# glample/tagger

Named Entity Recognition Tool

Repository: https://github.com/glample/tagger
Canonical: https://ross.abutalabs.com/products/tagger
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2019-05-27T13:38:50+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3829, "days_push": 2655, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1175, forks 424 (observed 2026-08-28T04:03:52.396590+00:00)

## What it is
A Named Entity Recognition (NER) tool implementing a state-of-the-art LSTM-CRF model that works across languages without gazetteers. It ships with pretrained models for English, Spanish, German, and Dutch and supports training custom models on CoNLL-formatted data.

## Use cases
- tag named entities in text
- run named entity recognition on tokenized sentences
- train a custom NER model on CoNLL-formatted data
- recognize entities in English, Spanish, German, or Dutch
- evaluate NER models on CoNLL datasets

## When to choose
- you need a pretrained NER tagger for CoNLL languages without language-specific resources
- you want to train and tune an LSTM-CRF NER model on your own IOB-formatted data

## When to avoid
- you need a maintained tool or modern framework support (requires Python 2.7 and Theano)
- you need NER for languages outside the four pretrained ones and lack training data
- you want transformer-based or GPU-accelerated modern NER models

## Facets
- artifact type: library
- maturity: abandoned
- function: nlp, machine-learning, deep-learning
- domain: machine-learning
- platform: python
- tags: named-entity-recognition, ner, lstm-crf, theano, pretrained-models, conll, natural-language-processing, linux, macos

## Member repositories
- glample/tagger (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:52.396590+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 2026-08-30T06:27:05.357984+00:00, confidence not recorded.
  - readme: https://github.com/glample/tagger (fetched 2026-08-28T04:03:52.396590+00:00, sha 1604f786d93d)
- Data as of 2026-08-30T08:39:29.467469+00:00.