NLP is used across many industries. Each industry below has 3 typical use cases, and 2 example companies together with the NLP algorithms they rely on.

Industries at a glance

IndustryUse casesCompanies (NLP algorithms)
HealthcareClinical documentation, diagnostic assistance, drug discovery and developmentIBM Watson Health (advanced ML, language models), Epic Systems (text parsing, extraction)
Finance and BankingFinancial report automation, fraud detection, customer service chatbotsKensho (text analytics, sentiment analysis), Yseop (natural language generation, data interpretation)
Retail and E-CommerceSentiment analysis of product reviews, personalised recommendations, customer service chatbotsClarabridge (sentiment analysis, deep learning), Algolia (semantic search, user intent understanding)
LegalDocument review and analysis, predictive analysis of case outcomes, compliance monitoringLegalSifter (contract analysis, key term extraction), Lex Machina (text mining, predictive analytics)
AutomotiveVoice-activated assistants, customer feedback analysis, automated vehicle information supportNuance Dragon Drive (speech recognition, language understanding), SoundHound's Houndify (voice recognition, NLU)
PublishingContent curation and management, reader engagement analysis, automated content generationOpenAI's GPT-3 (deep learning, transformer models), Narrativa (natural language generation, data interpretation)
EducationPlagiarism detection, content personalisation, language learning toolsTurnitin (text comparison, similarity scoring), Grammarly (grammar checking, style suggestions)
Travel and HospitalityAutomated booking assistants, customer feedback analysis, language translation servicesAmadeus (semantic search, natural language queries), Booking.com chatbot (chatbot technology, intent recognition)
Media and EntertainmentContent recommendation, automated subtitling and dubbing, sentiment analysis of social mediaNetflix (content recommendation, user preference analysis), Valossa (video content analysis, metadata generation)
Government and Public SectorPublic sentiment analysis, automated public services, document and record managementPalantir Gotham (text extraction, entity recognition), Digital Reasoning (sentiment analysis, entity recognition)

What to focus on

Know which NLP task serves which use case, for example sentiment analysis for reviews, NER for document records, text generation for reports. The company names are background only.

Common themes

The same 5 themes run through all the industries:

ThemeWhat it meansMain industries
Insight extractionGaining insights from dataHealthcare, finance, retail
Customer engagementBetter service with chatbotsBanking, retail, hospitality
Content personalisationTailoring experiences to each userMedia, education, e-commerce
Automated complianceStreamlining document processingLegal, government
Enhanced communicationBetter interaction with usersTravel, automotive

Remembering tip

I C C A E: "I Can Chat And Explain". Insight, Customer engagement, Content personalisation, Automated compliance, Enhanced communication.

Using an LLM for these use cases

A single instruction-tuned LLM can cover several of the use cases above, only by changing the prompt:

IndustryPrompt idea
HealthcareExtract the key points of a doctor and patient conversation into a markdown table
FinanceSummarise the effect of a promotion on sales from a sales table, in bullet points
RetailSuggest how to improve sales from a list of customer reviews
PublishingWrite a short introduction to a country in 4 sentences or less

LLM output is not always accurate, so the results must be checked before use.

The next note looks at a full NLP system in one of these industries, the Fraud Detection Model.