LIMA - Libre Multilingual Analyzer: multilingual text analysis

LIMA – Libre Multilingual Analyzer

LIMA is a multilingual natural-language-processing toolkit in C++ with neural modules for tokenization, part-of-speech tagging, morphological analysis, lemmatization and dependency parsing, plus ModEx for rule-based extraction of entities, relations and events.

Independent OpenViST project profile, based on linked sources.

Understand the project

Practical overview

When it fits

Use LIMA when linguistic analysis or information extraction needs to run inside a software workflow, and choose the Python quick start for the documented Linux setup.

Who it is for

Developers building multilingual text-processing applications.
Teams that need linguistic annotation or domain-specific entity, relation and event extraction.

Documented uses

Tokenize text and assign part-of-speech and morphological information.
Lemmatize text and parse dependency relations.
Extract entities, relations and events with rules in domains lacking annotated data.

Before you choose

Requirements & limits

The project describes LIMA as free software under the MIT license. The documented Python quick start requires Linux x86_64 and Python 3.7 or later.

The README identifies models for more than 60 languages.
Neural modules cover core linguistic analysis; ModEx provides a separate rule-based route for extracting entities, relations and events.
The README documents a Python quick start and points to Docker and source-build options in the installation guide.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up and run LIMA with the Python package

Install the documented Linux Python package, retrieve the English model and analyze a short string.

Before you start

Linux x86_64
Python 3.7 or later

Steps

Run the command below.
Documented command
```
pip install --upgrade pip
```
Install the package with the command below.
Documented command
```
pip install aymara==0.5.0b6
```
Retrieve the English model with lima_models -i eng.
Import aymara.lima, create Lima("ud-eng"), and pass text to the analyzer as shown in the README.

Expected outcome

A Python application can instantiate the English LIMA analyzer and obtain a document representation for input text.

Guide limitations

The quick start specifies Linux x86_64 and Python 3.7 or later.
The documented example processes a short string; it does not describe a complete production pipeline.

Documentation 1 ↗

Evidence and transparency

Sources & review

Official repository ↗

Source record details

Source availability: Active
Sources checked: 18 October 2026
Original website title: aymara/lima · Official homepage title · retained in its source language

How we review sources Suggest a correction