地表径流速度对城市内涝影响规律

为分析地表径流速度对城市内涝的影响,采用一维地下排水管网与二维城区地形的动态耦合模型,选取大连市某排水区块作为研究区域,设置4种地表径流速度10种设计降雨场景,模拟分析在不同重现期设计降雨及不同地表径流速度下研究区的内涝积水特性。结果表明:随着地表径流速度降低,管道排水压力变小,管道排水达标率最高可提升48.05%,且降雨重现期越短,地表径流流速对管道排水压力的削减效果越明显;地表径流流速对检查井溢流量影响显著,随着地表径流速度降低,检查井溢流量峰值最高可减小2 750 m~3,峰现时间最长可滞后56 min,同时随着降雨重现期增长,地表径流流速对检查井溢流量的削减效果减弱;研究区低、高风险区淹没面积随地表径流速度降低,最高可分别减小1.64万、8.37万m~2,但中风险区淹没面积变化反复。     

食用槟榔货架期内品质控制研究

目的：探究食用槟榔返卤返白的原因。方法：主要通过搜集2000—2020年涉及食用槟榔卤水专利，以及相关工厂案例进行研究与分析。结果：在食用槟榔卤水的制备过程中原料的粒径大小、环境温度与湿度的高低、样品中水分含量及设备的自动化程度均可能造成食用槟榔返卤返白。结论：加工槟榔时应采取以严格控制水分、复配添加剂使用为主，工艺包装调整为辅,给予低温贮藏市售环境的方法，抑制返卤返白的产生。     

The role of Persian-language word exercise games in improving spelling of students with dyslexia: Word exercise games in improving spelling

Children with dyslexia have reduced sensitivity to phonological sounds and words, and this deficiency in lexical processing causes many problems for them. Word exercise games based on phonological awareness have emphasized the mistakes of students with dyslexia, attempting to help children avoid these mistakes. This study was conducted to investigate the effect of Persian-language word exercise games on the spelling of students with dyslexia. The design of the present study was quasi-experimental, with a pretest and posttest of an experimental group and a control group. Participants were 30 students with dyslexia from second grade to fifth grade in elementary schools in Bojnord, who completed the spelling test as a pretest and posttest. The experimental group played eleven 40-min sessions of word exercise games. The results showed that the word exercise programme improved the spelling of the children with dyslexia. This suggests that basing training on the phonological mistakes of students with dyslexia and using the word exercise games can improve their spelling.     

Examining the role of regional culture and geographical distances on the representation of unfamiliar foods in a continental-size country

This study provides an experimental-exploratory investigation about the role of regional culture and Euclidean distances on the consumers’ representation of edible insects in Brazil, a country with an extensive geographical surface. Seven hundred and eighty participants were recruited on the streets of eight cities from different Brazilian states: Manaus in Amazonas; Porto Velho in Rondônia; Macapá in Amapá; Cuiabá in Mato Grosso; Aracaju in Sergipe; Rio de Janeiro in Rio de Janeiro; Campinas in São Paulo; and Santa Maria in Rio Grande do Sul. These participating cities were considered from their cultural identity differences and geographical distances. Through a continual restricted word association task, participants were instructed to promptly verbalize the first five terms that came to their minds when stimulated with the expression “food made with edible insects”. Following, they had to score the valence of each term they produced. The dictionaries produced in each city were compared and classified into groups using the Ellegård’s index. Each group presented distinct ways of expression and attitude with respect to the inductive expression. Basically, Brazil was divided into two main groups according to their representation of edible insects: one consisted by the cities situated near the shore of the Atlantic Ocean, which present a cultural formation influenced by the European immigrants; and the other comprised the cities from the continental region that have strong cultural influence from the Amerindians. Thus, the cultural formation was more decisive to explain the similar representations among the cities than their geographical proximity. Given that, to effectively introduce a novel food in a country with varied regional culture, the marketing strategy should be focused on the values and beliefs of their culture subgroups instead of a single strategy for the whole country.     

