Named entity recognition
NER marks named entities in text and assigns types such as person, organisation or place.
Which text spans does NER recognise?
Named entity recognition, or NER, identifies named entities in text and assigns types to the corresponding spans, such as person, organisation or place. Supported types and recognition reliability depend on the method, language and data. Labelling a name as an organisation does not link it to a specific customer record. Establishing that unique association is a separate task.
A fictional enquiry mentions Mira, Nordstern Service and Berlin. A system is to mark the names as suggested person, organisation and place entities. Before importing them into a CRM, the process must check which existing contact or company is actually meant. Similar names may belong to different records. The team therefore also plans cases with abbreviations, spelling variants and ambiguous names. Recognition provides text spans for further processing; it establishes neither the requester's identity nor their access rights.
Sources
Related terms
- Large language modelA large language model processes language using learned patterns. Fluent text proves neither factual accuracy nor access to current business data.
- Generative AIGenerative AI produces content such as text, images or code. Quality is assessed against its intended use and available source information.
- AI inferenceApplying an already trained model to inputs to obtain a result.
- Multimodal AIAI using several information types, such as text, images or sound, in inputs or outputs.
- Optical character recognitionOptical character recognition makes writing in images machine-processable. Reading an amount is not the same as checking an invoice against business rules.
- Sentiment analysisEstimating the attitude expressed in text, such as positive, negative or neutral; it does not replace assessment of the underlying business issue.
Articles on this topic
AI & Automation with ASES
AI assistants and automated workflows