Solving Arithmetic Word Problems of Entailing Deep Implicit Relations by Qualia Syntax-Semantic Model

Solving arithmetic word problems that entail deep implicit relations is still a challenging problem.However,significant progress has been made in solving Arithmetic Word Problems(AWP)over the past six decades.This paper proposes to discover deep implicit relations by qualia inference to solve Arithmetic Word Problems entailing Deep Implicit Relations(DIR-AWP),such as entailing commonsense or subject-domain knowledge involved in the problem-solving process.This paper proposes to take three steps to solve DIR-AWPs,in which the first three steps are used to conduct the qualia inference process.The first step uses the prepared set of qualia-quantity models to identify qualia scenes from the explicit relations extracted by the Syntax-Semantic(S2)method from the given problem.The second step adds missing entities and deep implicit relations in order using the identified qualia scenes and the qualia-quantity models,respectively.The third step distills the relations for solving the given problem by pruning the spare branches of the qualia dependency graph of all the acquired relations.The research contributes to the field by presenting a comprehensive approach combining explicit and implicit knowledge to enhance reasoning abilities.The experimental results on Math23K demonstrate hat the proposed algorithm is superior to the baseline algorithms in solving AWPs requiring deep implicit relations.

基于图像Bag-of-Words模型的无载体信息隐藏

介绍一种基于bag-of-words(BOW)模型的无载体信息隐藏方法.该方法使用BOW模型提取图像的视觉关键词(visual words,VW)以表达待隐藏的文本信息,从而实现文本信息在图像中的隐藏.首先使用BOW模型提取图像集中每幅图像的VW,构建文本信息的关键词和VW的映射关系库;然后把每幅图像分为若干子图像,统计每一幅子图像的VW频数直方图,选择频数最高的VW表示该子图像;最后根据构建的文本关键词和子图像VW的映射关系库,搜索出与待隐藏文本信息存在映射关系的子图像序列,将含有这些子图像的图像作为含密图像进行传递.实验结果和分析表明,该隐藏算法在抗隐写分析、鲁棒性和安全性方面均有良好的表现.

n-words模型下Hesse稀疏表示的图像检索算法

论文针对视觉词袋(BOVW)模型放弃图像空间结构的缺点,提出一种基于Hesse稀疏编码的图像检索算法。首先,建立n-words模型,获得图像局部特征表示。n-words模型由一系列连续视觉词获得,是图像特征的一种高级描述。该文从n=1到n=5进行试验,寻找最恰当的n值;其次,将二阶Hesse能量函数融入标准稀疏编码的目标函数,得到Hesse稀疏编码公式;最后,以获得的n-words序列作为编码特征,利用特征符号搜索算法求解最优Hesse系数,计算相似度,返回检索结果。实验在两类数据集上进行,与BOVW模型和已有的算法相比,新算法极大地提高了图像检索的准确率。

基于Bag of Words的干果图像分类研究

针对干果图像信息量大、分类精度低和耗时多的特点,提出利用Bag of Words模型提取图片的代表特征,并采用朴素贝叶斯分类器指导特征矩阵分类。结果表明,图像分类精度能达到80%,分类处理时间约为2 s。通过增加学习样本来进一步提高分类精度,将Bag of Words应用于干果图像识别和分类是可行的。

Chinese New-coined Words Management in P.R.C

The paper relies on the language management model. First of all, the thousands of new words coined each year in China can be roughly divided into eight groups. Besides, it exemplifies the problems that have occurred in communication. Last but not least, to reflect language management acts/processes, it reports the efforts the language authorities and governmental bodies have made in the struggle to solve the problems. It attempts to remind the language management agencies of the point that for the use of new words, the language users are always right as long as communication flows without problems in understanding.

A Study on Translation of Chinese Culture-loaded Words from the Per-spective of Relevance Theory

The essay tends to analyze the translation of Chinese Culture-loaded words from the perspective of Relevance Theory.The theory gains its prominence by studying the translation process and transcending the conflicts between literal and free translation. It incorporates recent work in cognitive linguistics, with ostensive-inference as its key model. Under the influence of Relevance theory, the translation of culture-loaded words is reader-oriented. Translators are obliged to help target readers to establish new assumptions to achieve equivalent response.

