Natural Language Processing (NLP)
Written by
Tiffany ClarkAbout the Author
Tiffany is an experienced workforce development expert with extensive experience in the public sector, course development, and online learning.
Reviewed by
VidCruiter Editorial TeamAbout the Author
The VidCruiter Editorial Team offers practical recruitment advice, drawing on insights from seasoned professionals. Our award-winning content, supported by industry specialists, underscores VidCruiter's dedication to innovation in recruitment.
Last Modified
Apr 17, 2024
Natural language processing (NLP) is a field of artificial intelligence (AI) that enables computers to understand, generate and manipulate human language. NLP facilitates interaction between humans and computers that mimics the natural language people use to speak and write.
NLP enables programs and devices to understand a user’s request and respond in a way that emulates natural language, in both speech and written text. NLP systems can be designed to function across multiple different languages, making it possible for computers to process and analyze large amounts of natural language data.
NLP Components
-
Semantics: The meaning of words and phrases is understood when they are combined in sentences.
-
Syntax: Phrases and words are arranged to create well-structured sentences.
-
Discourse: Language is interpreted and analyzed beyond the sentence level to consider how sentences are related to each other in conversation or text.
-
Pragmatics: Language is understood in various contexts to ensure the derived intended meaning is based on a speaker’s intent, shared knowledge, and situation.
NLP Methods and Techniques
-
Parsing: Analyzing the grammatical structure of a sentence for the purpose of extracting meaning
-
Named Entity Recognition (NER): Identifying entities such as locations, organizations, people, or other named items
-
Tokenization: Breaking text into symbols, phrases, words, or other meaningful elements
-
Lemmatization and Stemming: Reducing words to their root or base form to allow for the grouping of varying forms of the same words
-
Sentiment Analysis: Gaining an understanding of the emotion or sentiment being conveyed in a piece of text
Examples of Natural Language Processing
-
Smart assistants: Examples of smart assistants that use NLP include Amazon’s Alexa and Apple’s Siri.
-
Email filters: Email filters began with spam filters to uncover phrases or words commonly associated with spam emails. With upgraded filtering, email filters can now recognize which categories emails fall into. For example, Google’s Gmail uses NLP to filter emails into social, primary, and promotions.
-
Search results: NLP is used by search engines to deliver relevant results based on user intent and similar search behaviors. As an example, Google can predict other popular searches that apply to your search query as you type into the search bar.
-
Predictive text: Autocomplete, predictive text, and autocorrect are commonplace on search engines, in word processing programs, and on smartphones.
Related Terms
Machine Learning (ML)
is an AI subset centered on application development. Machine learning can use data to improve accuracy over time without the need for human intervention. However, while algorithms in machine learning can be trained to make better predictions and decisions by finding patterns, human intervention is typically needed.
Natural Language Understanding (NLU)
is a subset of NLP. NLU is focused on interpreting.
Natural Language Generation (NLG)
is also a subset of NLU. Specifically, NLG refers to the use of computers for generating human language.
Sequence Modeling
is also called sequence-to-sequence (seq2seq) modeling. This term refers to a sequence model's ability to take an entire document or sentence as input and produce other documents or sentences as output.
Deep Learning
is the most commonly used type of machine learning in natural language processing. Powered by neural network layers, the algorithms in deep learning are modeled loosely on the workings of human brains.
Transfer Learning
enables further training for trained deep neural networks. With transfer learning, deep neural networks can achieve new tasks with reduced computing effort and training data.
Pretrained Models
are trained on various combinations of datasets, languages, and pre-training tasks. Users can download pre-trained models and fine-tune them for a wide array of differing target tasks.