Open Source Python Linguistics Software

The central problem to be addressed in this project concerns a multidisciplinary (linguistics and computational linguistics) investigation into sharing of knowledge and resources between closely-related languages, specifically relating to the automatic processing of compounds. Specifically, we will explore the possibility to create new knowledge about closely-related languages, and efficiently develop additional, more advanced resources for (a) compound segmentation; and (b) the semantic analysis of compounds; as such, the project will be divided into two interrelated subprojects, to be executed simultaneously. The focus in this project will be on Afrikaans (with Dutch as the closely-related, well-sourced language), which will lay grounds for future work on other closely-related language pairs.

The program will turn a color into a list of 10 words, obtained according to a custom designed algorithm based on letter shape and position in the alphabet. - Click inside the frame on the left to pick a color through the color chooser window - The program will match the color with the colors corresponding to a list of all the English words contained in the file wordcolor.txt - The first 10 matches will appear in the frame on the right - Right-click - Copy to copy the word matches and the RGB values This version comes with a text file (wordcolor.txt) containing all the English words followed by Red, Green, Blue channel values for the corresponding color. The colors were obtained through a modified version of the program "Text to Color" by same author, available for download on GitHub and SourceForge on the profile page of Fonazza-Stent. The next version (coming soon) will include a tool to convert a custom word list into a word+color list named wordcolor.txt

An agent-based situated language learning simulation that focuses on lexical learning and grounding, featuring a unigram syntax structure and a CFG-based semantic grammar. Created as a MSc thesis project, using python.

KAF2Tiger2 is a KAF (KYOTO annotation format) to <tiger2/> (Tiger2 XML) converter.

Little Cohesion Helper (LCH), alias TraglWeck, semi-automates the annotation of lexical-cohesion in a given text. Input is a raw text file and this software generates a bunch of XML files which can be used with MMAX2.

PyAnnotation is a Python Library to access and manipulate linguistically annotated corpus files. Supported file formats are Kura XML, Elan XML and Toolbox files. A Corpus Reader API is provided to support statistical analysis within the NLTK.

Pylero is an open-source Python-based text generator.

The Rudify tools are a collection of tools for ontology tagging.

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 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).

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.