Vari-gram language model based on word clustering

Category-based statistic language model is an important method to solve the problem of sparse data.But there are two bottlenecks:1) The problem of word clustering.It is hard to find a suitable clustering method with good performance and less computation.2) Class-based method always loses the prediction ability to adapt the text in different domains.In order to solve above problems,a definition of word similarity by utilizing mutual information was presented.Based on word similarity,the definition of word set similarity was given.Experiments show that word clustering algorithm based on similarity is better than conventional greedy clustering method in speed and performance,and the perplexity is reduced from 283 to 218.At the same time,an absolute weighted difference method was presented and was used to construct vari-gram language model which has good prediction ability.The perplexity of vari-gram model is reduced from 234.65 to 219.14 on Chinese corpora,and is reduced from 195.56 to 184.25 on English corpora compared with category-based model.

Naxi-English Bilingual Word Alignment Based on Language Characteristics and Log-Linear Model

We propose a method that can achieve the Naxi-English bilingual word automatic alignment based on a log-linear model.This method defines the different Naxi-English structural feature functions,which are English-Naxi interval switching function and Naxi-English bilingual word position transformation function.With the manually labeled Naxi-English words alignment corpus,the parameters of the model are trained by using the minimum error,thus Naxi-English bilingual word alignment is achieved automatically.Experiments are conducted with IBM Model 3 as a benchmark,and the Naxi language constraints are introduced.The final experiment results show that the proposed alignment method achieves very good results:the introduction of the language characteristic function can effectively improve the accuracy of the Naxi-English Bilingual Word Alignment.

Word Embeddings and Semantic Spaces in Natural Language Processing

One of the critical hurdles, and breakthroughs, in the field of Natural Language Processing (NLP) in the last two decades has been the development of techniques for text representation that solves the so-called curse of dimensionality, a problem which plagues NLP in general given that the feature set for learning starts as a function of the size of the language in question, upwards of hundreds of thousands of terms typically. As such, much of the research and development in NLP in the last two decades has been in finding and optimizing solutions to this problem, to feature selection in NLP effectively. This paper looks at the development of these various techniques, leveraging a variety of statistical methods which rest on linguistic theories that were advanced in the middle of the last century, namely the distributional hypothesis which suggests that words that are found in similar contexts generally have similar meanings. In this survey paper we look at the development of some of the most popular of these techniques from a mathematical as well as data structure perspective, from Latent Semantic Analysis to Vector Space Models to their more modern variants which are typically referred to as word embeddings. In this review of algoriths such as Word2Vec, GloVe, ELMo and BERT, we explore the idea of semantic spaces more generally beyond applicability to NLP.

Investigating the Psychometric Impact of Negative Worded Items in Reading Comprehension Passages with a 3PL Cross-Classified Testlet Model

Negative worded(NW)items used in psychological instruments have been studied with the bifactor model to investigate whether the NW items form a secondary factor due to negative wording orthogonal to the measured latent construct,a validation procedure which checks whether NW items form a source of construct irrelevant variance(CIV)and hence constitute a validity threat.In the context of educational testing,however,no such validation attempts have been made.In this study,we studied the psychometric impact of NW items in an English proficiency reading comprehension test using a modeling approach similar to the bifactor model,namely the three-parameter logistic cross-classified testlet response theory(3PL CCTRT)model,to account for both guessing and possible local item dependence due to passage effect in the data set.The findings indicate that modeling the NW items with a separate factor leads to noticeable improvement in model fit,and the factor variance is marginal but nonzero.However,item and ability parameter estimates are highly similar between the 3PL CCTRT model and other models that do not model the NW items.It is concluded that the NW items introduce CIV into the data,but its magnitude is too small to change item and person ability parameter estimates to an extent of practical significance.

自然语言处理领域中的词嵌入方法综述

词嵌入作为自然语言处理任务的第一步,其目的是将输入的自然语言文本转换为模型可以处理的数值向量,即词向量,也称词的分布式表示。词向量作为自然语言处理任务的根基,是完成一切自然语言处理任务的前提。然而,国内外针对词嵌入方法的综述文献大多只关注于不同词嵌入方法本身的技术路线,而未能将词嵌入的前置分词方法以及词嵌入方法完整的演变趋势进行分析与概述。以word2vec模型和Transformer模型作为划分点,从生成的词向量是否能够动态地改变其内隐的语义信息来适配输入句子的整体语义这一角度,将词嵌入方法划分为静态词嵌入方法和动态词嵌入方法,并对此展开讨论。同时,针对词嵌入中的分词方法,包括整词切分和子词切分,进行了对比和分析;针对训练词向量所使用的语言模型,从概率语言模型到神经概率语言模型再到如今的深度上下文语言模型的演化,进行了详细列举和阐述;针对预训练语言模型时使用的训练策略进行了总结和探讨。最后,总结词向量质量的评估方法,分析词嵌入方法的当前现状并对其未来发展方向进行展望。

Research on high-performance English translation based on topic model

Retelling extraction is an important branch of Natural Language Processing(NLP),and high-quality retelling resources are very helpful to improve the performance of machine translation.However,traditional methods based on the bilingual parallel corpus often ignore the document background in the process of retelling acquisition and application.In order to solve this problem,we introduce topic model information into the translation mode and propose a topic-based statistical machine translation method to improve the translation performance.In this method,Probabilistic Latent Semantic Analysis(PLSA)is used to obtains the co-occurrence relationship between words and documents by the hybrid matrix decomposition.Then we design a decoder to simplify the decoding process.Experiments show that the proposed method can effectively improve the accuracy of translation.

