|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/nlp-through-gofai/
课程评论：没有评论
课程名称：使用Python进行自然语言处理 概述：传统的机器学习项目使用存储在常规数据库中的数值和文本数据。然而，仅基于文本数据开发智能应用程序是极具挑战性的。这是因为，世界上可用的文本数据量是传统数据库中数值数据的数百万倍。那么，我们能否从这个庞大的文本数据集中提取有用信息呢？当数据规模达到数太字节时，机器学习的整个视角都发生了变化。在传统数据库中，列的数量通常较少，因此用于机器学习的特征也很少，一般在几十到几百之间。然而，在自然语言处理（NLP）应用中，由于没有结构化数据库中的列，每个词都成为了模型训练的潜在特征，这使得训练一个具有数百万特征的模型几乎不可能。因此，开发机器学习应用的首要任务是通过减少词汇量来降低特征数量。而另一个主要需求是将文本数据转换为二进制格式，因为机器只能理解二进制数据。这使得NLP的学习与结构化数据库模型开发有了显著区别。 在本课程中，您将学习多种文本预处理技术，以准备庞大的文本数据集进行机器学习。具体学习的内容包括词干提取、词形还原、去除停用词、词性标注、词袋模型和tf-idf。接下来，您将学习应用基于传统统计的算法进行模型训练，并开发五个行业标准的实际NLP应用程序，涵盖广泛的NLP领域。您将学习二分类和多分类，以及监督学习和无监督学习。还将对文本数据进行无监督聚类，并使用LDA（潜在狄利克雷分配）算法进行聚类。使用支持向量机进行文本分类，同时在商业应用中学习情感分析、研究文章分类、根据客户评价对酒店排名、新闻摘要、主题建模以及快速入门自然语言理解（NLU）。该课程帮助您快速入门NLP，并通过实践方法掌握多种NLP技术。每节课都有代码练习，使学习变得容易并且高效。
Traditional Machine Learning projects use numeric and textual data stored in conventional databases. Developing intelligent applications based on purely text data is extremely challenging? Why is it so? In the first place, the available text data in this world is millions of times more than the numeric data available to us in the conventional databases. So, the question is can we extract some useful information from this huge corpus of text data - which can run into several terabytes or rather petabytes. The moment you talk about these sizes for the data, the whole perspective of machine learning changes. In the traditional databases, the number of columns is quite low and thus the number of features for machine learning too is very small - generally goes in tens and at the most few hundreds, max. In NLP applications, as there are no columns like structured databases, each word in the text corpus becomes a probable candidate to be considered as a feature for model training. It is impossible to train a model with millions of features. So, to develop ML applications, the first and the major requirement is to reduce this features count by reducing the vocabulary. The other major requirement is to convert the text data into binary format as our dumb machine understand only binaries. That is where the NLP learning becomes distinct from model development on structured databases. Once the text data is pre-processed to get a minimal number of features that represent the entire text corpus, the rest of the model development process remains same as the traditional one - popularly known as Good Old Fashioned AI. In this course, you will learn many text pre-processing techniques to make the huge text datasets ready for machine learning. You will learn many text-preprocessing techniques such as stemming, lemmatization, removing stop words, position-of-speech (POS) tagging, bag-of-words, and tf-idf.You will then learn to apply the traditional statistics based algorithms for training the models. You will develop five industry standard real-life NLP applications. These applications would cover a wide span of NLP domain. You will learn binary and multi-class classifications. You will use both supervised and unsupervised learning. You will learn to use unsupervised clustering on text data. You will use LDA (LatentDirichletAllocation) algorithm for clustering. You will use support vector machines for classifying text. On the business side, you will learn sentiment analysis, classifying research articles, ranking hotels based on customer reviews, news summarization, topic modeling and a quick start to Natural Language Understanding (NLU).This course helps in getting a quick start on NLP and mastering several NLP techniques through a very practical approach. Each lesson has code to practice that makes your learning easy and quick.
