PyThaiNLP/pythainlp

Thai natural language processing in Python

What it solves

PyThaiNLP is a comprehensive library for Thai Natural Language Processing (NLP), designed to be a Thai-focused counterpart to NLTK. It provides the essential linguistic analysis tools needed to process and analyze Thai text, which often lacks clear word boundaries, making standard NLP tasks more challenging.

How it works

The library provides a set of Python functions and models to handle various Thai linguistic tasks. It includes built-in Thai character sets, word lists, and stop words, and can be extended with optional dependencies for machine translation and WordNet support. It also features a command-line interface (CLI) for quick data cataloging and analysis.

Who it’s for

Developers, researchers, and data scientists working with the Thai language who need a standardized set of tools for linguistic analysis, text processing, and Thai-specific linguistic utilities.

Highlights

  • Linguistic Units: Supports sentence, word, and subword segmentation (tokenization).
  • Tagging: Provides part-of-speech (POS) tagging.
  • Transliteration: Handles Romanization and IPA conversion.
  • ** umaCorrection:** Offers spelling suggestion and correction.
  • Utilities: Includes tools for Soundex, collation, number-to-text (bahttext), and Thai-specific datetime formatting.
  • Data: Includes built-in Thai character sets and stop words.

Related

  • Project
    hankcs/HanLP

    HanLP is a multilingual NLP library (Python/Java) offering pre‑trained models for tokenization, POS, parsing, SRL, AMR, etc., across 130 languages. It provides both native Python APIs and tiny RESTful clients for easy integration, emphasizes reproducibility, and is released under Apache 2.0 (code) and CC BY‑NC‑SA 4.0 (models).

  • Project
    nltk/nltk

    The Natural Language Toolkit (NLTK) is a suite of Python modules and data sets that supports research and development in Natural Language Processing.

  • Project
    ixaxaar/pytorch-dnc

    A PyTorch library implementing Differentiable Neural Computers (DNC), Sparse DNC (SDNC) and Sparse Access Memory (SAM) with install instructions, API usage, debugging support, and example training tasks (copy, addition, argmax).

  • Project
    dongrixinyu/JioNLP

    A Python library for Chinese NLP preprocessing and parsing, providing tools for data cleaning, entity extraction, and automatic LLM evaluation.

  • Project
    SAIL-Research-Lab/cheetahclaws

    A Python-native agent harness for AI coding assistants that supports any LLM provider or local model, offering a hackable alternative to closed-source agent frameworks.