基于稳健词素序列和LSTM的维吾尔语短文本分类

维吾尔语是一种派生类语言,其词是由词干和词缀连接而成的。其中,词干是有实际意义的词汇单元,词缀提供语法功能。该文提出了基于词干单元和长短期记忆(LSTM)网络的维吾尔语短文本分类技术。用基于词-词素平行训练语料的稳健词素切分和词干提取方法,从互联网下载的文本中提取其词干,以此构建词干序列文本语料库,并通过Word2Vec算法映射到实数向量空间。然后用LSTM网络作为特征选择和文本分类算法进行维吾尔语短文本分类实验,并得到95.48%的分类准确率。从实验结果看,对于维吾尔语等派生类语言而言,特别是对于带噪声的文本,基于词干的分类方法有更多优异的性能。     

改进的维吾尔语Web文本后缀树聚类

该文提出了改进的维吾尔语Web文本后缀树聚类算法STCU,其中后缀树的构建以维吾尔语句子为基本单位。针对维吾尔语语言和Web文本特点,文中对词语进行词干提取,构建了维吾尔语绝对停用词表和相对停用词表,采用文档频率和词性结合的方法提取关键短语,改进了合并基类的二进制方法,根据语料类别数自动调整聚类类别阈值,利用最一般短语对聚类类别进行描述,有效地改善了文本聚类的质量。与传统的后缀树聚类算法相比,聚类全面率提高了44.51%,聚类准确率提高了11.74%,错误率降低了0.94%。实验结果表明 改进的后缀树算法在Web文本聚类的精度和效率方面具有较强的优越性。     

一种扩展Winnowing剽窃检测算法

剽窃是目前学术界和教育界面临的普遍问题,成熟的商业化剽窃检测系统运行时间和经济代价高,不适合实时性、轻量级的学生作业等日常检测。对基于文本指纹的Winnowing剽窃检测算法进行扩展,在提取指纹的同时记录文本定位及其长度信息,给出了指纹提取、文本定位、剽窃指纹索引合并等算法,实现了剽窃文本的检测、定位、标记。实验结果及算法在应用系统中实际运行状况表明,算法的扩展对其性能影响不大,普通硬件配置条件下即可满足中小规模应用需求。扩展算法在原算法轻量级、高效率、可靠性和灵活度高等特点基础上,进一步拓展了Winnowing的功能,增强了原算法的适应性和应用价值。     

基于词干的混合策略维吾尔语文本聚类特征选择方法研究

维吾尔语文本聚类中特征选择对聚类的效率和效果都有直接影响。根据维吾尔语构词法规律,在原有基于文档频率特征选择算法基础上,提出新的维吾尔语文本聚类的特征提取算法。新方法将词干作为文本的特征项,在原算法上融合了基于特征贡献度的选择方法,并使用Java语言实现了一个维吾尔语文本聚类系统。使用该系统在人工分类的文本集上进行实验,结果表明:新的特征提取算法有效地降低了文本向量空间维度,在准确率、召回率和F-Measure等指标方面均有不同程度提高。     

基于词干单元的维-哈语文本关键词提取研究

提出了基于词干单元的维吾尔语和哈萨克语（以下称维-哈语）文本关键词提取方法。维-哈语属于资源缺乏的派生类语言,词素结构分析和词干提取方法能有效地减少派生类语言的粒度容量,并且可以提高其覆盖率。从网上下载维-哈语文本,并切分成词素序列,用word2vec训练词干向量以分布式表示文本内容,再用TF-IDF算法对其词干向量进行加权处理。根据训练集关键词干向量和测试集词干向量相似度来提取关键词。实验结果表明,基于词素切分及词干向量表示的方法是在维-哈语等派生类语言关键词提取任务中的重要步骤,通过这个步骤,能够提高关键词提取的准确率。     

