# mit-nlp/MITIE

MITIE: library and tools for information extraction

Repository: https://github.com/mit-nlp/MITIE
Canonical: https://ross.abutalabs.com/products/mitie
Language: C++
License Family: other
Topics: machine-learning, natural-language-processing, information-extraction, python, c-plus-plus, java
Last push: 2025-09-28T14:46:03+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 44, release rhythm 8, longevity 100
- inputs: {"age_days": 4537, "days_push": 339, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2962, forks 532 (observed 2026-08-28T04:07:32.365277+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: nlp, machine-learning, parser
- domain: machine-learning
- platform: cpp, python, jvm, cross-platform, cli
- tags: named-entity-recognition, information-extraction, relation-detection, word-embeddings, c-api, pretrained-models, natural-language-processing

## Member repositories
- mit-nlp/MITIE (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:32.365277+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:32:08.838538+00:00, confidence not recorded.
  - readme: https://github.com/mit-nlp/MITIE (fetched 2026-08-28T04:07:32.365277+00:00, sha f11c9b542156)
- Data as of 2026-08-30T08:39:29.467469+00:00.