基于BERT和TextCNN的智能制造成熟度评估方法

随着智能制造2025目标的临近,企业为了解自身能力水平纷纷加入到智能制造成熟度评估的行列中。然而,由于智能制造成熟度评估标准的复杂性,企业缺乏其对行业水平的了解,导致企业贸然申请,浪费自身时间的同时又占用大量评估资源。鉴于此,设计了一种新的评估流程,采用文本处理算法对整个评估过程进行了重构,通过利用国标文件中智能制造成熟度评估标准,将其作为训练集,采用基于预训练语言模型与文本神经网络(BERT+TextCNN)相结合的智能评估算法代替人工评估。在真实的企业智能制造数据集上的验证表明,当BERT+TextCNN评估模型在卷积核为[2,3,4]、迭代次数为6次、学习率为3e-5时,对智能制造成熟度进行评估,准确率达到85.32%。这表明所设计的评估方法能够较准确地帮助企业完成智能制造成熟度自评估,有助于企业了解自身智能制造能力水平,制定正确的发展方向。

基于改进分层注意网络和TextCNN联合建模的暴力犯罪分级算法

为了科学、智能地对服刑人员的暴力倾向分级,将自然语言处理(NLP)中的文本分类方法引入犯罪心理学领域,提出一种基于改进分层注意网络(HAN)与TextCNN(Text Convolutional Neural Network)两通道联合建模的犯罪语义卷积分层注意网络(CCHA-Net),通过分别挖掘犯罪事实与服刑人员基本情况的语义信息,完成暴力犯罪气质分级。首先,采用Focal Loss同时替代两通道中的Cross-Entropy函数,优化样本数量不均衡问题。其次,在两通道输入层中,同时引入位置编码,改进对位置信息的感知能力;改进HAN通道,采用最大池化构建显著向量。最后,输出层都采用全局平均池化替代全连接方法,以避免过拟合。实验结果表明,与AC-BiLSTM(Attention-based Bidirectional Long Short-Term Memory with Convolution layer)、支持向量机(SVM)等17种相关基线模型相比,CCHA-Net各项指标均最优,微平均F1(Micro_F1)为99.57%,宏平均和微平均下的曲线下面积(AUC)分别为99.45%和99.89%,相较于次优的AC-BiLSTM提高了4.08、5.59和0.74个百分点,验证了CCHA-Net能有效胜任暴力犯罪气质分级任务。

基于PU-Learning和TextCNN的文献推荐方法研究

论文旨在将现有的机器学习研究成果运用到图书馆文献推荐的实际工作中,以充分发挥电子资源的作用。鉴于难以获得用户对文献资源的显式评价,因此将用户浏览、下载的文献视为正类文献,将用户未交互的文献视为未标记文献,通过卷积网络文本分类模型并结合PU-Learning算法对待推荐文献的推荐概率进行预测。实践证明该方法具有较高的精准性,能够在图书馆文献推荐实际应用中发挥作用。

Term-Based Pooling in Convolutional Neural Networks for Text Classification

To achieve good results in convolutional neural networks(CNN) for text classification task, term-based pooling operation in CNNs is proposed. Firstly, the convolution results of several convolution kernels are combined by this method, and then the results after combination are made pooling operation, three sorts of CNN models(we named TBCNN, MCT-CNN and MMCT-CNN respectively) are constructed and then corresponding algorithmic thought are detailed on this basis. Secondly, relevant experiments and analyses are respectively designed to show the effects of three key parameters(convolution kernel, combination kernel number and word embedding) on three kinds of CNN models and to further demonstrate the effect of the models proposed. The experimental results show that compared with the traditional method of text classification in CNNs, term-based pooling method is addressed that not only the availability of the way is proved, but also the performance shows good superiority.

