazem

In the present work, thermosensitive systems were prepared, characterized, and proposed for diltiazem administration in the topical treatment of anal fissures. Methylcellulose and PluronicF127 were used as gelling polymers. Some low-toxicity molecules, such as sodium glycocholate, citric acid, and lactic acid, were added to gel formulations as counterions to enhance diltiazem lipophilicity. The systems were characterized by sol-gel transition temperature, viscosity, and rheological studies. The resulting data allowed us to determine which systems presented sol-gel transition. A change from Newtonian to plastic behavior at sol-gel transition temperature was observed. An increase in diltiazem pig skin permeability and two-fold skin accumulation was observed in the presence of citric acid.     

Applying Text Analytics for Studying Research Trends in Dependability

The dependability of systems and networks has been the target of research for many years now. In the 1970s, what is now known as the top conference on dependability—The IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)—emerged gathering international researchers and sparking the interest of the scientific community. Although it started in niche systems, nowadays dependability is viewed as highly important in most computer systems. The goal of this work is to analyze the research published in the proceedings of well-established dependability conferences (i.e., DSN, International Symposium on Software Reliability Engineering (ISSRE), International Symposium on Reliable Distributed Systems (SRDS), European Dependable Computing Conference (EDCC), Latin-American Symposium on Dependable Computing (LADC), Pacific Rim International Symposium on Dependable Computing (PRDC)), while using Natural Language Processing (NLP) and namely the Latent Dirichlet Allocation (LDA) algorithm to identify active, collapsing, ephemeral, and new lines of research in the dependability field. Results show a strong emphasis on terms, like ‘security’, despite the general focus of the conferences in dependability and new trends that are related with ’machine learning’ and ‘blockchain’. We used the PRDC conference as a use case, which showed similarity with the overall set of conferences, although we also found specific terms, like ‘cyber-physical’, being popular at PRDC and not in the overall dataset.     

高分子材料导论课程中实施专题教学的探索

从高分子材料导论课程的设置意义、课程的现状分析、课程中实施专题教学改革的必要性、如何实施专题教学以及实施专题教学改革的效果和意义等几方面对高分子材料导论课程中实施专题教学进行了探讨。     

Self-Adaptive Topic Model： A Solution to the Problem of ＂Rich Topics Get Richer＂

The problem of ＂rich topics get richer＂（RTGR） is popular to the topic models,which will bring the wrong topic distribution if the distributing process has not been intervened.In standard LDA（Latent Dirichlet Allocation） model,each word in all the documents has the same statistical ability.In fact,the words have different impact towards different topics.Under the guidance of this thought,we extend ILDA（Infinite LDA） by considering the bias role of words to divide the topics.We propose a self-adaptive topic model to overcome the RTGR problem specifically.The model proposed in this paper is adapted to three questions：（1） the topic number is changeable with the collection of the documents,which is suitable for the dynamic data;（2） the words have discriminating attributes to topic distribution;（3） a selfadaptive method is used to realize the automatic re-sampling.To verify our model,we design a topic evolution analysis system which can realize the following functions：the topic classification in each cycle,the topic correlation in the adjacent cycles and the strength calculation of the sub topics in the order.The experiment both on NIPS corpus and our self-built news collections showed that the system could meet the given demand,the result was feasible.     

Power-law autocorrelated stochastic processes with long-range cross-correlations

We develop a stochastic process with two coupled variables where the absolute values of each variable exhibit long-range power-law autocorrelations and are also long-range cross-correlated. We investigate how the scaling exponents characterizing power-law autocorrelation and long-range cross-correlation behavior in the absolute values of the generated variables depend on the two parameters in our model. In particular, if the autocorrelation is stronger, the cross-correlation is also stronger. We test the utility of our approach by comparing the autocorrelation and cross-correlation properties of the time series generated by our model with data on daily returns over ten years for two major financial indices, the Dow Jones and the S&P500, and on daily returns of two well-known company stocks, IBM and Microsoft, over five years.     

锡晶须问题和对策的现状

概述了锡晶须问题和对策的现状以及今后的技术开发。     

统计模型在中文文本挖掘中的应用

本文讨论了中文文本挖掘的三个问题:分词、关键词提取和文本分类。对分词问题,介绍了基于层叠隐马尔可夫模型的ICTCLAS分词法,以及将词与词之间的分隔视为缺失数据并用EM算法求解的WDM方法;对关键词提取问题,提出了贝叶斯因子法,并介绍了使用稀疏回归的CCS方法;对文本分类问题,介绍了根据关键词频率建立分类器的方法,以及先建立主题模型再根据主题概率建立分类器的方法。本文通过两组文本数据对上述方法进行比较,并给出使用建议。     

基于多尺度上下文语义信息的图像场景分类算法

传统视觉词典模型没有考虑图像的多尺度和上下文语义共生关系.本文提出一种基于多尺度上下文语义信息的图像场景分类算法.首先,对图像进行多尺度分解,从多个尺度提取不同粒度的视觉信息;其次利用基于密度的自适应选择算法确定最优概率潜在语义分析模型主题数;然后,结合Markov随机场共同挖掘图像块的上下文语义共生信息,得到图像的多尺度直方图表示;最后结合支持向量机实现场景分类.实验结果表明,本文算法能有效利用图像的多尺度和上下文语义信息,提高视觉单词的语义准确性,从而改善场景分类性能.     

基于有监督主题模型的排序学习算法

文档表示是排序学习的关键,目前的排序学习算法多采用词袋法表示文档与查询,该方法假设词袋中的词相互独立,忽略了词之间的关系.为了表示文档中词之间的依赖关系,本研究利用文档与查询的主题特征构建排序学习模型,我们将排序函数定义为文档与查询之间的主题关系,提出了基于有监督主题模型的排序学习算法自动学习排序函数.为了评价模型的排序精度,我们在三个标准数据集(OHSUMED,MQ2007,MQ2008)上进行了实验.实验表明基于主题的排序学习算法能够发现文档与查询之间内在的语义关联,并改善排序模型的排序精度.