Hate Speech classification in Italian using XLM (fine-tuning). Published at the WOAH workshop (NAACL2022).

This repository contains my scripts, results and visualization for my bachelor thesis "Medical concept PROBLEM: Polarity, Modality and Temporal Relations" - ON GOING, doing some code reorganize

This is the official implementation of our paper Robust Hate Speech Detection via Mitigating Spurious Correlations (Tiwari et al., AACL-IJCNLP 2022)

Final project for the "Deep Natural Language Processing" course @ PoliTo, 2022/2023

https://arxiv.org/abs/2201.06499

Simple user-friendly webpage for spam classification of email and sms texts using a fine-tuned BERT base model (cased)

DACON 기후기술분류 경진대회 at @KNU-BrainAI (2021)

Scrap, token classification and model deployment for a selective process.

Its main goal wasn't to develop the solution with the best accuracy among others developed by Kaggle's community but rather to understand the applicability of the MLflow framework and how to use it to track different models during the training and evaluation steps, while also learning about the model's versioning and registry.

This cryptocurrency market sentiment analysis tool leverages a fine-tuned RoBERTa model for 98% accurate sentiment classification of cryptocurrency-related news articles. It uses Selenium and BeautifulSoup for web scraping news articles and provides insightful market sentiment analysis and data visualization

Applying Natural Language Processing Techniques to classify text from various sources

Training code and public data for the paper "A Legal Approach to Hate Speech - Operationalizing the EU's Legal Framework against the Expression of Hatred as an NLP Task"

BERT Model 2: Annotation and Fine-Tuning Deep-Learning Model for Passage Boundary Detection

Accessing the Writing skills of a document/author by classifiying the statements and sentences into different classes based on the sequential learning using Pre-trained models from BERT. Rating the document based on the score obtained from the classes for each statement/sentence.

Machine learning model trained on 520K social media comments generating sentiment analysis based on usage of emojis in comments.

This repository powers a Streamlit app for classifying text with respect to 16 of United Nations Sustainable Development Goals (SDG)..

A set of Python scripts that creates a dataset of bill texts and subjects, then fine-tunes BERT on the dataset.

The code for "Sarcasm Detection with Commonsense Knowledge"