基于深度学习的文本自动摘要方案

针对自然语言处理（NLP）生成式自动摘要领域的语义理解不充分、摘要语句不通顺和摘要准确度不够高的问题，提出了一种新的生成式自动摘要解决方案，包括一种改进的词向量生成技术和一个生成式自动摘要模型。改进的词向量生成技术以Skip-Gram方法生成的词向量为基础，结合摘要的特点，引入词性、词频和逆文本频率三个词特征，有效地提高了词语的理解；而提出的Bi-MulRnn+生成式自动摘要模型以序列映射（seq2seq）与自编码器结构为基础，引入注意力机制、门控循环单元（GRU）结构、双向循环神经网络（BiRnn）、多层循环神经网络（MultiRnn）和集束搜索，提高了生成式摘要准确性与语句流畅度。基于大规模中文短文本摘要（LCSTS）数据集的实验结果表明，该方案能够有效地解决短文本生成式摘要问题，并在Rouge标准评价体系中表现良好，提高了摘要准确性与语句流畅度。     

基于跨语言词向量模型的蒙汉查询词扩展方法研究

跨语言信息检索指以一种语言为检索词,检索出用另一种或几种语言描述的一种信息的检索技术,是信息检索领域重要的研究方向之一。近年来,跨语言词向量为跨语言信息检索提供了良好的词向量表示,受到很多学者的关注。该文首先利用跨语言词向量模型实现汉文查询词到蒙古文查询词的映射,其次提出串联式查询扩展、串联式查询扩展过滤、交叉验证筛选过滤三种查询扩展方法对候选蒙古文查询词进行筛选和排序,最后选取上下文相关的蒙古文查询词。实验结果表明: 在蒙汉跨语言信息检索任务中引入交叉验证筛选方法对信息检索结果有很大的提升。     

结合句法依存信息的方面级情感分类

引入句法依存信息到原方面术语,提出一种新的方面术语表示方法,利用Glove词向量表示单词以及单词与单词之间的依存关系,构造出包含句法依存信息的依存关系邻接矩阵和依存关系表示矩阵,利用图卷积神经网络和多头注意力机制将句法依存信息融入到方面术语中,使得方面术语表达与上下文结构高度相关。将改进后的方面词术语表示替换到现有模型后,模型泛化能力得到有效提升。对比试验和分析结果表明:该方法具有有效性和泛化性。     

黄浦江下游吴淞口站低潮位重现期研究

黄浦江为感潮河流,低潮位重现期的确定对黄浦江航道的设计具有重要意义。为了准确估计黄浦江低潮位的重现期,以黄浦江下游吴淞口站年最低潮位序列为例,在对样本进行三性审查的基础上,分别采用传统的数理统计方法和时变矩方法进行水文频率分析。结果表明:吴淞口站年最低潮位序列在1996年发生了变异;还现修正后的序列服从位置参数线性时变的GEV模型,低潮位存在缓慢的上升趋势;一致性条件下百年一遇低潮位约为0.261 m,在非一致性条件下其重现期增大为150 a。非一致性条件下的重现期增大说明黄浦江现有的航道设计标准偏安全,航道通航保证率提高。     

融合情感与语义信息的情感分析方法

在使用词嵌入法进行词转向量时，两个反义词会转换成相近的向量。如果这两个词是情感词，将会导致词的情感信息的丢失，这在情感分析任务中是不合理的。为了解决这个问题，提出了一种在词嵌入的基础上增加情感向量来获取情感信息的方法。首先利用情感词典资源构建情感向量，将其与词嵌入法得到的词向量融合在一起；然后采用双向长短期记忆（BiLSTM）网络获取文本的特征；最后对文本的情感进行分类。在4个数据集上分别对该方法与未融合情感向量的方法进行了实验。实验结果表明所提方法分类准确度与F1值都高于未融合方法，说明了加入情感向量有助于提高情感分析的性能。     

面向智能客服的句子相似度计算方法

针对金融领域中智能客服的句子相似度计算方法进行了研究。利用基于词性的分词纠正模型减少中文歧义词、金融相关词汇的分词错误；通过词向量方法和循环神经网络分别提取词语级和句子级的语义特征，并且得到句子向量；用融合层计算出句子向量间的差异特征；对差异特征进行降维和归一化得到句子相似度计算结果。实验结果表明，该方法具有较高的准确率和[F1]值。