An Effective Machine-Learning Based Feature Extraction/Recognition Model for Fetal Heart Defect Detection from 2D Ultrasonic Imageries

Congenital heart defect,accounting for about 30%of congenital defects,is the most common one.Data shows that congenital heart defects have seriously affected the birth rate of healthy newborns.In Fetal andNeonatal Cardiology,medical imaging technology(2D ultrasonic,MRI)has been proved to be helpful to detect congenital defects of the fetal heart and assists sonographers in prenatal diagnosis.It is a highly complex task to recognize 2D fetal heart ultrasonic standard plane(FHUSP)manually.Compared withmanual identification,automatic identification through artificial intelligence can save a lot of time,ensure the efficiency of diagnosis,and improve the accuracy of diagnosis.In this study,a feature extraction method based on texture features(Local Binary Pattern LBP and Histogram of Oriented Gradient HOG)and combined with Bag of Words(BOW)model is carried out,and then feature fusion is performed.Finally,it adopts Support VectorMachine(SVM)to realize automatic recognition and classification of FHUSP.The data includes 788 standard plane data sets and 448 normal and abnormal plane data sets.Compared with some other methods and the single method model,the classification accuracy of our model has been obviously improved,with the highest accuracy reaching 87.35%.Similarly,we also verify the performance of the model in normal and abnormal planes,and the average accuracy in classifying abnormal and normal planes is 84.92%.The experimental results show that thismethod can effectively classify and predict different FHUSP and can provide certain assistance for sonographers to diagnose fetal congenital heart disease.

基于BERT-BiLSTM-CRF模型的畜禽疫病文本分词研究

针对畜禽疫病文本语料匮乏、文本内包含大量疫病名称及短语等未登录词问题,提出了一种结合词典匹配的BERT-BiLSTM-CRF畜禽疫病文本分词模型。以羊疫病为研究对象,构建了常见疫病文本数据集,将其与通用语料PKU结合,利用BERT(Bidirectional encoder representation from transformers)预训练语言模型进行文本向量化表示;通过双向长短时记忆网络(Bidirectional long short-term memory network,BiLSTM)获取上下文语义特征;由条件随机场(Conditional random field,CRF)输出全局最优标签序列。基于此,在CRF层后加入畜禽疫病领域词典进行分词匹配修正,减少在分词过程中出现的疫病名称及短语等造成的歧义切分,进一步提高了分词准确率。实验结果表明,结合词典匹配的BERT-BiLSTM-CRF模型在羊常见疫病文本数据集上的F1值为96.38%,与jieba分词器、BiLSTM-Softmax模型、BiLSTM-CRF模型、未结合词典匹配的本文模型相比,分别提升11.01、10.62、8.3、0.72个百分点,验证了方法的有效性。与单一语料相比,通用语料PKU和羊常见疫病文本数据集结合的混合语料,能够同时对畜禽疫病专业术语及疫病文本中常用词进行准确切分,在通用语料及疫病文本数据集上F1值都达到95%以上,具有较好的模型泛化能力。该方法可用于畜禽疫病文本分词。

主题方面共享的领域主题层次模型

层次主题模型是构建主题层次的重要工具.现有的层次主题模型大多通过在主题模型中引入nCRP构造方法,为文档主题提供树形结构的先验分布,但无法生成具有明确领域涵义的主题层次结构,即领域主题层次.同时,领域主题不仅存在层次关系,而且不同父主题下的子主题之间还存在子领域方面共享的关联关系,在现有主题关系研究中没有合适的模型来生成这种领域主题层次.为了从领域文本中自动、有效地挖掘出领域主题的层次关系和关联关系,在4个方面进行创新研究.首先,通过主题共享机制改进nCRP构造方法,提出nCRP+层次构造方法,为主题模型中的主题提供具有分层主题方面共享的树形先验分布;其次,结合nCRP+和HDP模型构建重分层的Dirichlet过程,提出rHDP(reallocated hierarchical Dirichlet processes)层次主题模型;第三,结合领域分类信息、词语语义和主题词的领域代表性,定义领域知识,包括基于投票机制的领域隶属度、词语与领域主题的语义相关度和层次化的主题-词语贡献度;最后,通过领域知识改进rHDP主题模型中领域主题和主题词的分配过程,提出结合领域知识的层次主题模型rHDP_DK(rHDP with domain knowledge),并改进采样过程.实验结果表明,基于nCRP+的层次主题模型在评价指标方面均优于基于nCRP的层次主题模型(hLDA,nHDP)和神经主题模型(TSNTM);通过rHDP_DK模型生成的主题层次结构具有领域主题层次清晰、关联子主题的主题词领域差异明确的特点.此外,该模型将为领域主题层次提供一个通用的自动挖掘框架.

