This primer will take a deep dive into NLP, NLU and NLG, differentiating between them and exploring their healthcare applications.
NLP, NLU and NLG are related, but distinct concepts. Broadly, NLU and NLG are subsets of NLP.
NLP utilizes methods taken from computer and data science, language modeling, linguistics and AI to help computers understand verbal and written forms of human language. Using machine learning (ML) and deep learning techniques, NLP converts unstructured language data into a structured format via named entity recognition (NER).
NER is a type of information extraction that allows named entities within text to be classified into predefined categories, such as people, organizations, locations, quantities, percentages, times and monetary values.
Through NER and the identification of word patterns, NLP can be used for tasks like answering questions or language translation.
As a component of NLP, NLU focuses on determining the meaning of a sentence or piece of text. NLU tools analyze syntax -- the grammatical structure of a sentence -- and semantics -- the intended meaning of the sentence. NLU approaches also establish an ontology, or structure specifying the relationships between words and phrases, for the text data on which they are trained.
Syntax, semantics and ontologies are all naturally occurring in human speech, but analyses of each must be performed using NLU for a computer or algorithm to accurately capture the nuances of human language.
NLU is often used in sentiment analysis by brands looking to understand consumer attitudes, as the approach allows companies to more easily monitor customer feedback and address problems by clustering positive and negative reviews.
Healthcare applications for NLU often focus on research, as the approach can be used for data mining within patient records. In 2022, UPMC launched a partnership to help determine whether sentinel lymph node biopsy is appropriate for certain breast cancer cohorts by using NLU to comb through unstructured and structured EHR data.
While NLU is concerned with computer reading comprehension, NLG focuses on enabling computers to write human-like text responses based on data inputs.
NLG tools typically analyze text using NLP and considerations from the rules of the output language, such as syntax, semantics, lexicons and morphology. These considerations enable NLG technology to choose how to appropriately phrase each response.