Structural Analysis for Replicating Japanese Cultural Property Braids

ABSTRACT

Historic Japanese textiles from over 1000 years ago generally show marked deterioration and only very rare examples show their original forms and much information about textile reproduction has been lost. The replication of textile braids lacks systematic methodology and is still being practiced by only few individual braiding experts. The recreation of original braids as close as possible to original braids is a part of Japan’s intangible cultural heritage. The aim of this study is to clarify the decision-making procedure through which the braiding experts can decipher the original braiding structures. As a preliminary study of this project, interviews of a braid researcher and a replicating expert, Makiko Tada were performed regarding her working practices. It is important to clarify the braiding parameters for structural analysis such as the number of transits and the balance of ridges, and it became clear that the orientation of multiple colored threads plays an important role. The expert’s replicate works were also analyzed using a text-mining statistical technique to clarify the relationship of braiding parameters. The relationship between each braiding parameter and production method such as loop manipulation and Taka-dai became clear. As a result, the process of deciphering the original braid structure has been compiled in simplified workflows, which could contribute to the standardization and improvement in efficiency of replication of cultural property braids.     

网络招聘文本技能信息自动抽取研究

[目的/意义]针对目前网络招聘文本手工抽取技能信息无法满足大数据量分析要求的问题，提出一种针对大量网络招聘文本的技能信息自动抽取方法。[方法/过程]根据网络招聘文本的特点，利用依存句法分析选取候选技能，然后提出领域相关性指标衡量候选技能，将其融入传统的术语抽取方法之中，形成一种网络招聘文本技能信息自动抽取方法。[结果/结论]实验表明，本文提出的方法能够从网络招聘文本中自动、快速、准确地抽取技能信息。     

基于深度学习的中文专利自动分类方法研究

[目的/意义] 面向当前国内专利审查和专利情报分析工作中对于海量专利分类的客观需求，设计了7种基于深度学习的专利自动分类方法，对比各种方法的分类效果，从而助力专利分类效率和效果的提升。[方法/过程] 针对传统机器学习方法存在的缺陷，基于Word2Vec、CNN、RNN、Attention机制等深度学习技术，考虑专利文本语序特征、上下文特征以及分类关键特征，设计Word2Vec+TextCNN、Word2Vec+GRU、Word2Vec+BiGRU、Word2Vec+BiGRU+TextCNN等7种深度学习模型，以中国专利为例，选取IPC主分类号的"部"作为分类依据，对比这7种模型与3种传统分类模型在中文专利分类任务中的效果。[结果/结论] 实证研究效果显示，采用考虑语序特征、上下文特征及强化关键特征的深度学习方法进行中文专利分类具有更优的分类效果。     

Populist linguistic tone in recent U.S. presidential campaign discourse: a DICTION analysis

ABSTRACT

This study analyzed the tone of public campaign remarks of right- and left-wing populist (Donald Trump and Bernie Sanders, respectively) and right and left-wing non-populist (Mitt Romney and Hillary Clinton, respectively) U.S. presidential candidates using DICTION 7.0. Findings suggest that populists tended to use a linguistic tone that is high in pessimism, group abstractness, and exclusion. Pessimism and group abstractness were positively associated with immigration language in right-wing populist speech. Commonality and “we-ness” were positively associated with populist language in left-wing populist speech.     

OA出版技术进展及对国内OA论文可见度的启示

开放获取(Open Access,OA)出版平台及OA论文的查找定位技术在近5年飞速壮大。虽然学术出版界对OA论文在引用上的优势已达成共识,但是OA论文的传播途径和获取可见度的方式仍然模糊。本文通过分析近年来OA出版平台技术、索引技术及查找定位技术的发展,深入了解它们的运作机制,从而梳理出OA论文出版体系,描绘了OA论文的传播路径,并借此分析国内OA出版在技术上的短板及未来发展方向,提出了提升国内OA论文可见度的具体实施措施,以利于提高我国OA学术出版在国际上的影响力。     

Application of machine learning techniques to assess the trends and alignment of the funded research output

