检索结果-南通市图书馆

word embeddings and Semantic Spaces in Natural Language Processing

International Journal of Intelligence Science 2023年第1期13卷 1-21页

作者： Peter J. Worth Dept. of Computer Science and Electrical Engineering Florida Atlantic University Boca Raton FL USA

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.

关键词： Natural Language Processing Vector Space Models Semantic Spaces word embeddings Representation Learning Text Vectorization Machine Learning Deep Learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Applying a Context-based Method to Build a Knowledge Graph for the Blue Amazon

引用

Data Intelligence 2024年第1期6卷 64-103页

作者： Pedro de Moraes Ligabue Anarosa Alves Franco Brandão Sarajane Marques Peres Fabio Gagliardi Cozman Paulo Pirozelli Escola Politécnica Universidade de São PauloRua Visconde da Luz60São PauloSão Paulo 05508-010Brazi Escola Politécnica Universidade de São PauloAv.Prof.Luciano Gualbertotv 3158São Paulo 05508-010Brazil Escola de Artes Ciências e Humanidades Universidade de São PauloRua Arlindo Béttio1000São Paulo 03828-000Brazil Instituto de Estudos Avançados Universidade de São PauloRua da Praça do Relógio109São Paulo 05508-050Brazil

Knowledge graphs are employed in several tasks,such as question answering and recommendation systems,due to their ability to represent relationships between *** constructing such a graphs,however,remains an unresolved challenge within knowledge *** tackle this challenge,we propose CtxKG,a method specifically aimed at extracting knowledge graphs in a context of limited resources in which the only input is a set of unstructured text *** is based on OpenIE(a relationship triple extraction method)and BERT(a language model)and contains four stages:the extraction of relationship triples directly from text;the identification of synonyms across triples;the merging of similar entities;and the building of bridges between knowledge graphs of different *** method distinguishes itself from those in the current literature(i)through its use of the parse tree to avoid the overlapping entities produced by base implementations of OpenIE;and(ii)through its bridges,which create a connected network of graphs,overcoming a limitation similar methods have of one isolated graph per *** compare our method to two others by generating graphs for movie articles from Wikipedia and contrasting them with benchmark graphs built from the OMDb movie *** results suggest that our method is able to improve multiple aspects of knowledge graph *** also highlight the critical role that triple identification and named-entity recognition have in improving the quality of automatically generated graphs,suggesting future paths for ***,we apply CtxKG to build BlabKG,a knowledge graph for the Blue Amazon,and discuss possible improvements.

关键词： knowledge graph word embeddings relationship triple extraction Blue Amazon Atlantic Ocean Brazilian coast

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A Data Mining Approach to Detecting Bias and Favoritism in Public Procurement

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 3501-3516页

作者： Yeferson Torres-Berru Vivian F.Lopez-Batista Lorena Conde Zhingre University of Salamanca Salamanca37008Spain Instituto Tecnológico Superior Sudamericano Loja1101608Ecuador Universidad Internacional del Ecuador Loja1101608Ecuador

In a public procurement process,corruption can occur at each stage,favoring a participant with a previous agreement,which can result in over-pricing and purchases of substandard products,as well as gender *** paper’s aim is to detect biased purchases using a Spanish Language corpus,ana-lyzing text from the questions and answers registry platform by applicants in a public procurement process in ***,gender bias is detected,pro-moting both men and women to participate under the same *** order to detect gender bias and favoritism towards certain providers by contracting enti-ties,the study proposes a unique hybrid model that combines Artificial Intelli-gence algorithms and Natural Language Processing(NLP).In the experimental work,303,076 public procurement processes have been analyzed over 10 years(since 2010)with 1,009,739 questions and answers to suppliers and public insti-tutions in each *** bias and favoritism were analyzed using a word2-vec model with word embedding,as well as sentiment analysis of the questions and answers using the VADER *** 32%of cases(96,984 answers),there was favoritism or gender bias as evidenced by responses from contracting *** proposed model provides accuracy rates of 88% for detecting favor-itism,and 90%for detecting gender *** one-third of the procure-ment processes carried out by the state have indications of corruption and *** Latin America,government corruption is one of the most significant challenges,making the resulting classifier useful for detecting bias and favoritism in public procurement processes.

