mit-nlp/MITIE

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

2962 stars · 532 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

MITIE is a C++ library and toolset for information extraction, providing named entity recognition and binary relation detection built on dlib with structural SVMs and distributional word embeddings. It ships pre-trained English, Spanish, and German models and offers bindings for Python, Java, R, C, and community bindings for other languages.

Use cases

• extract named entities from text
• train a custom NER model
• detect binary relations between entities in documents
• run NER from the command line on a text file
• add entity extraction to a Python or Java application
• perform multilingual NER in English, Spanish, or German

When to choose

• you need free-for-commercial-use NER with pre-trained models
• you want to train custom entity or relation extractors on your own data
• you need a fast C/C++ core with bindings for Python, Java, or R

When to avoid

• you need modern transformer-based NLP accuracy or broad language coverage
• you want an actively maintained Python-first ecosystem like spaCy or Hugging Face
• you need tasks beyond NER and relation detection, such as full NLP pipelines

Facets

library · maturity active

nlp machine-learning parser machine-learning cpp python jvm cross-platform cli named-entity-recognition information-extraction relation-detection word-embeddings c-api pretrained-models natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mit-nlp/MITIE")