中文科技政策文本分类:增强的TextCNN视角

近年尽管针对中文本文分类的研究成果不少,但基于深度学习对中文政策等长文本进行自动分类的研究还不多见。为此,借鉴和拓展传统的数据增强方法,提出集成新时代人民日报分词语料库(NEPD)、简单数据增强(EDA)算法、word2vec和文本卷积神经网络(TextCNN)的NEWT新型计算框架;实证部分,基于中国地方政府发布的科技政策文本进行算法校验。实验结果显示,在取词长度分别为500、750和1000词的情况下,应用NEWT算法对中文科技政策文本进行分类的效果优于RCNN、Bi-LSTM和CapsNet等传统深度学习模型,F1值的平均提升比例超过13%;同时,NEWT在较短取词长度下能够实现全文输入的近似效果,可以部分改善传统深度学习模型在中文长文本自动分类任务中的计算效率。

Text Feature Extraction and Classification Based on Convolutional Neural Network(CNN)

With the high-speed development of the Internet,a growing number of Internet users like giving their subjective comments in the BBS,blog and shopping website.These comments contains critics’attitudes,emotions,views and other information.Using these information reasonablely can help understand the social public opinion and make a timely response and help dealer to improve quality and service of products and make consumers know merchandise.This paper mainly discusses using convolutional neural network(CNN)for the operation of the text feature extraction.The concrete realization are discussed.Then combining with other text classifier make class operation.The experiment result shows the effectiveness of the method which is proposed in this paper.

一种基于BERT微调-TextCNN的电信网络诈骗案情文本分类设计

为了有效遏制电信网络诈骗案件高发多发态势,公安机关在持续实行高压严打政策的同时,还需注重打防结合,以防为先,突出精准宣传。电信网络诈骗类型多样,各具特点。通过归纳总结特征进行诈骗类型分类,可以达到对受骗者诈骗类型进行预测的目的,以帮助公安机关精准宣传。目前,警务实践中通过人工标注的方法过于依赖标注人员个人经验,进而耗费一定警力资源。本文采用了BERT模型与卷积神经网络CNN模型相结合的BERT微调-TextCNN模型。首先,利用BERT微调生成包含上下文信息的动态词向量,然后通过TextCNN提取文本局部特征,最后通过全连接层传入Softmax进行多分类。实验结果表明,在诈骗案情文本分类研究中,相比于TextCNN和BERT微调,BERT微调-TextCNN在准确率上分别提升了7.71%和6.3%,效果显著。借助BERT微调-TextCNN模型快速准确地对诈骗案情文本进行分类,让警务人员快速掌握受骗人被骗类型从而进行精准宣传,可以优化警力资源配置,节省警务成本。

Fake News Classification Using a Fuzzy Convolutional Recurrent Neural Network

In recent years,social media platforms have gained immense popularity.As a result,there has been a tremendous increase in content on social media platforms.This content can be related to an individual’s sentiments,thoughts,stories,advertisements,and news,among many other content types.With the recent increase in online content,the importance of identifying fake and real news has increased.Although,there is a lot of work present to detect fake news,a study on Fuzzy CRNN was not explored into this direction.In this work,a system is designed to classify fake and real news using fuzzy logic.The initial feature extraction process is done using a convolutional recurrent neural network(CRNN).After the extraction of features,word indexing is done with high dimensionality.Then,based on the indexing measures,the ranking process identifies whether news is fake or real.The fuzzy CRNN model is trained to yield outstanding resultswith 99.99±0.01%accuracy.This work utilizes three different datasets(LIAR,LIAR-PLUS,and ISOT)to find the most accurate model.

Recurrent Convolutional Neural Network MSER-Based Approach for Payable Document Processing

A tremendous amount of vendor invoices is generated in the corporate sector.To automate the manual data entry in payable documents,highly accurate Optical Character Recognition(OCR)is required.This paper proposes an end-to-end OCR system that does both localization and recognition and serves as a single unit to automate payable document processing such as cheques and cash disbursement.For text localization,the maximally stable extremal region is used,which extracts a word or digit chunk from an invoice.This chunk is later passed to the deep learning model,which performs text recognition.The deep learning model utilizes both convolution neural networks and long short-term memory(LSTM).The convolution layer is used for extracting features,which are fed to the LSTM.The model integrates feature extraction,modeling sequence,and transcription into a unified network.It handles the sequences of unconstrained lengths,independent of the character segmentation or horizontal scale normalization.Furthermore,it applies to both the lexicon-free and lexicon-based text recognition,and finally,it produces a comparatively smaller model,which can be implemented in practical applications.The overall superior performance in the experimental evaluation demonstrates the usefulness of the proposed model.The model is thus generic and can be used for other similar recognition scenarios.