Research and development activities are regarded as one of the most influencing factors of the future of a country. Large investments in research can yield a tremendous outcome in terms of a country’s overall wealth and strength. However, public financial resources of countries are often limited which calls for a wise and targeted investment. Scientific publications are considered as one of the main outputs of research investment. Although the general trend of scientific publications is increasing, a detailed analysis is required to monitor the research trends and assess whether they are in line with the top research priorities of the country. Such focused monitoring can shed light on scientific activities evolution as well as the formation of new research areas, thus helping governments to adjust priorities, if required. But monitoring the output of the funded research manually is not only very expensive and difficult, it is also subjective. Using structural topic models, in this paper we evaluated the trends in academic research performed by federally funded Canadian researchers during the time-frame of 2000–2018, covering more than 140,000 research publications. The proposed approach makes it possible to objectively and systematically monitor research projects, or any other set of documents related to research activities such as funding proposals, at large-scale. Our results confirm the accordance between the performed federally funded research projects and the top research priorities of Canada.     

预印本平台数据开放共享政策的内容构成与特点剖析

[目的 /意义]开放科学环境下,探究预印本平台的数据开放共享政策有助于保障科研利益相关者的数据质量,推动研究数据更加开放、共享、安全与透明。[方法 /过程]基于研究团队跟踪的125个预印本平台中共63份数据开放共享政策文本,利用网络调查与文本分析的方法进行内容挖掘与特点剖析。[结果 /结论 ]通过分析得出预印本平台的数据开放共享政策在数据创建、数据存储、数据发布、数据访问、数据重用5个阶段的主要特征,为更多预印本平台在未来制定完备的数据开放共享政策提供切入点与参考思路。     

网络舆情衍进指数构建与实证分析

[目的/意义]提出和构建网络舆情衍进指数，以描述网络舆情演化过程中常衍生出新的子话题的现象，对于舆情预警、预测具有重要的理论及实践意义。[方法/过程]以文本聚类结果和文本聚类有效性为依据，提出网络舆情衍进的判别标准和舆情衍进指数的构建过程，并以"教科书老赖"这一事件作为样本数据进行实证分析。[结果/结论]所构建的舆情衍进速率指数可以用于描述舆情衍进。在突发期阶段话题舆情衍进指数最高，此后逐渐下降，这一阶段的舆情衍进最为剧烈，子话题的出现呈现爆发性增长；舆情衍进指数在舆情蔓延期内出现阶梯式下降，此后保持为负值，舆情的子话题开始逐渐减少，舆情内容本身由发散转为收敛；进入消散期后，子话题数量趋于稳定。作为舆情衍进速率的测度和舆情衍进的判别方式，舆情衍进指数为舆情监管和舆情预警提供了全新的角度。     

中文电子病历的分词及实体识别研究

[目的/意义]健康医疗大数据是我国重要的基础性战略资源，本研究对中文电子病历分词与实体识别的探讨与实证较好地完成了医疗数据的信息抽取任务，对今后医疗大数据在语义层面的应用发展具有重要意义。[方法/过程]本研究首先融合权威词表、官方标准、健康网站数据及其他医学补充词库构建了词语数量级达到10万的医学词表；然后对电子病历的字段进行分词，对比了jieba工具、导入词典后的jieba、无监督学习及AC自动机4种模型的分词效果；最后，以自动分词和人工标注结果为语料，实现基于条件随机场的电子病历实体识别研究，并比较不同实体类别以及不同文本特征下的实体识别效果，选出最优模板。[结果/结论]分词结果显示，AC自动机的效果最好，F值可达82%；实体识别结果表明，"检查"和"疾病"实体的识别效果最好，而"症状"的识别效果不太理想。     

Time gap analysis by the topic model-based temporal technique

This study proposes a temporal analysis method to utilize heterogeneous resources such as papers, patents, and web news articles in an integrated manner. We analyzed the time gap phenomena between three resources and two academic areas by conducting text mining-based content analysis. To this end, a topic modeling technique, Latent Dirichlet Allocation (LDA) was used to estimate the optimal time gaps among three resources (papers, patents, and web news articles) in two research domains. The contributions of this study are summarized as follows: firstly, we propose a new temporal analysis method to understand the content characteristics and trends of heterogeneous multiple resources in an integrated manner. We applied it to measure the exact time intervals between academic areas by understanding the time gap phenomena. The results of temporal analysis showed that the resources of the medical field had more up-to-date property than those of the computer field, and thus prompter disclosure to the public. Secondly, we adopted a power-law exponent measurement and content analysis to evaluate the proposed method. With the proposed method, we demonstrate how to analyze heterogeneous resources more precisely and comprehensively.