一种改进的维吾尔语句子相似度计算方法

在基于实例的维吾尔语汉语机器翻译系统中维吾尔语相似度计算起重要作用。维吾尔语的黏着性特性要求对单词进行词干提取。本文提出的方法结合简单的句子结构相似度计算方法,通过对单词词干提取进行句子相似度计算。小规模实验结果比较接近人工评价的句子相似度。     

关于中文文档复制检测算法的改进

文本复制检测是这样一种行为:它判断一个文档的内容是否抄袭、剽窃或者复制于另外一个或者多个文档。文档复制检测领域的算法有很多,基于句子相似度的检测算法结合了基于字符串比较的方法和基于词频统计的方法的优点,在抓住了文档的全局特征的同时又能兼顾文档的结构信息,是一种很好的算法。本文在该算法的基础上对相似度算法进行了改进,提出了一种新的面向中文文档的基于句子相似度的文档复制检测算法。本算法充分考虑了中文文档的特点,选择句子作为文档的特征单元,并解决了需要人工设定阈值的问题,提高了检测精度。实验证明,无论是在效率上,还是在准确性上,该算法都是可行的。     

基于内容的网络异常信息过滤

通过对信息过滤一般过程的分析,提出了一种基于内容的网络异常信息过滤方法。在源信息采集方面,建立了网络信息捕获构架,基于协议分析实现网络数据的提取;在信息内容处理方面,采用设立切分标志进行文本信息的预处理,在此基础上,基于向量空间模型实现文档的结构化表示;在信息匹配算法方面,通过计算文档向量之间的相似度,实现网络信息的有效过滤。     

文本指纹在旋律相似性检测中的应用研究

旋律抄袭是一个严重的问题,实现音乐旋律的相似性检测对于整治音乐抄袭具有极其重要的作用。为有效识别旋律抄袭,本文提出一种基于文本指纹的旋律相似性检测方案。该方法通过将音乐旋律转换为文本,使用N-gram算法对长旋律片段进行分片并进行哈希编码,通过MinHash算法生成文本指纹,最后使用LSH算法进行快速相似性检索,实现旋律之间的高效匹配。实验结果表明,该方案的相似性识别的平均准确率达到90%以上,能够有效识别存在剽窃行为的音乐旋律。     

基于多级文本检测的复杂文档图像扭曲矫正算法

文档的扭曲矫正是进行文档OCR(Optical Character Recognition)的基础步骤,对提高OCR的准确率有重要作用.文档图像的扭曲矫正常常依赖于文本的提取,然而目前文档图像矫正算法大都无法对复杂文档中的文本进行准确定位和分析,导致其矫正效果不理想.针对此问题,提出了一种基于全卷积网络的文字检测框架,并使用合成文档对网络进行针对性训练,可实现对字符、词、文本行三级文本信息的准确获取,进而对文本进行自适应采样并利用三次函数对页面进行三维建模,将矫正问题转化为模型参数优化问题,达到矫正复杂文档图像的目的.使用合成扭曲文档以及真实测试数据进行矫正实验,结果表明,提出的矫正方法能够对复杂文档进行精确的文本提取,明显改善了复杂文档图像矫正后的视觉效果,相比于其他算法,该算法矫正后OCR的准确率得到显著提高.     

Detection of idea plagiarism using syntax–Semantic concept extractions with genetic algorithm

Plagiarism is increasingly becoming a major issue in the academic and educational domains. Automated and effective plagiarism detection systems are direly required to curtail this information breach, especially in tackling idea plagiarism. The proposed approach is aimed to detect such plagiarism cases, where the idea of a third party is adopted and presented intelligently so that at the surface level, plagiarism cannot be unmasked. The reported work aims to explore syntax-semantic concept extractions with genetic algorithm in detecting cases of idea plagiarism. The work mainly focuses on idea plagiarism where the source ideas are plagiarized and represented in a summarized form. Plagiarism detection is employed at both the document and passage levels by exploiting the document concepts at various structural levels. Initially, the idea embedded within the given source document is captured using sentence level concept extraction with genetic algorithm. Document level detection is facilitated with word-level concepts where syntactic information is extracted and the non-plagiarized documents are pruned. A combined similarity metric that utilizes the semantic level concept extraction is then employed for passage level detection. The proposed approach is tested on PAN13-14¹plagiarism corpus for summary obfuscation data, which represents a challenging case of idea plagiarism. The performance of the current approach and its variations are evaluated both at the document and passage levels, using information retrieval and PAN plagiarism measures respectively. The results are also compared against six top ranked plagiarism detection systems submitted as a part of PAN13-14 competition. The results obtained are found to exhibit significant improvement over the compared systems and hence reflects the potency of the proposed syntax-semantic based concept extractions in detecting idea plagiarism.     

