Solutions to Exercism exercises.

Using Stanford's CoreNLP, 'stanza', module to convert scraped reviews (TripAdvisor - Airlines) into CoNLL formatted .tsv files (for a sequence labelling task)

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

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.

This project aims to implement word-based, character-based and subword-based tokenization techniques.

This project aims to implement the charCNN word embedding method that is leveraged in ELMo and characterBERT.

Code for sentence analysis and feature extraction using NLP

Dockerized Stanza as API. Easy config and cached models.

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.

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

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

A rule-based RE

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

An extractor of keywords for Estonian texts.

An easy-to-use library to linguistically compare one sentence and its words to another, in the same language or a different one. For instance useful for comparing a translation with the original text, to find differences and similarities between two different translations, or to see how a machine translation differs from a reference translation.

Graduation project aimed at composing multiple-choice questions for learning Ukrainian grammar. Best suited for A1 level of fluency in Ukrainian.

script de entrenamiento de un chatbot con nltk

The NLP project which aggregates information about rocket strikes happening during the russian invasion of Ukraine since Feb. 24.

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

This project aims to implement the result of the sentence-level and word-level polarity of a given text.