Part-of-Speech Tagging Fundamentals, Uses, and How to Get Started

Key takeaways

• Part-of-speech tagging labels words in a sentence with their part of speech based on the context around each word.

• In natural language processing (NLP), part-of-speech tagging serves as a tool to analyze human speech patterns and transform words into mathematical models that machines can understand.

• Part-of-speech tagging works by disambiguating words and classifying each part of speech based on sentence position and context, using techniques such as rule-based and stochastic tagging.

A part-of-speech tagging example in health care is how it helps medical professionals search health records and research as part of NLP to make informed decisions about patient care and diagnosis. Discover more about the part-of-speech tagging methods and their use cases in the following article.

If you’re ready to get your start in NLP right away, consider enrolling in DeepLearning.AI’s Natural Language Processing Specialization. You’ll have the opportunity to learn how to use word vectors to implement sentiment analysis, identify part-of-speech tags for words, utilize dynamic programming, and more.

What is part-of-speech tagging?

Part-of-speech (POS) tagging is a tool in NLP that “tags” words in a sentence with their part of speech based on the context around the word. The English language includes a broad range of different parts of speech, including prepositions, nouns, verbs, adverbs, adjectives, conjunctions, pronouns, interjections, and articles. Part-of-speech tagging is necessary because a word in English can have multiple parts of speech. For example, the word eye can act as both a verb and a noun, such as “I’ve got my eye on you” or “Take a look at my eye.” To address the manual tagging of sentences, NLP researchers developed methods to automate POS tagging.

Part-of-speech tagging methods

You can divide POS tagging methods into three general categories: rule-based tagging, stochastic tagging, and machine learning (ML) and deep learning (DL) tagging. Explore each framework and the methods they offer in more detail below.

Rule-based tagging

Rule-based tagging uses a specific set of rules that you create. These rules often follow linguistic principles, using sentences' lexical, morphological, and syntactic features. A linguist can create these rules or use machine learning on a classified data set. This type of POS tagging is time-consuming and can lead to errors.

Stochastic tagging

Stochastic or probabilistic tagging is a popular approach to part-of-speech tagging that uses supervised learning and trains on sample data sets. Two stochastic tagging approaches include:

• Hidden Markov Model (HMM): The HMM is one of the most common approaches to POS tagging. This generative sequence model tries to classify each word in a sentence, in this case, labeling it as a part of speech. In an HMM, the hidden part of the model (the part of speech) only depends on the known part of the model (the word) to make its prediction.

• Maximum Entropy Markov Model (MEMM): The MEMM uses logistic regression in a discriminative sequence model, rather than the HMM's generative one. This allows the model to use the previous word's class to help it define the current word it’s analyzing.

ML and DL tagging

Machine learning and deep learning in NLP use neural networks to process words by mimicking the way neurons function in the human brain. Some effective and popular kinds of neural networks for POS tagging include:

• Recurrent neural network (RNN): RNNs take an input, process it in a hidden layer, and continually update their outputs using the previous findings.

• Bidirectional long short-term memory (BLSTM): A popular deep learning method of tagging, BLSTM uses two hidden layers, one that feeds forward and another that processes backward. These have the most accurate outputs among all available RNNs.

Read more: Deep Learning vs. Neural Network: What’s the Difference?

How does part-of-speech tagging work?

Part-of-speech tagging disambiguates words, classifying each part of speech with respect to its sentence placement and context. It is a fundamental process in creating any NLP pipeline and, thus, fundamental to creating a proper NLP parser. NLP is a key technology behind speech recognition and synthesis, which helps many people in their daily lives. Speech translation, artificial intelligence (AI) powered chatbots, and document summaries all use natural language processing.

Part-of-speech tagging examples

Part-of-speech tagging supports a wide range of NLP tasks, from analyzing financial records to reviewing legal documents. Explore these use cases in greater detail.