基于多种技术的混合式程序代码抄袭检测方法

在分析现有程序代码抄袭检测系统的特点及局限性的基础上,提出一种综合文本分析、结构度量和属性计数技术的混合式程序抄袭检测方法。应用文档指纹技术和Winnowing算法计算程序的文本相似度;将程序代码表示成动态控制结构树（Dynamic Control Structure tree,DCS）,运用Winnowing算法计算DCS树相似度,从而得到结构相似度;收集并统计程序中的每个变量信息,应用变量相似度算法分析变量信息节点获取变量相似度;分别赋予文本相似度、结构相似度和变量相似度一个权值,计算得到总体的代码相似度。实验结果表明,所提出的方法能够有效检测出各种抄袭行为。针对不同的抄袭门槛值,使用该方法的检测结果准确度和查全率高于JPLAG系统。特别对于结构简单的程序组,此方法和JPLAG系统检测结果的平均准确度分别为82.5%和69.5%,说明所提的方法更加有效。     

基于序列匹配的作业相似度检测系统

为辅助教师进行电子作业的批改和抄袭鉴别,设计并实现一种基于序列匹配的作业相似度检测系统。以班级为分组建立相似度计算模型,利用序列匹配算法计算公共子序列的长度,得到每组作业两两之间的相似度,并在此基础上进行聚类分析,给出可视化结果。实验结果表明,该系统具有较强的实用性,能够辅助教师在批改作业时快速高效地鉴别疑似抄袭的情况。     

Efficient privacy-preserving similar document detection

Similar document detection plays important roles in many applications, such as file management, copyright protection, plagiarism prevention, and duplicate submission detection. The state of the art protocols assume that the contents of files stored on a server (or multiple servers) are directly accessible. However, this makes such protocols unsuitable for any environment where the documents themselves are sensitive and cannot be openly read. Essentially, this assumption limits more practical applications, e.g., detecting plagiarized documents between two conferences, where submissions are confidential. We propose novel protocols to detect similar documents between two entities where documents cannot be openly shared with each other. The similarity measure used can be a simple cosine similarity on entire documents or on document fragments, enabling detection of partial copying. We conduct extensive experiments to show the practical value of the proposed protocols. While the proposed base protocols are much more efficient than the general secure multiparty computation based solutions, they are still slow for large document sets. We then investigate a clustering based approach that significantly reduces the running time and achieves over 90% of accuracy in our experiments. This makes secure similar document detection both practical and feasible.     

Text plagiarism classification using syntax based linguistic features

The proposed work models document level text plagiarism detection as a binary classification problem, where the task is to distinguish a given suspicious-source document pair as plagiarized or non-plagiarized. The objective is to explore the potency of syntax based linguistic features extracted using shallow natural language processing techniques for plagiarism classification task. Shallow syntactic features, viz., part of speech tags and chunks are utilized after effective pre-processing and filtrations for pruning the irrelevant information. The work further proposes the modelling of this classification phase as an intermediate stage, which will be post candidate source retrieval and before exhaustive passage level detections. A two-phase feature selection approach is proposed, which improves the effectiveness of classification by selecting appropriate set of features as the input to machine learning based classifiers. The proposed approach is evaluated on smaller and larger test conditions using the corpus of plagiarized short answers (PSA) and plagiarism instances collected from PAN corpus respectively. Under both the test conditions, performances are evaluated using general as well as advanced classification metrics. Another main contribution of the current work is the analysis of dependencies and impact of the extracted features, upon the type and complexity of plagiarism imposed in the documents. The proposed results are compared with the two state-of-the-art approaches and they outperform the baseline approaches significantly. This in turn reflects the cogency of syntactic linguistic features in document level plagiarism classification, especially for the instances close to manual or real plagiarism scenarios.     