基于权重词向量与改进TextCNN的中文新闻分类

为了解决单一深度学习模型提取信息不充分、分类效果不佳的问题,提出一种混合多神经网络的BA-Info-CNN-BiLSTM模型。该模型使用BERT作为词嵌入层,获得词的向量表示,再使用注意力机制让词获得不同权重;然后一方面将其送入改进的文本卷积神经网络(InfoCNN)中获取文本的局部信息特征,另一方面送入双向的长短时记忆网络(Bi-LSTM)中获得文本的全局信息特征;最后将提取到的局部信息和全局信息进行拼接融合,送入softmax函数中进行分类,得到分类结果。通过与其他模型进行对比实验,该模型获得了较好的分类效果,在新浪新闻和搜狐新闻数据集上分别取得了95.07%和84.95%的准确率,在一定程度上解决了单一模型捕获信息不充分的问题。

Recognition of Urdu Handwritten Alphabet Using Convolutional Neural Network (CNN)

Handwritten character recognition systems are used in every field of life nowadays,including shopping malls,banks,educational institutes,etc.Urdu is the national language of Pakistan,and it is the fourth spoken language in the world.However,it is still challenging to recognize Urdu handwritten characters owing to their cursive nature.Our paper presents a Convolutional Neural Networks(CNN)model to recognize Urdu handwritten alphabet recognition(UHAR)offline and online characters.Our research contributes an Urdu handwritten dataset(aka UHDS)to empower future works in this field.For offline systems,optical readers are used for extracting the alphabets,while diagonal-based extraction methods are implemented in online systems.Moreover,our research tackled the issue concerning the lack of comprehensive and standard Urdu alphabet datasets to empower research activities in the area of Urdu text recognition.To this end,we collected 1000 handwritten samples for each alphabet and a total of 38000 samples from 12 to 25 age groups to train our CNN model using online and offline mediums.Subsequently,we carried out detailed experiments for character recognition,as detailed in the results.The proposed CNN model outperformed as compared to previously published approaches.

English Text Sentiment Analysis Based on Convolutional Neural Network and U-network

English text sentiment orientation analysis is a fundamental problem in the field of natural language processing.The traditional word segmentation method can produce ambiguity when dealing with English text.Therefore,this paper proposes a novel English text sentiment analysis based on convolutional neural network and U-network.The proposed method uses a parallel convolution layer to learn the associations and combinations between word vectors.The results are then input into the hierarchical attention network whose basic unit is U-network to determine the affective tendency.The experimental results show that the accuracy of bias classification on the English review dataset reaches 93.45%.Compared with many existing sentiment analysis models,it has more accuracy.

CTSF:An End-to-End Efficient Neural Network for Chinese Text with Skeleton Feature

The past decade has seen the rapid development of text detection based on deep learning.However,current methods of Chinese character detection and recognition have proven to be poor.The accuracy of segmenting text boxes in natural scenes is not impressive.The reasons for this strait can be summarized into two points:the complexity of natural scenes and numerous types of Chinese characters.In response to these problems,we proposed a lightweight neural network architecture named CTSF.It consists of two modules,one is a text detection network that combines CTPN and the image feature extraction modules of PVANet,named CDSE.The other is a literacy network based on spatial pyramid pool and fusion of Chinese character skeleton features named SPPCNN-SF,so as to realize the text detection and recognition,respectively.Our model performs much better than the original model on ICDAR2011 and ICDAR2013(achieved 85%and 88%F-measures)and enhanced the processing speed in training phase.In addition,our method achieves extremely performance on three Chinese datasets,with accuracy of 95.12%,95.56%and 96.01%.

