2020 version of 100 knocks of language processing, which is famous as a collection of problems of natural language processing, has been released. In this article, I will introduce 100 examples of answers in Python. Feel free to comment if you have any questions, such as mistakes or better ways. All answer notebooks are available on github.
We use Google Colaboratory for answers. For details on how to set up and use Google Colaboratory, see this article. However, no special settings are required and you can use it immediately if you have a Google account.
Review some advanced topics in programming languages while working on subjects dealing with text and strings.
Chapter 1 Questions and Answers
Experience useful UNIX tools for research and data analysis. Through these reimplements, you will experience the ecosystem of existing tools while improving your programming skills.
Chapter 2 Questions and Answers
By applying regular expressions to the markup description on Wikipedia pages, various information and knowledge can be extracted.
[Chapter 3 Questions and Answers] (https://qiita.com/yamaru/items/255d0c5dcb2d1d4ccc14)
Apply a morphological analyzer to Natsume Soseki's novel "I Am a Cat" to find the statistics of the words in the novel.
[Chapter 4 Questions and Answers] (https://qiita.com/yamaru/items/e06014b146a18e97ca59)
Apply the dependency analyzer to "I am a cat" and experience the operation of the dependency tree and syntactic analysis.
[Chapter 5 Questions and Answers] (https://qiita.com/yamaru/items/48dcc527f433c22e0af9)
Build a document classifier by machine learning. In addition, you will learn how to evaluate machine learning methods.
Chapter 6 Questions and Answers
Learn how to handle word vectors through word similarity calculation and word analogy. In addition, you will experience clustering and vector visualization.
Chapter 7 Questions and Answers
Learn how to use the deep learning framework and implement categorization based on neural networks.
Chapter 8 Questions and Answers
Implement recurrent neural networks (RNNs) and convolutional neural networks (CNNs) using deep learning frameworks.
Preparing to answer
Build a neural machine translation model using existing tools.
Preparing to answer
100 Language Processing Knock is designed so that you can learn not only natural language processing itself, but also basic data processing and general-purpose machine learning. Even those who are studying machine learning in online courses will be able to practice very good output, so please try it.
Recommended Posts