What is Natural Language Processing? Definition and Examples | Coursera

在这个"双十一"，致力于职业发展 。Coursera Plus全年会员享8折优惠。
Natural language processing ensures that AI can understand the natural human languages people speak every day. Learn more about this impactful AI subfield.
Natural language processing (NLP) is a subset of artificial intelligence, computer science, and linguistics that allows computers to understand human language, whether you write it, speak it, or even scribble it. At a glance, here's what you need to know about NLP:
Some benefits of natural language processing in AI include its ability to analyze structured and unstructured data, identify customer insights using sentiment analysis, and help an organization understand its target market by analyzing social media posts and reviews.
Natural language processing works by using techniques such as sentiment analysis, summarization, keyword extraction, and tokenization.
Natural language processing software includes Google Cloud NLP API, IBM watsonx, and Amazon Comprehend.
Below, you'll learn a bit more about NLP, including what it is, how its used, and some common applications of it in the work world. Afterward, if you're interested in developing your NLP skill set, consider enrolling in DeepLearning.AI's Natural Language Processing Specialization. In as little as three months, you can learn about large language modeling, applied machine learning, artificial neural networks, TensorFlow, and more.
NLP is a subset of artificial intelligence, computer science, and linguistics focused on making human communication, such as speech and text, comprehensible to computers.
NLP is used in a wide variety of everyday products and services. Some of the most common technologies that use NLP are voice-activated digital assistants on smartphones, email-scanning programs used to identify spam, and translation apps that decipher foreign languages.
Read more: Using ChatGPT as a Personal Assistant: Work Smarter, Not Harder
NLP encompasses a wide range of techniques to analyze human language. Some of the common techniques you will likely encounter in the field include:
Sentiment analysis: An NLP technique that analyzes text to identify its sentiments, such as “positive,” “negative,” or “neutral.” Sentiment analysis is commonly used by businesses to better understand customer feedback.
Summarization: An NLP technique that summarizes a longer text in order to make it more manageable for time-sensitive readers. Some common texts this technology can summarize include reports and articles.
Keyword extraction: An NLP technique that analyzes a text to identify the most important keywords or phrases. Keyword extraction is commonly used for search engine optimization (SEO), social media monitoring, and business intelligence purposes.
Tokenization: The process of breaking characters, words, or subwords down into “tokens” that the program can analyze. Tokenization undergirds common NLP tasks like word modeling, vocabulary building, and frequent word occurrence.
Whether it’s being used to quickly translate a text from one language to another or producing business insights by running sentiment analysis on hundreds of reviews, NLP provides both businesses and consumers with a variety of benefits.
Unsurprisingly, then, you can expect to see more of it in the coming years. According to research by Fortune Business Insights, they project the global market for NLP to grow from $45.74 billion in 2026 to $193.4 billion in 2034 [1].
Some common benefits of NLP include:
The ability to analyze both structured and unstructured data, such as speech, text messages, and social media posts.
Improving customer satisfaction and experience by identifying insights using sentiment analysis.
Reducing costs by employing NLP-enabled AI to perform specific tasks, such as chatting with customers via chatbots or analyzing large amounts of text data.
Better understanding a target market or brand by conducting NLP analysis on relevant data like social media posts, focus group surveys, and reviews.
NLP can be used for a wide variety of applications, but it's far from perfect. In fact, many NLP tools struggle to interpret sarcasm, emotion, slang, context, errors, and other types of ambiguous statements. This means that NLP is mostly limited to unambiguous situations that don't require a significant amount of interpretation.
Although natural language processing might sound like something out of a science fiction novel, the truth is that NLP examples already exist in your everyday life as you interact with countless NLP-powered devices and services every day.
Online chatbots, for example, use NLP to engage with consumers and direct them toward appropriate resources or products. While chatbots can’t answer every question that customers may have, businesses like them because they offer cost-effective ways to troubleshoot common problems or questions that consumers have about their products.
Another common use of NLP is for text prediction and autocorrect, which you’ve likely encountered many times before while messaging a friend or drafting a document. This technology allows texters and writers alike to speed up their writing process and correct common typos.
ChatGPT, a chatbot powered by AI and natural language processing, produces unusually human-like responses. Recently, it has dominated headlines due to its ability to produce responses that far outperform what was previously commercially possible.
If you'd like to learn more, the University of Michigan's ChatGPT Teach Out brings together experts on communication technology, the economy, artificial intelligence, natural language processing, health care delivery, and law to discuss the impacts of the technology now and into the future.
NLP has a wide array of applications across various sectors such as finance, insurance, and health care. Prominent applications for NLP technology include voice-activated assistants, machine translation, sentiment analysis, chatbots, virtual customer support, classification and categori