Natural language processing (python) environment configuration - installation of NLTK
1. Introduction to Natural Language Processing
NLP (Natural Language Processing) is a subfield of artificial intelligence (AI). It is an important part of the machine that can really understand human speech. Natural language processing is not a new research field. It has been studied as early as the last century. However, given the computer environment and other factors, the development of this field has been stagnant. With the rapid development of machine learning, statistics, and computer science, NLP has ushered in a new spring, and it is also a very important part in the future development. For details, please refer to Baidu Encyclopedia ( https://baike.baidu.com/item/nlp/25220 ).
2. Natural language processing language tools
In natural language processing, python has also become a language that does its part. The inheritance of this kind of package is like standing on the shoulders of giants. However, this is only the use of current technology, and it is indeed necessary for in-depth research. Effort. Especially for postgraduates, doctoral students, etc., it is necessary to really think about the formation of language, and here is Chomsky's theory of formal language and Chinese natural language processing. The works of Professor Feng Yuanwei are all worthy of our thinking and For reference, combined with the current development of statistics, machine learning, and computer science, natural language processing will develop better on the basis of python, a useful programming tool.
3. The first step in natural language processing
Of course, the blogger is a novice who wants to engage in research in this area. He has just started. I hope this is a platform to record my growth, and I also hope to share what I know and the problems encountered in my study. This is the beginning of learning, using the relatively well-known nltk package, of course, for the word segmentation of Chinese characters, etc., as far as bloggers know, there are also jieba word segmentation and so on.
Environment preparation:
System: window 10
IDE: anaconda-spyder
Environment configuration: It seems that nltk has been integrated in anaconda, of course, you can also enter: pip install nltk on the command line (provided that the reader has already configured the environment); After that, open the IDE and create a py file
import nltk
nltk.download()You can download nltk's corpus and other resources. As shown in the
figure :
Since domestic access is relatively slow, it needs to be downloaded. The blogger has already downloaded it: Link: https://pan.baidu.com/s/1WbNb-h9U8VKYQXSYZonbvQ Password : dq4s
More information can also be viewed on the official website: http://www.nltk.org/