基于SWPF2vec和DJ-TextRCNN的古籍文本主题分类研究

以编目分类和规则匹配为主的古籍文本主题分类方法存在工作效能低、专家知识依赖性强、分类依据单一化、古籍文本主题自动分类难等问题。对此,本文结合古籍文本内容和文字特征,尝试从古籍内容分类得到符合研究者需求的主题,推动数字人文研究范式的转型。首先,参照东汉古籍《说文解字》对文字的分析方式,以前期标注的古籍语料数据集为基础,构建全新的“字音(说)-原文(文)-结构(解)-字形(字)”四维特征数据集。其次,设计四维特征向量提取模型(speaking,word,pattern,and font to vector,SWPF2vec),并结合预训练模型实现对古籍文本细粒度的特征表示。再其次,构建融合卷积神经网络、循环神经网络和多头注意力机制的古籍文本主题分类模型(dianji-recurrent convolutional neural networks for text classification,DJ-TextRCNN)。最后,融入四维语义特征,实现对古籍文本多维度、深层次、细粒度的语义挖掘。在古籍文本主题分类任务上,DJ-TextRCNN模型在不同维度特征下的主题分类准确率均为最优,在“说文解字”四维特征下达到76.23%的准确率,初步实现了对古籍文本的精准主题分类。

CVTD: A Robust Car-Mounted Video Text Detector

Text perception is crucial for understanding the semantics of outdoor scenes,making it a key requirement for building intelligent systems for driver assistance or autonomous driving.Text information in car-mounted videos can assist drivers in making decisions.However,Car-mounted video text images pose challenges such as complex backgrounds,small fonts,and the need for real-time detection.We proposed a robust Car-mounted Video Text Detector(CVTD).It is a lightweight text detection model based on ResNet18 for feature extraction,capable of detecting text in arbitrary shapes.Our model efficiently extracted global text positions through the Coordinate Attention Threshold Activation(CATA)and enhanced the representation capability through stacking two Feature Pyramid Enhancement Fusion Modules(FPEFM),strengthening feature representation,and integrating text local features and global position information,reinforcing the representation capability of the CVTD model.The enhanced feature maps,when acted upon by Text Activation Maps(TAM),effectively distinguished text foreground from non-text regions.Additionally,we collected and annotated a dataset containing 2200 images of Car-mounted Video Text(CVT)under various road conditions for training and evaluating our model’s performance.We further tested our model on four other challenging public natural scene text detection benchmark datasets,demonstrating its strong generalization ability and real-time detection speed.This model holds potential for practical applications in real-world scenarios.

Text-to-SQL文本信息处理技术研究综述

信号与信息处理的需求日益增加,离不开数据处理技术,数据处理需要数据库的支持,然而没有经过训练的使用者会因为不熟悉数据库操作产生诸多问题。文本转结构化查询语言(Text to Structured Query Language,Text-to-SQL)的出现,使用户无需掌握结构化查询语言(Structured Query Language,SQL)也能够熟练操作数据库。介绍Text-to-SQL的研究背景及面临的挑战;介绍Text-to-SQL关键技术、基准数据集、模型演变及最新研究进展,关键技术包括Transformer等主流技术,用于模型训练的基准数据集包括WikiSQL和Spider;介绍Text-to-SQL不同阶段模型的特点,详细阐述Text-to-SQL最新研究成果的工作原理,包括模型构建、解析器设计及数据集生成;总结Text-to-SQL未来的发展方向及研究重点。

Assessing trends in wildland-urban interface fire research through text mining: a comprehensive analysis of published literature

