Developed a Python desktop application for collecting, analyzing, and reporting on unstructured text data from a public Telegram group.

The Classical Language Toolkit

Measuring Slovak law's growing word count (and other metrics)

A rule-based RE

A post-processing pipeline to fact-check, entity-link, and verify answers from Large Language Models (LLMs). Developed for the Web Data Processing Systems course at Vrije Universiteit Amsterdam.

too many unstructured data, alok has too many req, seeing what helps

A comprehensive desktop application designed for intelligent text analysis and linguistic processing. Built with Python and tkinter, it provides advanced natural language processing capabilities including word frequency analysis, named entity recognition, pattern extraction, and multi-language support with automatic language detection.

Some APIs around AI models, for NLP, with docker image.

Multi-model sentiment analysis REST API using NLTK, TextBlob, Flair & Stanford CoreNLP. Features 6 endpoints, Docker support, comprehensive tests, and 99% accuracy on social media data.

A production-ready Python application for automated vendor due diligence that leverages advanced NLP and web automation to analyze online risk, generate contextual reports, and archive web evidence as PDFs—all through an intuitive, modern GUI.

Bidirectional, Expandable and Stacked Tagger --- BEaST. This package provides POS-tagging using a system composed of treetagger, spaCy and Stanza. Package also provides training of a new system provided the necessary files.

id-svo-extractor: Extract SVO triples from Indonesian text.

A Python XMPP client with authentication, contact and group chat management, and a Tkinter interface.

📱 This project implements an instant messaging client that supports the XMPP protocol. 💻

💥 Use the latest Stanza (StanfordNLP) research models directly in spaCy

Pipeline component for spaCy (and other spaCy-wrapped parsers such as spacy-stanza and spacy-udpipe) that adds CoNLL-U properties to a Doc and its sentences and tokens. Can also be used as a command-line tool.

Dockerized Stanza as API. Easy config and cached models.

Solutions to Exercism exercises.

ThamizhiMorph: A Tamil Morphological Analyser and Generator

Code for sentence analysis and feature extraction using NLP