Open Source Python Linguistics Software - Page 3

SpeakingInNumbers converts numbers into pronounceable pseudo words.

Sylli is a universal syllabifier. Developed for Italian, it can easily be adapted to any language that is claimed to respect the SSP. Sylli divides timit, strings, files and directories into syllables.

TextTools is a freeware corpus linguistics tool developed in Python to aid in research. This program analyzes user-created corpora and displays information about word (token) frequency, n-grams, clusters, collocations, keyword in context (KWIC), and keyness. TextTools is designed to be user-friendly and intuitive and will run natively on Mac OS X.

This tool performs token-by-token alignment of two versions of a text with differing tokenization by interpreting the results of a file diff (https://docs.python.org/3/library/difflib.html). It is intended for use in the preparation of annotated linguistic corpora, where differences in tokenization may arise (i) following corrections or modifications to the source text or (ii) through the creation of different layers of annotation (part-of-speech, treebank) requiring different tokenization. In its default implementation, it produces a human-readable CSV table associating tokens in text A with tokens in text B, and can also inject token-level annotation from text B to text A. The Aligner class on which the default implementation is based can be incorporated into more complex workflows.

This tool translates the text of the selected language to the language of your choice in the status bar and add the translated text in a note. Esta ferramenta traduz o texto do idioma selecionado para o idioma de sua escolha na barra de status..

Translation Agent is a Python demonstration of an agentic translation workflow that uses reflection to improve machine translation quality. Instead of asking a language model for a single direct translation, it first generates a translation, then asks the model to critique it, and finally uses that critique to produce a stronger version. This structure makes the system more steerable than a traditional translation pipeline. Users can adjust prompts to control tone, formality, terminology, idiom handling, and regional language choices. The project includes example scripts and a simple Python interface for translating between source and target languages. It is useful for researchers, developers, and localization teams exploring how LLM-based workflows can produce better, more customizable translations.

The Varro toolkit is a system for identifying and frequently recurring unordered subtrees in semi-structured data. It is mostly for linguistics but has applications in semi-structured data mining too.

This project is an approach for synonym extraction and extending WordNet by the so found synonyms. The python application is realised as a kind of pipe that starts with a web-corpus-reader which is followed by several workers (tokenizers, lemmatizers, ...) and finally completed by a result writer. In contrast to the state of the art approaches, this implementation is based on single words found in the web used as a corpus and translated to other languages. If translations of different source words intersect, it is assumed that the source words are synonymous. Finally, the matches are written into a proprietary file format in conjunction with WordNet synsets (note currently the result writer uses a very trivial method for placing the matches into WordNet and will be modified in the near future)

WordNetLMF converts WordNet (http://wordnet.princeton.edu/) lexicographer files into KYOTO-LMF, the LMF dialect used in the KYOTO project (http://www.kyoto-project.eu/).

This program is a web application to collect and organize data of text analysis. It works with sets of texts and the analysis are done on portions of the length of a sentence. One of the preprocessing modules is based on CoGroo (A LibreOffice & OpenOffice.org Portuguese Grammar Checker).

A Python module for EuroWordNet files and data.

Melete is a program to apply sound changes to a lexicon, simulating historical linguistic sound changes. It supports a flexible and easy to use format for specifying sounds, characters and diacritics, support for phonological features, and more.

Extracts MultiWord Units using the LocalMaxs algorithm by Silva and Lopes 1999.

This project aims at building an efficient indexer and search engine for natural language corpora with multilevel annotations.

Moved to Github: http://github.com/tremby/py-translate

Python API to the german wordnet GermaNet. In the current state this can be only seen as a quickstart-help to access GermaNet. To be honest, this API can't be called API. To use it, you will need access to a licensed copy of GermaNet (version > 5).

YA BASTA! is a Python/R application for Lyrics Web Scraper and Text Analysis. Web scraping is developed in Python, text analysis in R as Python subprocesses. YA BASTA! is only tested on windows OS. To run YA BASTA! just type on window command prompt: python.exe yabasta.py