基于A-BiLSTM和CNN的文本分类

为解决单一神经网络不能获取准确全局文本信息的问题,提出一种基于A-BiLSTM双通道和优化CNN的文本分类模型。A-BiLSTM双通道层使用注意力机制关注对文本分类贡献值较大的部分,并用BiLSTM提取文本中上下文语义信息;A-BiLSTM双通道层中将两者输出的特征信息融合,得到高级语义;A-BiLSTM双通道层后,使用优化CNN的强学习能力提取关键局部特征,得到最终文本特征表示。分类器输出文本信息的类别。实验结果表明,该模型分类效果优于其它对比模型,具有良好的泛化能力。

基于复杂网络的在线口碑传播模型研究

在线口碑已成为信息传播领域的核心力量,对其进行系统分析对于理解当代社交媒体环境中的消费者行为至关重要。论文引入了传播激活和接受激活的概念,基于病毒传播的SIR模型构建在线口碑传播模型,并运用复杂网络和系统仿真的方法模拟在线口碑传播过程,深入探讨了不同因素对在线口碑传播规模的影响,识别了在线口碑传播网络中各个节点的特征并分析了网络的结构特性。结果表明,不同因素对在线口碑传播规模的作用不同,且关键节点和免疫节点具有不同的属性特征。此外,研究还发现在线口碑传播网络具有小世界特性和无标度特性,该结论进一步丰富了在线口碑传播的理论框架,也为企业网络营销策略及产品质量追溯的优化等提供一定的应用参考。

文本相似度计算方法综述

文本相似度计算是自然语言处理的一部分,用来计算两个词、句子及文本之间的相似程度,具有多种应用场景,文本相似度计算的研究对于人工智能的发展有着重要作用。文本相似度计算起初基于字符串表面,随着词向量的提出,文本相似度计算可进行基于统计以及深度学习的建模与计算,也可与预训练模型相结合。首先,将文本相似度计算方法分为基于字符串、基于词向量、基于预训练模型、基于深度学习、其他方法5类,并对这些方法进行简要介绍。然后,根据不同文本相似度计算方法的原理,具体介绍了编辑距离、汉明距离、词袋模型、向量空间模型(VSM)、深度结构语义模型(DSSM)、句子嵌入的简单对比学习(SimCSE)等常见方法。最后,对文本相似度计算常用的数据集以及评价标准进行整理和分析,并对文本相似度计算的未来发展进行展望。

考虑网络口碑的供应链定价与协调研究

随着电子商务和社交网络的迅速发展,网络口碑正在影响和改变消费者的购买习惯,并对企业决策产生重要影响。本文考虑由一个制造商和一个零售商组成的二级供应链,通过建立两阶段定价模型研究网络口碑对供应链定价和协调的影响。首先,文章分析了集中决策下网络口碑对供应链最优定价策略和整体利润的影响;其次,设计批发价契约和收益共享契约对分散决策下的供应链进行协调。研究表明:当受正面口碑影响时,系统会降低第一阶段价格,提高第二阶段价格,且口碑影响力度越大,两阶段的价格差异越小,供应链整体利润越高;当受负面口碑影响时,系统会提高第一阶段价格,降低第二阶段价格,且口碑影响力度越大,两阶段的价格差异越大,供应链整体利润越低;批发价契约无法实现供应链的协调,收益共享契约可以同时改善制造商、零售商和供应链整体利润,实现供应链协调。

英语单词学习推荐模型在教学改革中的应用研究

在人工智能技术的背景下,文章主要探讨了英语单词学习的推荐方法。其中,建立了1个基于人工智能的英语单词学习推荐模型,该模型利用用户的学习行为数据和单词特征进行训练,旨在为用户提供个性化的单词推荐。实验验证结果显示,相较于传统方法,该模型具有更高的准确性和可靠性,能够有效提升英语单词学习的效果。