基于BERT字向量和TextCNN的农业问句分类模型分析

【目的】研究不同词向量和深度学习模型组合对农业问句分类结果的影响,为构建农业智能问答系统提供技术支撑。【方法】通过爬虫获取农业种植网等网站的问答数据,选择20000条问句进行人工标注,构建农业问句分类语料库。采用BERT对农业问句进行字符编码,利用文本卷积神经网络(TextCNN)提取问句高维度特征对农业问句进行分类。【结果】在词向量对比实验中,BERT字向量与TextCNN结合时农业问句分类F1值达93.32%,相比Word2vec字向量提高2.1%。在深度学习模型的分类精度对比方面,TextCNN与Word2vec和BERT字向量结合的F1值分别达91.22%和93.32%,均优于其他模型。在农业问句的细分试验中,BERT-TextCNN在栽培技术、田间管理、土肥水管理和其他4个类别中分类F1值分别为86.06%、90.56%、95.04%和85.55%,均优于其他深度学习模型。超参数设置方面,BERT-TextCNN农业问句分类模型卷积核大小设为[3,4,5]、学习率设为5e-5、迭代次数设为5时效果最优,该模型在数据样本不均衡的情况下,对于农业问句的平均分类准确率依然能达93.00%以上,可满足农业智能问答系统的问句分类需求。【建议】通过阿里NLP等开源平台提升数据标注质量;在分类过程中补充词频和文档特征,提高模型分类精度;农业相关政府职能部门加强合作,积极探索农业技术数字化推广和服务新模式。

针对直播弹幕的TextCNN过滤模型

网络直播的兴起,促使直播弹幕成为一种新型的交流方式。随之而来的还有各类非法弹幕。在识别非法弹幕方面,人工筛选过于低效,传统关键词过滤方法和统计机器学习方法识别率较低,且无法应对变异短文本。如何让机器更高效、更准确地识别非法弹幕以营造更好的网络环境是一个很有意义的问题。提出了基于文本卷积神经网络(TextCNN)的带噪非法短文本识别方法。通过对带噪短文本的预处理以及利用文本卷积神经网络挖掘字符间的相关特征,极大地提高了直播弹幕中非法短文本的识别率。

融合TextCNN与TextRNN模型的谣言识别方法

传统的谣言识别方法耗费人力物力并且准确率较低。为了有效识别社交网络中的谣言,提出一种基于融合模型的谣言识别方法.该方法首先通过BERT预训练模型构建文本句向量;其次构建TextCNN模型挖掘文本的语义特征,构建TextRNN模型用于挖掘文本的时序特征;最后,对两种模型进行加权融合,实现对谣言的识别.此外,还对原始主流模型进行了改进,一是借鉴Inception模型的思想来增加TextCNN模型的深度,二是将注意力机制注入TextRNN模型中,增加其可解释性和泛化能力.实验结果表明,相较于当前主流的谣言识别方法,该方法准确率可达到97.12%并且F1值可达到97.14%.

Enhanced Attention-Based Encoder-Decoder Framework for Text Recognition

Recognizing irregular text in natural images is a challenging task in computer vision.The existing approaches still face difficulties in recognizing irre-gular text because of its diverse shapes.In this paper,we propose a simple yet powerful irregular text recognition framework based on an encoder-decoder archi-tecture.The proposed framework is divided into four main modules.Firstly,in the image transformation module,a Thin Plate Spline(TPS)transformation is employed to transform the irregular text image into a readable text image.Sec-ondly,we propose a novel Spatial Attention Module(SAM)to compel the model to concentrate on text regions and obtain enriched feature maps.Thirdly,a deep bi-directional long short-term memory(Bi-LSTM)network is used to make a con-textual feature map out of a visual feature map generated from a Convolutional Neural Network(CNN).Finally,we propose a Dual Step Attention Mechanism(DSAM)integrated with the Connectionist Temporal Classification(CTC)-Attention decoder to re-weights visual features and focus on the intra-sequence relationships to generate a more accurate character sequence.The effectiveness of our proposed framework is verified through extensive experiments on various benchmarks datasets,such as SVT,ICDAR,CUTE80,and IIIT5k.The perfor-mance of the proposed text recognition framework is analyzed with the accuracy metric.Demonstrate that our proposed method outperforms the existing approaches on both regular and irregular text.Additionally,the robustness of our approach is evaluated using the grocery datasets,such as GroZi-120,Web-Market,SKU-110K,and Freiburg Groceries datasets that contain complex text images.Still,our framework produces superior performance on grocery datasets.