Research on fires at the wildland-urban inter-face(WUI)has generated significant insights and advance-ments across various fields of study.Environmental,agri-culture,and social sciences have played prominent roles in understanding the impacts of fires in the environment,in protecting communities,and addressing management challenges.This study aimed to create a database using a text mining technique for global researchers interested in WUI-projects and highlighting the interest of countries in this field.Author’s-Keywords analysis emphasized the dominance of fire science-related terms,especially related to WUI,and identified keyword clusters related to the WUI fire-risk-assessment-system-“exposure”,“danger”,and“vulnerability”within wildfire research.Trends over the past decade showcase shifting research interests with a growing focus on WUI fires,while regional variations highlighted that the“exposure”keyword cluster received greater atten-tion in the southern Europe and South America.However,vulnerability keywords have relatively a lower representation across all regions.The analysis underscores the interdisci-plinary nature of WUI research and emphasizes the need for targeted approaches to address the unique challenges of the wildland-urban interface.Overall,this study provides valu-able insights for researchers and serves as a foundation for further collaboration in this field through the understanding of the trends over recent years and in different regions.

Leveraging Uncertainty for Depth-Aware Hierarchical Text Classification

Hierarchical Text Classification(HTC)aims to match text to hierarchical labels.Existing methods overlook two critical issues:first,some texts cannot be fully matched to leaf node labels and need to be classified to the correct parent node instead of treating leaf nodes as the final classification target.Second,error propagation occurs when a misclassification at a parent node propagates down the hierarchy,ultimately leading to inaccurate predictions at the leaf nodes.To address these limitations,we propose an uncertainty-guided HTC depth-aware model called DepthMatch.Specifically,we design an early stopping strategy with uncertainty to identify incomplete matching between text and labels,classifying them into the corresponding parent node labels.This approach allows us to dynamically determine the classification depth by leveraging evidence to quantify and accumulate uncertainty.Experimental results show that the proposed DepthMatch outperforms recent strong baselines on four commonly used public datasets:WOS(Web of Science),RCV1-V2(Reuters Corpus Volume I),AAPD(Arxiv Academic Paper Dataset),and BGC.Notably,on the BGC dataset,it improvesMicro-F1 andMacro-F1 scores by at least 1.09%and 1.74%,respectively.

Ensemble Filter-Wrapper Text Feature Selection Methods for Text Classification

Feature selection is a crucial technique in text classification for improving the efficiency and effectiveness of classifiers or machine learning techniques by reducing the dataset’s dimensionality.This involves eliminating irrelevant,redundant,and noisy features to streamline the classification process.Various methods,from single feature selection techniques to ensemble filter-wrapper methods,have been used in the literature.Metaheuristic algorithms have become popular due to their ability to handle optimization complexity and the continuous influx of text documents.Feature selection is inherently multi-objective,balancing the enhancement of feature relevance,accuracy,and the reduction of redundant features.This research presents a two-fold objective for feature selection.The first objective is to identify the top-ranked features using an ensemble of three multi-univariate filter methods:Information Gain(Infogain),Chi-Square(Chi^(2)),and Analysis of Variance(ANOVA).This aims to maximize feature relevance while minimizing redundancy.The second objective involves reducing the number of selected features and increasing accuracy through a hybrid approach combining Artificial Bee Colony(ABC)and Genetic Algorithms(GA).This hybrid method operates in a wrapper framework to identify the most informative subset of text features.Support Vector Machine(SVM)was employed as the performance evaluator for the proposed model,tested on two high-dimensional multiclass datasets.The experimental results demonstrated that the ensemble filter combined with the ABC+GA hybrid approach is a promising solution for text feature selection,offering superior performance compared to other existing feature selection algorithms.

