Data Science continues to be a hot topic, but more specifically, Natural Language Processing (NLP) is increasing in demand.

数据科学仍然是一个热门话题，但更具体地说，自然语言处理(NLP)的需求正在增长。

Broadly speaking, NLP is a subset of artificial intelligence and machine learning that helps computers understand, interpret, and manipulate human language. It has MANY applications including speech recognition, automated chatbots, sentiment analysis, and more.

从广义上讲，NLP是人工智能和机器学习的子集，可帮助计算机理解，解释和操纵人类语言。 它具有许多应用程序，包括语音识别，自动聊天机器人，情绪分析等。

Below are several high-quality courses on Natural Language Processing that are FREE:

以下是一些免费的自然语言处理高质量课程：

1.从语言到信息(斯坦福大学) (1. From Languages to Information (Stanford University))

If you’re looking for an introduction to NLP, this course is it. Keep in mind that this course was made even for those who don’t have any experience in Python, hence the tutorial on Python. Personally, I feel like this definitely covers a lot on theoretically, but there are definitely other courses out there that are better for applications.

如果您正在寻找有关NLP的介绍，那么就是这门课程。 请记住，本课程甚至是为那些没有Python经验的人开设的，因此请参阅Python教程。 就个人而言，我觉得这在理论上肯定涵盖了很多内容，但是肯定还有其他课程更适合于应用程序。

This course covers the basics on text processing, sentiment analysis, information retrieval, chatbots, and more. I highly recommend this course if you are new to programming or know absolutely nothing about NLP.

本课程涵盖了文本处理，情感分析，信息检索，聊天机器人等基础知识。 如果您不熟悉编程或对NLP完全一无所知，我强烈建议您参加本课程。

2.深度学习中的自然语言处理(斯坦福大学) (2. Natural Language Processing with Deep Learning (Stanford University))

This course is also from Stanford but it is a little more advanced. You’re expected to be proficient in Python and have a good understanding of basic calculus, statistics, and machine learning. This course is more math-heavy, so make sure that you have a good understanding of vectors and matrices.

该课程也是斯坦福大学的课程，但要高级一些。 您应该精通Python，并且对基本演算，统计数据和机器学习有很好的了解。 本课程比较重数学，因此请确保您对向量和矩阵有充分的了解。

Keep in mind that a big portion of the course focuses on vectors, matrix calculus, and neural networks because these concepts make up the foundation of a lot of NLP concepts. So if you don’t feel like you have the mathematical skills required, I recommend that you start with the first course above.

请记住，本课程的很大一部分重点是矢量，矩阵演算和神经网络，因为这些概念构成了许多NLP概念的基础。 因此，如果您不具备所需的数学技能，建议您从上述第一门课程开始。

3.用于自然语言处理的深度学习(牛津大学) (3. Deep Learning for Natural Language Processing (University of Oxford))

Quoted by them, this is an advanced course on NLP.

由他们引用，这是一门有关NLP的高级课程。

“This will be an applied course focussing on recent advances in analysing and generating speech and text using recurrent neural networks. We will introduce the mathematical definitions of the relevant machine learning models and derive their associated optimisation algorithms. The course will cover a range of applications of neural networks in NLP including analysing latent dimensions in text, transcribing speech to text, translating between languages, and answering questions.”

“这将是一门应用课程，重点是使用递归神经网络分析和生成语音和文本的最新进展。 我们将介绍相关机器学习模型的数学定义，并推导它们相关的优化算法。 该课程将涵盖NLP中神经网络的一系列应用，包括分析文本的潜在维度，将语音转录为文本，在语言之间进行翻译以及回答问题。”

Similar to the second course, this course has a heavy emphasis on neural networks, and so, it is highly recommended that you understanding fundamental linear algebra, continuous mathematics, and probability concepts. This course is also very practical and application-heavy, so you should also be a proficient programmer.

与第二门课程类似，本课程着重于神经网络，因此强烈建议您了解基本的线性代数，连续数学和概率概念。 本课程也是非常实用且需要大量应用程序的课程，因此您也应该是一个熟练的程序员。

4.自然语言处理(华盛顿大学) (4. Natural Language Processing (University of Washington))

This is a unique course that initially focuses on things that aren’t normally focused on, like Hidden Markov Models, Probabilistic Context-Free Grammars, and more. The latter half of the course primarily focuses on vectors and neural networks.

这是一门独特的课程，最初重点关注通常不关注的事物，例如隐马尔可夫模型，概率上下文无关文法，等等。 课程的后半部分主要关注向量和神经网络。

Personally, I feel like the course material provides nice summaries for certain topics, like neural networks. However, with a like of assignments/practicals, I feel like this is more of a resource that you could use to skim or refresh your memory.

我个人觉得课程材料为某些主题(如神经网络)提供了很好的总结。 但是，通过类似的作业/实践，我觉得这更多地是您可以用来浏览或刷新记忆的资源。

5.应用自然语言处理(加州大学伯克利分校) (5. Applied Natural Language Processing (UC Berkeley))

This is a graduate course that is quite extensive. It emphasizes the use of scikit-learn, keras, gensim, and spacy. In terms of raw theory, this course has top-tier slides and extra readings to further your knowledge. It also covers several topics that some of the courses above don’t.

这是一门非常广泛的研究生课程。 它强调使用scikit-learn，keras，gensim和spacy。 在原始理论方面，本课程包含顶级幻灯片和更多阅读材料，以进一步提高您的知识水平。 它还涵盖了一些上述课程没有的主题。

The only unfortunate thing is that they don’t share any of their assignments/practicals or quizzes, so there aren’t any opportunities for you to put your knowledge to the test.

唯一不幸的是，他们没有分享他们的任何作业/实践或测验，因此您没有任何机会进行知识测验。

Quoted from them, “Topics include text-driven forecasting and prediction (using text for problems involving classification or regression); experimental design; the representation of text, including features derived from linguistic structure (such as parts of speech, named entities, syntax, and coreference) and features derived from low-dimensional representations of words, sentences and documents; exploring textual similarity for the purpose of clustering; information extraction (extracting relations between entities mentioned in text); and human-in-the-loop interactive NLP.”

引述他们的话， “主题包括文本驱动的预测和预测(将文本用于涉及分类或回归的问题)； 实验设计; 文本表示，包括从语言结构衍生的特征(例如词性，命名实体，语法和共指)，以及从单词，句子和文档的低维表示衍生的特征； 探索文本相似性以进行聚类； 信息提取(提取文本中提到的实体之间的关系)； 以及环人互动NLP。”

谢谢阅读！ (Thanks for Reading!)

I hope that you find a course that suits your needs and I wish you the best in your data science journey.

我希望您找到适合您需求的课程，并祝您在数据科学之旅中一切顺利。

特伦斯·辛 (Terence Shin)

• Check out my free data science resource with new material every week!

  每周 查看 我的免费数据科学资源 以及新材料！

• If you enjoyed this, follow me on Medium for more

  如果您喜欢这个，请 在Medium上关注我以 了解更多

• Let’s connect on LinkedIn

  让我们在 LinkedIn上建立联系