• Finance: NLP mines financial documents, statements, reports, and the news to assist in strong, data-driven decision-making that impacts earnings.

• Health care: In health care, NLP searches health records and research to help professionals make informed decisions about patient care, prevention, and diagnosis.

• Legal: With the amount of paperwork and documents in a legal proceeding, NLP can help organize, summarize, and review to ensure lawyers receive all relevant information that could help their case.

Who uses part-of-speech tagging?

NLP engineers, machine learning engineers, and AI engineers are among the professionals who use part-of-speech tagging in NLP systems. Learn more about these job roles and salary prospects below.

All salary information represents the median total pay from Glassdoor as of September 2026. These figures include base salary and additional pay, which may represent profit-sharing, commissions, bonuses, or other compensation.

NLP engineer

Median annual total US pay (Glassdoor): $166,000 [1]

Requirements: This role typically requires a bachelor’s degree in computer science or a related field, with some employers requiring graduate experience in AI.

The NLP engineer role requires you to design NLP systems by creating the language training data sets needed to train machine learning algorithms. This role also involves processing the results and tweaking the models accordingly. Other work duties involve analyzing human speech patterns and turning the words into mathematical models that machines can understand and use to produce AI-generated speech.

Machine learning engineer

Median annual total US pay (Glassdoor): $165,000 [2]

Requirements: Many machine learning engineers earn a degree in data science or computer science, sometimes earning an advanced degree to progress in the field.

As a machine learning engineer, you might work toward creating programs and algorithms that analyze and process data to find inherent patterns and use insights to make predictions. Furthermore, you may design these programs by training them to identify patterns in large swathes of data. Over time, they make predictions with increasing accuracy.

Artificial intelligence engineer

Median annual total US pay (Glassdoor): $155,000 [3]

Requirements: Many AI engineers need a master’s degree at a minimum to gain the necessary skills in the field.

In the position of an AI engineer, you may use machine learning and deep learning to build intelligent AI models. Specifically, you might combine extensive knowledge of programming, software development, and data science to produce effective models for use across various industries. Also within the scope of your role is creating and managing the infrastructure that the rest of the data science team will follow to create and maintain AI models.

Challenges in part-of-speech tagging

The barriers to effective part-of-speech tagging often stem from technical and resource-related limitations, such as:

• Difficulty in finding balanced corpus data sets to train more accurate POS taggers

• Lack of publicly available corpus data sets for research

• Heavy reliance on computing resources that are power-intensive for part-of-speech tagging work

Other challenges include the need for a sufficient corpus across many languages, especially those that are morphologically rich and have large vocabularies, such as Hungarian, Czech, and Romanian.

How to get started in part-of-speech tagging

To build skills in NLP and POS tagging, you need to develop your linguistic skills and gain proficiency in programming languages like C++, Python, and R. These give you the fundamental tools to understand language and translate it into a form that a machine can understand.

If you are already familiar with Python, consider learning how NLP works by using the Natural Language Toolkit (NLTK), an open-source language processing library. It gives you access to over 50 corpora and tools for tokenization, stemming, POS tagging, and semantic reasoning. It’s an effective computational linguistics tool with a large community and sufficient documentation, including an online version of the NLTK book for Python 3.

Check out our free resources for NLP professionals

Join Career Chat on LinkedIn to get weekly updates on popular skills, tools, and certifications. Continue your learning journey with NLP and machine learning with our other free digital resources:

• Structure your learning: Natural Language Processing Learning Roadmap: Beginner to Expert

• Take a quiz: Which Machine Learning Course Should You Take? Find Out in 1 Minute

• Read our Career Chat issue: 6 Machine Learning Certificates + How to Choose the Right One for You

Accelerate your career growth with a Coursera Plus subscription. When you enroll in either the monthly or annual option, you’ll get access to over 10,000 courses.

Build job-ready skills with Coursera Plus

Start 7-day free trial

• 
• 
• 
• 

Start 7-day free trial