Analyzing COVID-19 Discourse on Twitter: Text Clustering and Classification Models for Public Health Surveillance

Social media has revolutionized the dissemination of real-life information,serving as a robust platform for sharing life events.Twitter,characterized by its brevity and continuous flow of posts,has emerged as a crucial source for public health surveillance,offering valuable insights into public reactions during the COVID-19 pandemic.This study aims to leverage a range of machine learning techniques to extract pivotal themes and facilitate text classification on a dataset of COVID-19 outbreak-related tweets.Diverse topic modeling approaches have been employed to extract pertinent themes and subsequently form a dataset for training text classification models.An assessment of coherence metrics revealed that the Gibbs Sampling Dirichlet Mixture Model(GSDMM),which utilizes trigram and bag-of-words(BOW)feature extraction,outperformed Non-negative Matrix Factorization(NMF),Latent Dirichlet Allocation(LDA),and a hybrid strategy involving Bidirectional Encoder Representations from Transformers(BERT)combined with LDA and K-means to pinpoint significant themes within the dataset.Among the models assessed for text clustering,the utilization of LDA,either as a clustering model or for feature extraction combined with BERT for K-means,resulted in higher coherence scores,consistent with human ratings,signifying their efficacy.In particular,LDA,notably in conjunction with trigram representation and BOW,demonstrated superior performance.This underscores the suitability of LDA for conducting topic modeling,given its proficiency in capturing intricate textual relationships.In the context of text classification,models such as Linear Support Vector Classification(LSVC),Long Short-Term Memory(LSTM),Bidirectional Long Short-Term Memory(BiLSTM),Convolutional Neural Network with BiLSTM(CNN-BiLSTM),and BERT have shown outstanding performance,achieving accuracy and weighted F1-Score scores exceeding 80%.These results significantly surpassed other models,such as Multinomial Naive Bayes(MNB),Linear Support Vector Machine(LSVM),and Logistic Regression(LR),which achieved scores in the range of 60 to 70 percent.

A Comparative Study of Artificial Intelligence and Translation Software in Chinese-English Translation:A Focus on Literary and Technical Texts

In recent years,the domain of machine translation has experienced remarkable growth,particularly with the emergence of neural machine translation,which has significantly enhanced both the accuracy and fluency of translation.At the same time,AI also showed its tremendous advancement,with its capabilities now extending to assisting users in a multitude of tasks,including translation,garnering attention across various sectors.In this paper,the author selects representative sentences from both literary and scientific texts,and translates them using two translation software and two AI tools for comparison.The results show that all four translation tools are very efficient and can help with simple translation tasks.However,the accuracy of terminology needs to be improved,and it is difficult to make adjustments based on the characteristics of the target language.It is worth mentioning that one of the advantages of AI is its interactivity,which allows it to modify the translation according to the translator’s needs.

A Study on Short Text Matching Method Based on KS-BERT Algorithm

To improve the accuracy of short text matching,a short text matching method with knowledge and structure enhancement for BERT(KS-BERT)was proposed in this study.This method first introduced external knowledge to the input text,and then sent the expanded text to both the context encoder BERT and the structure encoder GAT to capture the contextual relationship features and structural features of the input text.Finally,the match was determined based on the fusion result of the two features.Experiment results based on the public datasets BQ_corpus and LCQMC showed that KS-BERT outperforms advanced models such as ERNIE 2.0.This Study showed that knowledge enhancement and structure enhancement are two effective ways to improve BERT in short text matching.In BQ_corpus,ACC was improved by 0.2%and 0.3%,respectively,while in LCQMC,ACC was improved by 0.4%and 0.9%,respectively.

基于TextCNN-Attention-BiLSTM融合模型的煤矿隐患文本分类研究

为实现大量煤矿隐患文本的迅速、精确分类,及时了解安全概况并加以管理。首先,选取安全文库网中多个煤矿隐患数据库为实验数据源,对煤矿隐患文本进行预处理,包括去除噪声词、分词和词向量表示等;其次,利用TextCNN对文本进行卷积操作,提取不同尺寸的特征表示,再利用BiLSTM模型对得到的特征向量进行时序建模,并结合注意力机制(Attention),从而更好地关注文本中关键信息,捕捉文本全局语义信息;最后,利用全连接层的多标签分类器预测文本隐患类别。实验结果表明:TextCNN-Attention-BiLSTM融合模型在准确率、精确率、召回率和F 1值上均达到92%以上,为煤矿隐患文本分类提供了一种更加准确和有效的解决方案,对煤矿安全管理优化具有重要意义。