关键词： Favoritism bias natural language processing word2vec sentiment analysis word embeddings

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Automatic Classification of Swedish Metadata Using Dewey Decimal Classification:A Comparison of Approaches

引用

Journal of Data and Information Science 2020年第1期5卷 18-38页

作者： Koraljka Golub Johan Hagelback Anders Ardo Department of Cultural Sciences Faculty of Arts and HumanitiesLinnaeus UniversityVaxjoSweden Department of Computer Science and Media Technology Faculty of TechnologyLinnaeus UniversityKalmarSweden Department of Electrical and Information Technology Lund UniversityLundSweden

Purpose:With more and more digital collections of various information resources becoming available,also increasing is the challenge of assigning subject index terms and classes from quality knowledge organization *** the ultimate purpose is to understand the value of automatically produced Dewey Decimal Classification(DDC)classes for Swedish digital collections,the paper aims to evaluate the performance of six machine learning algorithms as well as a string-matching algorithm based on characteristics of ***/methodology/approach:State-of-the-art machine learning algorithms require at least 1,000 training examples per *** complete data set at the time of research involved 143,838 records which had to be reduced to top three hierarchical levels of DDC in order to provide sufficient training data(totaling 802 classes in the training and testing sample,out of 14,413 classes at all levels).Findings:Evaluation shows that Support Vector Machine with linear kernel outperforms other machine learning algorithms as well as the string-matching algorithm on average;the string-matching algorithm outperforms machine learning for specific classes when characteristics of DDC are most suitable for the *** embeddings combined with different types of neural networks(simple linear network,standard neural network,1 D convolutional neural network,and recurrent neural network)produced worse results than Support Vector Machine,but reach close results,with the benefit of a smaller representation *** of features in machine learning shows that using keywords or combining titles and keywords gives better results than using only titles as *** only marginally improves the *** stop-words reduced accuracy in most cases,while removing less frequent words increased it *** greatest impact is produced by the number of training examples:81.90%accuracy on the training set is achieved when at least 1,000 records per class are available

关键词： LIBRIS Dewey Decimal Classification Automatic classification Machine learning Support Vector Machine Multinomial Naive Bayes Simple linear network Standard neural network 1D convolutional neural network Recurrent neural network word embeddings String matching

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

An Intelligent Deep Neural Sentiment Classification Network

引用

Intelligent Automation & Soft Computing 2023年第5期36卷 1733-1744页

作者： Umamaheswari Ramalingam Senthil Kumar Murugesan Karthikeyan Lakshmanan Chidhambararajan Balasubramaniyan Department of Electronics and Instrumentation Engineering SRM Valliammai Engineering CollegeKattankulathurTamilnaduIndia Department of Computer Science and Engineering SRM Valliammai Engineering CollegeKattankulathurTamilnaduIndia Department of Electronics and Communications Engineering SRM Valliammai Engineering CollegeKattankulathurTamilnaduIndia

A Deep Neural Sentiment Classiﬁcation Network(DNSCN)is devel-oped in this work to classify the Twitter data *** attempts to extract the negative and positive sentiments in the Twitter *** main goal of the system is toﬁnd the sentiment behavior of tweets with minimum ambiguity.A well-deﬁned neural network extracts deep features from the tweets *** extracting features deeper and deeper,the text in each tweet is represented by Bag-of-words(BoW)and word embeddings(WE)*** effectiveness of DNSCN architecture is analyzed using Twitter-Sanders-Apple2(TSA2),Twit-ter-Sanders-Apple3(TSA3),and Twitter-DataSet(TDS).TSA2 and TDS consist of positive and negative tweets,whereas TSA3 has neutral tweets ***,the proposed DNSCN acts as a binary classiﬁer for TSA2 and TDS databases and a multiclass classiﬁer for *** performances of DNSCN architecture are evaluated by F1 score,precision,and recall rates using 5-fold and 10-fold *** show that the DNSCN-WE model provides more accuracy than the DNSCN-BoW model for representing the tweets in the feature *** F1 score of the DNSCN-BW based system on the TSA2 database is 0.98(binary classiﬁcation)and 0.97(three-class classiﬁcation)for the TSA3 *** system provides better a F1 score of 0.99 for the TDS database.

关键词： Deep neural network word embeddings bag-of-words sentiment analysis text classiﬁcation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：