This repository is a comprehensive project that leverages the XLM-Roberta model for intent detection. This repository is a valuable resource for developers looking to build and fine-tune intent detection models based on state-of-the-art techniques.

This is the official repository of Team Anastasia, which achieved 1st place in Subtask 1 of the SemEval 2025 challenge.

Using machine learning to analyze trends in hate speech

Hallucination in Chat-bots: Faithful Benchmark for Information-Seeking Dialogue

Implement an Intelligent Form Agent that can process and understand a wide variety of forms. It answers to questions related to individual forms, and generate holistic insights when analyzing multiple forms together.

This project contains codes and paperwork based on the course CSI5386 at University of Ottawa (delivered by Professor Dr. Diana Inkpen).

Emotion Analysis with Transformers

Developed a project which detects the news either as fake or real. GPT2 transformer model is used to predict the sentiment and genre of news. Classifier Machine Learning models and Hugging Face Transformer-Based language models are used to classify the news

An approch to implement embeddings alignment from a latent space to another one

More and more people are exchanging text messages through the use of social media, and the analysis of the information can be used to make statistics in the behavior and in people's psychology. Using Natural Language Processing (NLP), we can extrapolate key words from each message that allow us to achieve the proposed goals.