多视图融合DJ-TextRCNN的古籍文本主题推荐研究

传统编目分类和规则匹配方法存在工作效能低、过度依赖专家知识、缺乏对古籍文本自身语义的深层次挖掘、编目主题边界模糊、较难实现对古籍文本领域主题的精准推荐等问题。为此,本文结合古籍语料特征探究如何实现精准推荐符合研究者需求的文本主题内容的方法,以推动数字人文研究的进一步发展。首先,选取本课题组前期标注的古籍语料数据进行主题类别标注和视图分类;其次,构建融合BERT(bidirectional encoder representation from transformers)预训练模型、改进卷积神经网络、循环神经网络和多头注意力机制的语义挖掘模型;最后,融入“主体-关系-客体”多视图的语义增强模型,构建DJ-TextRCNN(DianJi-recurrent convolutional neural networks for text classification)模型实现对典籍文本更细粒度、更深层次、更多维度的语义挖掘。研究结果发现,DJ-TextRCNN模型在不同视图下的古籍主题推荐任务的准确率均为最优。在“主体-关系-客体”视图下,精确率达到88.54%,初步实现了对古籍文本的精准主题推荐,对中华文化深层次、细粒度的语义挖掘具有一定的指导意义。

Text Type and C-E Translation of Public Signs

This paper contends that the public sign is a kind of text with such vocative functions as indicating,instructing,restricting,prohibiting,persuading,and publicizing,so it falls into the type of vocative texts.The paper suggests that conveying the vocative function of the public sign is the essential task of the translator,so as to achieve the intended effect of the public sign.

基于语义增强模式链接的Text-to-SQL模型

为优化基于异构图编码器的Text-to-SQL生成效果,提出SELSQL模型。首先,模型采用端到端的学习框架,使用双曲空间下的庞加莱距离度量替代欧氏距离度量,以此优化使用探针技术从预训练语言模型中构建的语义增强的模式链接图;其次,利用K头加权的余弦相似度以及图正则化方法学习相似度度量图使得初始模式链接图在训练中迭代优化;最后,使用改良的关系图注意力网络(RGAT)图编码器以及多头注意力机制对两个模块的联合语义模式链接图进行编码,并且使用基于语法的神经语义解码器和预定义的结构化语言进行结构化查询语言(SQL)语句解码。在Spider数据集上的实验结果表明,使用ELECTRA-large预训练模型时,SELSQL模型比最佳基线模型的准确率提升了2.5个百分点,对于复杂SQL语句生成的提升效果很大。

CINO-TextGCN:融合CINO与TextGCN的藏文文本分类模型研究

为提高藏文新闻文本分类准确性,文章提出一种融合少数民族语言预训练模型(Chinese Minority Pr-etrained Language Model,CINO)和图卷积神经网络模型(Text Graph Convolutional Networks,TextGCN)的方法,即CINO-TextGCN模型。为有效评测该模型对藏文文本的分类性能,自建了较大规模和较高质量的藏文新闻文本公开数据集TNEWS(https://github.com/LG2016/CINO-TextGCN),通过实验发现,CINO-Text-GCN在公开数据集TNCC上的准确率为74.20%,在TNEWS上为83.96%。因此,该融合模型能够较好地捕捉到藏文文本语义,提升藏文文本分类性能。

Adapter Based on Pre-Trained Language Models for Classification of Medical Text

We present an approach to classify medical text at a sentence level automatically.Given the inherent complexity of medical text classification,we employ adapters based on pre-trained language models to extract information from medical text,facilitating more accurate classification while minimizing the number of trainable parameters.Extensive experiments conducted on various datasets demonstrate the effectiveness of our approach.

