#nlp

Smart expansion of Spanish legal acronyms. 647 verified acronyms from RAE, BOE and DPEJ. | Expansión inteligente de siglas legales españolas.

Collection of string similarity and distance algorithms in PHP including Levenshtein, Damerau-Levenshtein, Jaro-Winkler, and more

Python port of Moses tokenizer, truecaser and normalizer

An ONNX implementation of GLiNER 1 and 2

Calculate syllable count for English words.

该仓库未发布描述。

Modern TypeScript implementation of EDTF (Extended Date/Time Format) with natural language parsing

Decoupled decision heads (Choice, Score, Flag) on a shared semantic backbone - local, deterministic, no model training.

An Elixir wrapper around the Rust Lingua language detection library.

HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382

Sandbox for Deep-Learning based Computational Protein Design

Agent Session Manager - A comprehensive Elixir library for managing AI agent sessions, state persistence, conversation context, and multi-agent orchestration workflows

A Cython MeCab wrapper for fast, pythonic Japanese tokenization and morphological analysis.

Rust port of Misaki

🔤 Natural language detection for Elixir without AI

Fast and accurate natural language detection. Detector written in PHP. Nito-ELD, ELD.

Parse partial JSON generated by LLM

📟 Logging utilities for spaCy

Turbo Module integrating cppjieba for React Native.

Text tokenizer for linguistic purposes, such as text matching. Supports more than 40 languages, including English, French, Russian, Japanese, Thai etc.