Text Retrieval from Document Images Based on Word Shape Analysis

In this paper, we propose a method of text retrieval from document images using a similarity measure based on word shape analysis. We directly extract image features instead of using optical character recognition. Document images are segmented into word units and then features called vertical bar patterns are extracted from these word units through local extrema points detection. All vertical bar patterns are used to build document vectors. Lastly, we obtain the pair-wise similarity of document images by means of the scalar product of the document vectors. Four corpora of news articles were used to test the validity of our method. During the test, the similarity of document images using this method was compared with the result of ASCII version of those documents based on the N-gram algorithm for text documents.     

基于层级匹配的维吾尔文关键词文档图像检索

为实现基于关键词的维吾尔文文档图像检索,提出一种基于由粗到细层级匹配的关键词文档图像检索方法。使用改进的投影切分法将经过预处理的文档图像切分成单词图像库,使用模板匹配对关键词进行粗匹配;在粗匹配的基础上,提取单词图像的方向梯度直方图(HOG)特征向量;通过支持向量机(SVM)分类器学习特征向量,实现关键词图像检索。在包含108张文档图像的数据库中进行实验,实验结果表明,检索准确率平均值为91.14%,召回率平均值为79.31%,该方法能有效实现基于关键词的维吾尔文文档图像检索。     

代码相似性检测在程序设计教学中的应用

代码剽窃是程序设计课程中经常出现的一种作弊行为,检测剽窃的源代码、验证学生程序作业的原创性在教学中很重要。程序代码的相似度度量是剽窃检测的关键技术。本文首先对现有程序代码相似性检测技术进行研究,然后改进Halstead算法,提出了基于统计学方法程序代码相似性检测算法,最后对算法的有效性进行了实验分析。     

基于TextRank算法和互信息相似度的维吾尔文关键词提取及文本分类

针对维吾尔语文本的分类问题,提出一种基于TextRank算法和互信息相似度的维吾尔文关键词提取及文本分类方法。首先,对输入文本进行预处理,滤除非维吾尔语的字符和停用词;然后,利用词语语义相似度、词语位置和词频重要性加权的TextRank算法提取文本关键词集合;最后,根据互信息相似度度量,计算输入文本关键词集和各类关键词集的相似度,最终实现文本的分类。实验结果表明,该方案能够 提取出具有较高识别度的关键词,当关键词集大小为1250时,平均分类率达到了91.2%。     

Cross-language plagiarism detection

Cross-language plagiarism detection deals with the automatic identification and extraction of plagiarism in a multilingual setting. In this setting, a suspicious document is given, and the task is to retrieve all sections from the document that originate from a large, multilingual document collection. Our contributions in this field are as follows: (1) a comprehensive retrieval process for cross-language plagiarism detection is introduced, highlighting the differences to monolingual plagiarism detection, (2) state-of-the-art solutions for two important subtasks are reviewed, (3) retrieval models for the assessment of cross-language similarity are surveyed, and, (4) the three models CL-CNG, CL-ESA and CL-ASA are compared. Our evaluation is of realistic scale: it relies on 120,000 test documents which are selected from the corpora JRC-Acquis and Wikipedia, so that for each test document highly similar documents are available in all of the six languages English, German, Spanish, French, Dutch, and Polish. The models are employed in a series of ranking tasks, and more than 100 million similarities are computed with each model. The results of our evaluation indicate that CL-CNG, despite its simple approach, is the best choice to rank and compare texts across languages if they are syntactically related. CL-ESA almost matches the performance of CL-CNG, but on arbitrary pairs of languages. CL-ASA works best on “exact” translations but does not generalize well.