基于Bert-TextCNN的开源威胁情报文本的多标签分类方法

开源威胁情报对网络安全防护十分重要,但其存在着分布广、形式多、噪声大的特点.所以如何能对收集到的海量开源威胁情报进行高效的整理和分析就成为亟需解决的问题.因此,探索了一种以Bert-TextCNN模型为基础且同时考虑标题、正文和正则判断的多标签分类方法.根据情报源发布文本的特点,设置正则判断规则,以弥补模型的欠缺;为更全面反映开源威胁情报文本所涉及的威胁主题,针对标题和正文分别设置了Bert-TextCNN多标签分类模型,并将2部分标签整理去重以得到文本的最终威胁类别.通过与只依据正文建立的Bert-TextCNN多标签分类模型进行对比,所设置的模型在性能上有所提升,且召回率提升明显,能为开源威胁情报分类工作提供有价值的参考.

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。

基于PaddleOCR与Style-Text的金融票据手写体文本识别

该文提出一种基于PaddleOCR框架的金融票据手写体文本识别方法,通过引入基于生成对抗网络(GAN)的数据合成工具Style-Text,增强模型对不同背景文本的识别能力。在真实的金融票据数据集上进行的实验表明,该方法在处理复杂文本和低质量图像方面表现出显著的优势,证明其在金融票据手写体文本识别中的有效性和实用性。

基于SPI-RRV指数中国气象干旱及其风险时空演变特征研究

为全面揭示变化环境下我国多维气象干旱特征,耦合气象干旱指数(SPI)和可靠性-回弹性-脆弱性(RRV)指数,提出了一种基于SPI-RRV指数的干旱风险评价方法,定量评价了中国气象干旱及其风险的时空演变特征。结果表明:SPI-RRV指数具有特征稳定和时空可比性强的特点,能够较为准确地评估气象干旱风险时空演变特征;南方平均干旱栅格比、干旱月占比和频次大于北方,湿润区和半湿润区干旱历时短、烈度大,半干旱区和干旱区干旱历时长、烈度相对较小;干旱高风险区转移具有显著年代际变化规律,空间上从西北向西南地区转移。

深部煤储层孔裂隙结构对煤层气赋存的影响-以鄂尔多斯盆地东缘大宁-吉县区块为例

深部煤储层孔隙–裂缝结构对深部煤层气资源潜力评价和勘探开发具有重要意义。选取鄂尔多斯盆地东缘大宁–吉县区块DJ57井本溪组5个煤岩样品为研究对象,在煤岩煤质参数测试的基础上,采用气体吸附法、高压压汞法和微米CT扫描等测试手段,对深部煤储层中的纳米级孔隙-微米级裂缝进行多尺度定量表征,综合评价不同尺度的孔裂隙结构特征。再结合渗透率和甲烷等温吸附试验,探讨了微观孔裂隙对深部煤储层中煤层气的赋存和渗流的影响。研究结果表明:基于多种孔隙表征方法对深部煤储层孔裂隙进行多尺度定量表征,其孔裂隙体积分布类型主要以“U”型为主,呈现出微孔与微裂缝并存双峰态,主要集中在0.3~1.5 nm和>100μm的范围内。其中,微孔(<2 nm)、介孔(2~50 nm)、宏孔(50 nm~10μm)和微裂缝(>10μm)体积平均分别占总孔裂隙体积的80.18%,6.70%,1.65%和11.47%。随着微孔发育而吸附气量呈增大的趋势,微孔可以提供大量吸附点位,为深部煤层气的吸附和赋存提供场所。随着微裂缝发育而游离气量呈增大的趋势,微裂缝可以提供大量储集空间,为深部煤层气的富集提供空间条件。此外,微裂缝在三维空间中相互连通,形成网状结构,连通性强。随着微裂缝越发育,煤储层渗透率越大,微裂缝增强了煤层气的渗流能力。纳米级孔隙和微米级裂隙发育特征分别控制着深部煤层气吸附能力和开发潜力。