Deep-BERT:Transfer Learning for Classifying Multilingual Offensive Texts on Social Media

Offensive messages on social media,have recently been frequently used to harass and criticize people.In recent studies,many promising algorithms have been developed to identify offensive texts.Most algorithms analyze text in a unidirectional manner,where a bidirectional method can maximize performance results and capture semantic and contextual information in sentences.In addition,there are many separate models for identifying offensive texts based on monolin-gual and multilingual,but there are a few models that can detect both monolingual and multilingual-based offensive texts.In this study,a detection system has been developed for both monolingual and multilingual offensive texts by combining deep convolutional neural network and bidirectional encoder representations from transformers(Deep-BERT)to identify offensive posts on social media that are used to harass others.This paper explores a variety of ways to deal with multilin-gualism,including collaborative multilingual and translation-based approaches.Then,the Deep-BERT is tested on the Bengali and English datasets,including the different bidirectional encoder representations from transformers(BERT)pre-trained word-embedding techniques,and found that the proposed Deep-BERT’s efficacy outperformed all existing offensive text classification algorithms reaching an accuracy of 91.83%.The proposed model is a state-of-the-art model that can classify both monolingual-based and multilingual-based offensive texts.

Text Extraction with Optimal Bi-LSTM

Text extraction from images using the traditional techniques of image collecting,and pattern recognition using machine learning consume time due to the amount of extracted features from the images.Deep Neural Networks introduce effective solutions to extract text features from images using a few techniques and the ability to train large datasets of images with significant results.This study proposes using Dual Maxpooling and concatenating convolution Neural Networks(CNN)layers with the activation functions Relu and the Optimized Leaky Relu(OLRelu).The proposed method works by dividing the word image into slices that contain characters.Then pass them to deep learning layers to extract feature maps and reform the predicted words.Bidirectional Short Memory(BiLSTM)layers extractmore compelling features and link the time sequence fromforward and backward directions during the training phase.The Connectionist Temporal Classification(CTC)function calcifies the training and validation loss rates.In addition to decoding the extracted feature to reform characters again and linking them according to their time sequence.The proposed model performance is evaluated using training and validation loss errors on the Mjsynth and Integrated Argument Mining Tasks(IAM)datasets.The result of IAM was 2.09%for the average loss errors with the proposed dualMaxpooling and OLRelu.In the Mjsynth dataset,the best validation loss rate shrunk to 2.2%by applying concatenating CNN layers,and Relu.

An Efficient Hybrid Model for Arabic Text Recognition

In recent years,Deep Learning models have become indispensable in several fields such as computer vision,automatic object recognition,and automatic natural language processing.The implementation of a robust and efficient handwritten text recognition system remains a challenge for the research community in this field,especially for the Arabic language,which,compared to other languages,has a dearth of published works.In this work,we presented an efficient and new system for offline Arabic handwritten text recognition.Our new approach is based on the combination of a Convolutional Neural Network(CNN)and a Bidirectional Long-Term Memory(BLSTM)followed by a Connectionist Temporal Classification layer(CTC).Moreover,during the training phase of the model,we introduce an algorithm of data augmentation to increase the quality of data.Our proposed approach can recognize Arabic handwritten texts without the need to segment the characters,thus overcoming several problems related to this point.To train and test(evaluate)our approach,we used two Arabic handwritten text recognition databases,which are IFN/ENIT and KHATT.The Experimental results show that our new approach,compared to other methods in the literature,gives better results.