Information Extraction & NER
Pick names, places and relations out of free text
WHAT THIS CAPABILITY MEANS
Takes natural-language text and returns structured fragments: typed entities (person, organisation, date, amount) plus the relations or events among them. Unlike classification it does not give one label to the whole text but locates spans; unlike schema-driven structured output, the extracted targets come from the text itself rather than a fully prescribed field list.
How it is done
Early systems used conditional random fields or rule-based sequence labelling, tagging tokens BIO-style; pre-trained encoders with a tagging head then became standard. Relation and event extraction are often framed as entity-pair classification or as generation of triples directly. More recently, large models perform few-shot or zero-shot extraction against a given schema, avoiding per-type annotation.
Representative products
5GPT-4o
2024A natively multimodal general model, with text, image and audio through one door
Qwen
2023An open-weight family spanning many sizes, with multimodal versions
ERNIE
2019A Chinese model that began with knowledge-enhanced pretraining, an early landmark version
Doubao
2023ByteDance’s general chat model and application
GLM
2023A Chinese general model that began with autoregressive blank-infilling pretraining
Organizations involved
Typical uses
- Clause and amount extraction from contracts and filings
- Résumé parsing and talent-pool building
- Drug and symptom recognition in clinical notes
- News events and knowledge-graph construction
How it is evaluated
- Span-level F1
- A hit requires both boundary and type to be correct
- Relation F1
- Share of triples (head, relation, tail) matched exactly
- Exact-match rate
- Share of records whose fields are all correct
Limits and hard parts
- Nested and overlapping entities are flattened by token-level tagging schemes
- Cross-sentence coreference is hard; pronouns bind to the wrong antecedent
- Domain terms and novel words are missed when the type was unseen in training
Concepts behind it
Tokenization
Models do not read characters, they read tokens — and how you split text quietly sets both capability and cost
Pretraining & Fine-tuning
Learn language first from vast unlabelled text, then specialise with little data — the most data-efficient paradigm in modern AI
Supervised Learning
Pairs of questions and answers teach a model to answer on its own