Text classification model - Bs.c degree final project

Utilizing AI and machine learning, the project extracts text from images via Apple's Vision Framework and offers instant answers to questions in documents through the BERT model.

Exploring Python-based projects

In this project we have tried to do multi-label hate-speech classification in Bengali and Hindi language using fill-mask transformer models.

This project utilizes the power of BERT (Bidirectional Encoder Representations from Transformers) for sentiment analysis

Enrutamiento de preguntas médicas

🗨️ This repository contains a collection of notebooks and resources for various NLP tasks using different architectures and frameworks.

Slides about my research at the Oxford Internet Institute.

This repository contains the code and data for the text re-identification attack presented in B. Manzanares-Salor, D. Sánchez, P. Lison, Evaluating the disclosure risk of anonymized documents via a machine learning-based re-identification attack, Submitted, (2024)

Code for searching the English Wikipedia dataset with semantic search using Elasticsearch and the BERT algorithm.

EconBERTa is a large language model pretrained on scientific publications in economics, and ECON-IE is a new expert-annotated dataset of economics abstracts for Named Entity Recognition (NER).

This tool helps businesses, understand customer sentiment surrounding their products and brand. Through insights extracted from reviews.

Deep Learning, Attention, Transformers, BERT, GPT-2, GTP-3

😷 The Fill-Mask Association Test (FMAT): Measuring Propositions in Natural Language.

Projekt u sklopu predmeta Obrada prirodnog jezika

This project involves analyzing and classifying the BoolQ dataset from the SuperGLUE benchmark. We implemented various classifiers and techniques, including rules-based logic, BERT, RNN, and GPT-3/4 data augmentation, achieving performance improvements.

Tools for Arabic language processing using the MADAR dataset. Includes Next Word Prediction with an n-gram model and Dialect Identification with a BERT model. Features an interactive UI with Streamlit and comprehensive text preprocessing for Arabic.

qlamda: txt2ques generation model

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at [email protected].

The "LLM Projects Archive" is a centralized GitHub repository, offering a diverse collection of Language Model Models projects. A valuable resource for researchers, developers, and enthusiasts, it showcases the latest advancements and applications in the realm of LLMs. Explore and contribute to the dynamic landscape of language model projects.